OpenClaw is a comprehensive self-hosted AI agent control plane that orchestrates autonomous tasks across multiple communication channels and LLM providers. The system functions as a gateway-server architecture, managing agent sessions, tool execution, and persistent memory via SQLite. It features a robust plugin system that decouples channel integrations (Discord, Telegram, WhatsApp, etc.) and model providers (OpenAI, Anthropic, Ollama) from the core runtime, allowing for extensible capabilities without modifying the base application. The platform supports cross-platform deployment including a Node.js CLI, a WebSocket-based gateway, and native companion applications for macOS, iOS, and Android. The architecture emphasizes security and safety, implementing sandboxed tool execution via Docker, strict file system safety wrappers, and centralized secret management. It utilizes a monorepo structure with pnpm, featuring extensive test coverage through Vitest and contract testing to ensure plugin compatibility. The codebase demonstrates high craftsmanship in its plugin SDK design, configuration validation using Zod schemas, and security patterns for exec approval and SSRF guards. However, the sheer scale of the repository (20k+ files) and the high volume of open issues (6745) indicate significant complexity and maintenance overhead. While the project is actively maintained with recent commits, the technical drift is moderate due to the reliance on volatile external APIs (messaging channels, LLM providers) and the use of bleeding-edge dependencies like Node 24. The codebase is suitable for engineers seeking a production-grade, extensible agent platform, though the complexity requires careful navigation. The quality is high, with reusable components for security, configuration, and plugin architecture, but the issue backlog suggests ongoing architectural challenges.

ClawHub is a full-stack registry marketplace for AI agent skills and OpenClaw plugins. It provides a web application (React + TanStack Router + Convex backend), a CLI tool (clawhub) for publishing and managing skills, an admin CLI for moderation, and a public HTTP API. The system handles skill/plugin publishing, versioning, search (with OpenAI embeddings), trending leaderboards, security scanning (VirusTotal, ClawScan, static analysis), moderation, and catalog feeds. It also mirrors an external skills.sh catalog. The architecture is a monorepo with shared schema packages, extensive test coverage (unit, e2e, Convex), and CI/CD via GitHub Actions. While primarily an application, it includes data/research elements like security dataset export and ranking metrics pipelines.

gog is a comprehensive, production-grade CLI tool for Google Workspace automation that unifies 20+ Google services (Gmail, Calendar, Drive, Docs, Sheets, Slides, Forms, Meet, Chat, Contacts, Tasks, Classroom, YouTube, Analytics, Search Console, Admin, Groups, Keep, Photos, Maps, Apps Script) into a single binary. It excels at task-first workflows: searching and sanitizing mail, resolving calendar names, auditing Drive sharing, editing Docs, appending Sheet tables, building Slides from Markdown, managing Workspace users, and performing encrypted backups. The architecture is a modular monolith with clean internal package boundaries for each service domain. Key entry points are cmd/gog/main.go and the Kong-based command tree in internal/cmd. Primary data flows: command invocation -> account/client resolution -> authenticated Google API client creation -> API execution -> structured output (JSON, plain TSV, or human-readable tables). External dependencies include Google APIs, OAuth2, keyring backends (macOS Keychain, Windows Credential Manager, Linux Secret Service, encrypted file), MCP for agent integration, and age encryption for backups. The codebase demonstrates exceptional craftsmanship in cross-platform secret storage, Gmail push notification processing, sed-style Docs editing with UTF-16 index tracking, atomic Docs request batching, encrypted backup with Git shard checkpointing, email open tracking with versioned key rotation and bot detection, and build-time safety profile compilation to hash-based allow/deny switches. Active development with recent commits, comprehensive test coverage (unit + integration + live tests), and modern dependency versions.

Peekaboo is a mature macOS desktop automation toolkit that provides a CLI, Mac app, and MCP server for screen capture, UI element detection, input synthesis, window management, and AI agent integration. The architecture is modular: a Swift CLI (peekaboo) exposes ~33 commands for interaction, system control, and AI agent orchestration; a Mac app provides a menu bar interface, session management, and visualizer overlays; a bridge daemon (PeekabooBridge) enables secure remote automation via a versioned socket protocol with operation allowlisting. The MCP server exposes native automation tools to AI clients (Claude, Cursor, etc.) via stdio transport. The agent runtime (PeekabooAgentService) supports multiple AI providers (OpenAI, Anthropic, Ollama, etc.) with streaming, tool calling, and session persistence. The codebase is written in Swift 6.2 with strict concurrency, extensive unit/integration tests, and a focus on safety (fail-closed target validation, honest effect reporting). It is not a data research project; it is a production-grade application for macOS automation.

mcporter is a portable Model Context Protocol (MCP) runtime, CLI, and code-generation toolkit. It connects to configured MCP servers—over stdio, HTTP/SSE, or Chrome DevTools relay—and exposes their tools via a rich command-line interface (subcommands: list, call, resource, auth, config, serve, daemon, generate-cli, emit-ts, record, replay) and a programmatic API (createRuntime, createServerProxy). The architecture is modular: a config layer merges JSON/JSONC files and imports from common editor configs (Cursor, Claude, VS Code); a runtime layer manages transport connections with OAuth support, record/replay, and error classification; a daemon process pools keep-alive servers for low-latency reuse; and a codegen subsystem produces standalone CLIs or typed TypeScript clients from server schemas. The codebase is heavily tested (~150 test files, coverage ≥89.6%), follows modern TypeScript patterns, and supports protocol versions from 2024-10-07 to 2026-07-28. It is not a data pipeline or research project—it is a production-grade developer tool for integrating MCP-powered agents and workflows.

acpx is a headless CLI client and runtime for the Agent Client Protocol (ACP), enabling orchestration of AI agent sessions with persistent state, multi-step flow execution, permission policies, and a replay viewer for auditing. The architecture combines a CLI entry point, an embeddable runtime (AcpRuntime), a queue-based IPC system for shared session access, and a separate React-based replay viewer for inspecting flow run bundles. It supports 20+ built-in agents (Claude, Gemini, Cursor, etc.) via ACP, manages session persistence as JSON files with event logs, and provides output formatting in text, JSON, or quiet modes. The codebase is predominantly TypeScript with extensive test coverage (85%+), conformance testing against the ACP specification, and platform-specific process management for Windows and POSIX systems.

OpenClaw Windows Node is a native Windows system-tray companion application for the OpenClaw AI agent ecosystem. It provides a full desktop experience for managing gateway connections, executing AI agent workflows with local and remote models, and controlling Windows capabilities (camera, screen, location, browser proxy, speech I/O) under granular permission and sandbox policies. The application is built with WinUI 3 and .NET 10, and features a complex multi-process architecture including a WSL-based gateway installer, a native MSIX gateway runtime, a Reactor chat surface with markdown rendering, a local AI inference subsystem (CUDA, Whisper STT, Piper TTS, Ollama), and an extensive exec approval pipeline with allowlist/deny/prompt modes and confusable command detection. The codebase exhibits strong engineering discipline with high test coverage (unit, integration, UI, accessibility, and source-contract tests), clean separation of concerns via dependency injection, and reusable patterns for concurrency control, file-based leasing, URL safety, and telemetry. It is actively maintained with regular CI, code review automation, and GitHub triage workflows.

ClawSweeper is a production GitHub App and CLI that autonomously reviews issues and pull requests across OpenClaw repositories, writes durable markdown reports with YAML front matter, applies conservative close/merge/repair actions behind policy guards, and runs Codex/OpenClaw-powered fix, automerge, and issue-implementation repair pipelines. It is deployed as a set of GitHub Actions workflows plus a Cloudflare Workers dashboard backed by Durable Objects, R2, and a separate git state repository with ledgers, canonical record tuples, and telemetry. This is a hard operational bot, not a library or user-facing product; it consumes GitHub webhook and scheduled sweep data and emits state, review records, notifications, and merge/close mutations.

Crabbox is a production-grade, multi-provider remote development environment orchestrator. The core is a Go CLI that provisions ephemeral sandboxes, VMs, and containers across 60+ cloud and virtualization backends (AWS, Azure, GCP, Hetzner, Firecracker, Docker, KubeVirt, Nomad, and many delegated-run services). Users issue commands like `crabbox run`, `warmup`, `connect`, `ssh`, `vnc`, and `cp`; the CLI leases a remote host, syncs a workspace archive, executes commands or opens interactive sessions, collects artifacts and test results, and tears the resource down. A Cloudflare Worker/Node.js coordinator handles lease state, provider reconciliation, artifacts, and runtime-adapter relays, while a Swift/Virtualization.framework daemon supports Apple VM backends. This is an application, not a research or data-analysis project, though it emits operational telemetry and parses remote JUnit results as part of its execution pipeline.

This repository is a macOS iMessage/SMS automation tool called `imsg`. It provides a CLI and JSON-RPC interface for reading, watching, and sending messages. The architecture has three layers: a Swift CLI that parses commands and outputs NDJSON or plain text; a core library (`IMsgCore`) that reads the local Messages SQLite database and manages the bridge to Messages.app; and an injected Objective-C dylib (`IMsgHelper`) that hooks into private IMCore APIs for advanced features like typing indicators, polls, stickers, rich links, and message mutations. The tool can fall back to AppleScript automation for basic sends when the bridge is unavailable (e.g., SIP enabled). The RPC server runs over stdio, making it suitable for integration with AI agents and scripts. The codebase is well-tested with unit tests for all layers, including native Objective-C tests for the injected helper. It demonstrates deep reverse-engineering of Apple's private messaging protocols and careful handling of platform-specific quirks. The primary data flow is read-only from the local `chat.db` SQLite database for history and live updates, with write operations going through either AppleScript (via `osascript`) or the injected bridge (via UUID-keyed IPC queues). External dependencies include SQLite.swift, PhoneNumberKit, ffmpeg, afconvert, and private macOS frameworks (IMCore, CNContactStore). The build system uses SwiftPM with custom scripts for universal macOS binaries and Linux static archives. The project is actively maintained with CI, releases, and a documentation site.

Lobster is a local-first workflow runtime for AI agents, implemented as a TypeScript CLI and embeddable SDK. It executes deterministic pipelines defined in JSON, YAML, or .lobster files: steps are shell commands or built-in pipeline commands (where, pick, map, sort, groupBy, table, approve, ask, llm.invoke, openclaw.agent, etc.) connected through typed async-iterator data flow rather than text pipes. Pipelines support approval gates, interactive input, parallel branches, for_each loops, retry/timeout policies, on_error handlers, cost limits, and persistent state that can be suspended and resumed via base64url resume tokens. Architecturally it is a modular Node.js application: a core runtime (src/runtime.ts, src/core/tool_runtime.ts) with a command registry, a workflow file loader/executor, an atomic-file state store, an LLM cost-tracking and accounting layer, and a small SDK (src/sdk/index.ts). CLI entry points are bin/lobster.js, bin/openclaw.invoke.js, and bin/clawd.invoke.js. The package also ships GitHub and Gmail recipes that shell out to the gh and gog CLIs, and can delegate agent turns to OpenClaw. External dependencies are limited to those CLIs, the OpenClaw gateway/LLM adapters, and Node.js >= 22. Notable engineering strengths are crash-safe state persistence, idempotent LLM spend accounting, retry/backoff, abortable process-tree cancellation, and extensive tests covering resume, cancellation, concurrency, and billing edge cases. The repository is unambiguously an application; it has no data-research pipelines, notebooks, or analytics assets. It is a well-maintained, thoughtfully structured codebase with several independently reusable Node.js components.

This repository is the canonical source for **OpenClaw Agent Skills**, a collection of portable, reusable agent workflows (skills) for coding agents such as Claude Code, Codex, Pi, and OpenClaw. The primary deliverable is not a standalone application but a set of self-contained skills that provide automated code review (autoreview), redacted session publication (beam), session transcript provenance (agent-transcript), local session viewing (session-viewer), behavior validation (behavior-validator), and remote test orchestration (crabbox). Each skill lives under `skills/<name>/` with a required `SKILL.md` file and auxiliary scripts, tests, and references. The repository also includes cross-platform installer (`scripts/install-skills`) and validator (`scripts/validate-skills`) scripts that support symlink or copy installation into agent skill directories. Architecturally, the skills are independent of each other and are consumed by agents via direct symlink/copy. The most complex skill is `autoreview`, which performs a full AI-driven code review pipeline: capture git diff/commit/working-tree state, build a review prompt with evidence, invoke one of several engines (Codex, Claude, Amp, Pi) via subprocess, parse structured JSON reports, and produce a final review result with security hardening (isolation probes, credential scanning, terminal escape prevention). The `autoreview` script is monolithic (~80k tokens) but contains reusable patterns for safe subprocess environment sanitization, git diff collection, JSON extraction from noisy output, and engine isolation verification. The `session-viewer` skill provides a polished local HTML renderer for agent session JSONL files, with importers for multiple session formats. The `beam` skill focuses on redacted publication of coding sessions to a read-only catalog. The codebase demonstrates high engineering craftsmanship: extensive test coverage (Python unittest, Jest for TypeScript, shell-based harness), security-conscious patterns (symlink validation, stat-preserving writes, process group signal handling, environment sanitization), and cross-platform support (Windows, macOS, Linux via CI). The test suite is especially thorough for `autoreview`, covering edge cases like CRLF handling, binary files, merge commits, worktrees, shallow clones, and sensitive path patterns. The installer pattern (symlink for development, copy for vendored snapshots) is designed to minimize drift while allowing zero-setup downstream usage. Overall, the repository is actively maintained, uses modern tooling (Python 3.14, Node 26, TypeScript 7), and is well-suited for teams adopting agent-assisted development workflows who need reusable, vetted skill definitions.

discrawl is a Go CLI application for archiving and searching Discord data. It syncs messages from the Discord API, imports Discord desktop cache, stores raw JSON in SQLite via sqlc-generated code, and provides subcommands for sync, publish, subscribe, share import, and remote status. It also exports/imports compressed JSONL snapshots with manifests and commits them to a Git snapshot repo using NUL-delimited path-only commits to preserve unrelated staged work. The repository is primarily an application, but it also vendors agent skills (autoreview, crabbox, discrawl) under .agents/skills, making it a hybrid monorepo.

Clawpatch is an automated code review and repair CLI tool that maps a repository into bounded semantic feature slices, invokes external AI coding agents (Codex, Claude, ACPX, Grok, etc.) to review each slice for bugs and quality issues, and supports explicit fix workflows with validation. The architecture is a modular TypeScript application with a provider abstraction layer, language-specific feature mappers (Node, Python, Ruby, Go, Rust, C/C++, .NET, Java/Kotlin, Swift, Elixir, PHP/Laravel), state persistence via JSON files in a `.clawpatch` directory, and a safety-first design (read-only reviews, explicit fix commands, clean worktree checks, change auditing). Key entry points are the CLI (`src/cli.ts`) and application orchestrator (`src/app.ts`), with data flowing from project detection to feature mapping to provider-based review to optional fix/revalidation/PR creation. External dependencies include git, gh CLI, various AI coding CLIs, and the npm registry (optional). The tool is well-tested with Vitest, has extensive CI/CD, and demonstrates high craftsmanship in its provider abstraction, state management with locking, prompt building with provenance tracking, and review validation pipeline.

OpenClaw is a Nix flake that packages the OpenClaw AI assistant gateway for declarative installation on NixOS, macOS, and Home Manager. It provides a Home Manager module (programs.openclaw) and a NixOS module (services.openclaw-gateway) with options for instances, plugins, skills, workspace files, environment variables, and systemd/launchd services. The flake also includes an overlay, a Home Manager module for runtime plugins, and a set of Nix scripts that generate and validate plugin locks, config options, and runtime plugin materialization.

This is an Ansible role and playbook collection that automates the hardened installation of the OpenClaw messaging gateway on Debian/Ubuntu Linux systems. It provisions a dedicated system user, installs Docker CE with UFW-based firewall and DOCKER-USER chain isolation, configures fail2ban and unattended-upgrades, sets up Node.js and pnpm, and installs OpenClaw either from npm (release mode) or from a Git checkout (development mode). The role does not configure the application or install its systemd service—those steps are left to the operator via `openclaw onboard --install-daemon`. It supports remote deployment via inventory and includes CI tests for syntax, linting, and integration. The codebase is well-structured, security-conscious, and actively maintained, though it does not contain independently extractable components suitable for reuse outside this project.

remindctl is a macOS command-line interface for Apple Reminders, built with Swift and Apple's EventKit framework. It provides a comprehensive set of commands to create, edit, complete, delete, and search reminders, manage lists, set due dates, alarms, recurrence, location triggers, and URLs. The application is structured as a modular library (RemindCore) containing the core EventKit interaction and business logic, and a CLI executable (remindctl) that uses the Commander library for command routing and argument parsing. The CLI supports multiple output formats (JSON, plain, table, quiet) and includes advanced features like fuzzy list name resolution, stable numeric indexing across reordered fetches, and a custom async timeout pattern for system operations. The codebase demonstrates strong Swift concurrency practices (async/await, actors), comprehensive unit tests, and a well-documented release pipeline with signed notarized binaries and Homebrew distribution.

AXorcist is a Swift library and CLI tool for macOS accessibility automation, wrapping the Accessibility (AX) APIs to inspect, query, and control UI elements programmatically. The core library provides a typed `Element` struct over `AXUIElement`, a command-response protocol with JSON envelopes, a powerful observer system with retry/backoff and process-generation tracking, input simulation (mouse, keyboard), and tree traversal with search criteria. The CLI (`axorc`) exposes commands like `find`, `tree`, `raw`, `permissions`, and `observe`, all producing structured JSON output. The architecture is modular with heavy use of Swift extensions, `@MainActor` isolation, and async/await concurrency. The codebase is well-structured, extensively tested (unit and integration tests), and follows modern Swift practices with pinned dependencies (Commander, swift-log) and strict concurrency checking. It is actively maintained with CI workflows for building, linting, and security scanning.

This repository is the marketing website for OpenClaw, an open-source AI agent platform that runs locally and integrates with chat applications. The site serves as the primary distribution channel for installer scripts (macOS/Linux via shell, Windows via PowerShell), hosts a blog with technical product notes, an ecosystem catalog of ~70 open-source projects, press coverage, podcast episodes, and community testimonials. It is built as a static site using Astro 7 with TypeScript, deployed on Vercel, and leverages a custom design system (Carapace) for CSS tokens and components. The codebase is well-structured with reusable utility libraries, client-side interactive components (hero animation, integration rail, quickstart code selector), and comprehensive SEO/security measures (sanitized URLs, JSON-LD escaping, CSP headers). While primarily a marketing site, it also includes CI workflows for cross-platform installer testing and skill updates. The repository is actively maintained with frequent commits, dependabot updates, and a clear separation between website code and product installer scripts.

Tachikoma is a production-grade Swift SDK/library that provides a unified typed interface to a broad spectrum of LLM providers: OpenAI (Chat Completions, the newer Responses API for GPT-5+ generations, and a ChatGPT Codex OAuth backend), Anthropic (Claude with streaming signed thinking blocks), Google Gemini, Mistral, Groq, Grok/xAI, Kimi, MiniMax, OpenRouter, Together, Replicate, Ollama, LM Studio, Azure OpenAI, and arbitrary OpenAI/Anthropic-compatible endpoints. Its public surface is deliberately modeled on the Vercel AI SDK: generateText/streamText, generateObject/streamObject with partial-JSON repair, embeddings, vision analysis, and multi-step agent tool-calling loops. Beyond generation, it ships composable stop conditions, response caching, retry policies, usage/cost accounting, reasoning-effort controls, and a provider feature-parity adapter that normalizes differences in system roles, vision, and tool limits across backends. The repo is strictly an application SDK in character: no datasets, notebooks, or data pipelines. The one data-like facet is its manually curated model capability catalog (context lengths, pricing, per-generation reasoning support), which is embedded as Swift enums rather than external registries. Architecturally it is a SwiftPM monorepo of five products: Tachikoma (core generation/provider layer), TachikomaAgent (conversations, dynamic tool registry, MCP tool binding), TachikomaAudio (transcription, TTS, and an OpenAI Realtime WebSocket voice client), TachikomaMCP (a client for Model Context Protocol servers over stdio/SSE/HTTP with full JSON Schema bridging), and TachikomaConfigCLI (auth/credential helper), plus two example CLIs (ai-cli, gpt5cli). All providers implement a common ModelProvider protocol with ProviderRequest/ProviderResponse and AsyncThrowingStream-based streaming, with shared SSE/NDJSON parsing funneled through OpenAICompatibleHelper and provider-specific adapters for Anthropic, Google, and Ollama. The code is Swift 6.2, heavily async/await, and covered by a substantial test suite (Swift Testing, mock URLProtocol fixtures, snapshot tests, serialized mutex-guarded tests for shared state), with CI across macOS and Linux. The codebase exhibits strong engineering practice: clean provider abstraction, genuinely reusable utilities (stream transforms, retry policies, TTL caches, typed JSON Schema views), modular product boundaries, and disciplined error modeling. Its principal weaknesses are the enormous provider surface that must be manually maintained (hardcoded capability matrices, context-length string heuristics like isOpus48/isSonnet5, static pricing tables in ModelCostCalculator), a handful of @unchecked Sendable singletons and NSLock-guarded global state, Linux/Apple streaming divergence (Linux buffers the full response instead of streaming bytes), some dead placeholder APIs (the legacy generate() returning a mock string), and a rapid feature-churn cadence visible in the changelog (GPT-5.6/6, Claude 5, reasoning replay). These are maintainability risks more than correctness defects; the tested behavior is consistently thorough. Overall this is a high-craft SDK that an engineer building AI application features in Swift would benefit from studying, particularly its OpenAI-compatible adapter pattern, cache-key determinism, and MCP schema translation.

ClickClack is a production-grade, self-hostable team chat platform built for people, bots, and agents. The backend is a single Go binary serving a REST API with WebSocket real-time events, supporting both SQLite and PostgreSQL as interchangeable storage backends. The frontend is a Svelte 5 single-page application embedded into the Go binary, with an optional Electron desktop client and a TypeScript SDK for bot development. The system provides workspaces, channels, threads, direct messages, file uploads, full-text search, reactions, pinned messages, slash commands, event subscriptions, and push notifications (Web Push and Pushover). Authentication supports magic links, passwords (Argon2id), GitHub OAuth, and Cloudflare Access JWT. The architecture emphasizes security with SSRF-safe callback dialers, strict cookie namespacing, rate limiting, and bot scope enforcement. The codebase is notable for its dual-database store pattern with shared contract tests, a real-time event hub with cursor-based recovery, and a comprehensive test suite including unit, integration, and Playwright end-to-end tests. It is not a data research project; it is a fully featured application designed for self-hosting or cloud deployment.

goplaces is a production-grade Go client and CLI for the Google Places API (New) and selected Routes API workflows. It provides typed request/response structs, deterministic field masks for cost control, context support, and pluggable HTTP. The CLI offers eight commands (search, nearby, autocomplete, details, photo, resolve, route, directions) with both human-readable and JSON output. The repository includes an extensive release pipeline with code signing, notarization, reproducible builds, and Homebrew distribution. The codebase is well-structured with clear separation between CLI rendering, API client logic, and validation. It demonstrates strong engineering practices: high test coverage (≥90%), linting, vulnerability scanning, and hardened release scripts with pinned tool versions and multi-phase verification. The project is actively maintained with frequent releases and comprehensive documentation.

spogo is a terminal-based Spotify client written in Go that provides full control over playback, library management, search, and user listening data. It authenticates via browser cookies (sp_dc/sp_t) instead of the official OAuth flow, allowing it to bypass rate limits by using Spotify's internal web API endpoints (Connect/GraphQL) alongside the public Web API. The architecture is modular with multiple engine backends (connect, web, auto, applescript) and a clean CLI interface built with Kong. It features robust output formatting (human, JSON, plain), comprehensive error handling with documented exit codes, and extensive test coverage. While the tool is highly functional and well-crafted, its reliance on undocumented internal Spotify APIs and webpack hash resolution introduces fragility that may require maintenance as Spotify's frontend evolves.

Crabfleet is a cross-platform remote desktop application that enables users to access and control computers from anywhere. The system comprises a native macOS viewer app (Swift), a web viewer (TypeScript/Preact), a Linux connector (Go, X11/Wayland capture), a Windows connector (Go, GDI), and a backend infrastructure on Cloudflare Workers (D1 database, Durable Objects for relay). It uses the VNC/RFB protocol with custom extensions for H.264/HEVC video encoding, audio streaming, clipboard synchronization, and file sharing. Authentication supports GitHub OAuth and native device-code authorization. Transport options include direct VNC, WebSocket relay via Cloudflare, QUIC, and WebRTC. The codebase is architecturally sound with clean separation of concerns, extensive test suites, and careful security patterns (bounded buffers, token fencing, safe prime validation). However, the multi-language stack (Go, Swift, Rust, TypeScript) and multiple protocol implementations increase maintenance complexity.

slacrawl is a local-first Slack archiving CLI tool written in Go. It ingests messages, files, users, and channels from multiple sources—Slack API (bot/user tokens), Slack Desktop local cache (LevelDB + IndexedDB), MCP (Model Context Protocol) adapters, and external provider subprocesses—and stores them in a local SQLite database with full-text search (FTS5). The tool provides a rich command surface including sync, search, TUI browsing, analytics reports (digest, trends, quiet channels), retention purging, and Git-based archive sharing (publish/subscribe). It is designed for privacy-conscious users who want offline access to their Slack history without cloud dependency. The architecture follows a clean internal package separation: `cmd/slacrawl` is the entry point, `internal/cli` handles command routing via Kong, `internal/store` provides the SQLite persistence layer with schema migrations and batch writes, `internal/syncer` orchestrates multi-source synchronization, and `internal/slackapi`, `internal/slackdesktop`, `internal/slackmcp`, and `internal/provider` implement source-specific adapters. The codebase is well-tested with extensive Go tests, CI/CD via GitHub Actions, and cross-platform releases (Linux, macOS, Docker). While primarily an application, slacrawl exhibits data pipeline characteristics: it ingests raw Slack data, transforms it into a normalized relational schema with FTS indexing, and exposes analytical outputs (reports, digests). The embedding_jobs table hints at future ML integration. The Git archive sharing module is a novel pattern for distributed data replication. Overall, the codebase demonstrates strong engineering practices with reusable components like the generic MCP client, platform-specific file locking, and the external provider protocol.

wacrawl is a local-first Go application for importing, merging, searching, and exporting WhatsApp Desktop archive data. It reads the WhatsApp Desktop SQLite database directly from local files, normalizes it into a private SQLite store, and exposes a CLI (import, status, chats, messages, search, sql, web, backup, contacts, metadata) plus a loopback-only read-only web viewer. The system is deliberately private: no network protocol, media confined to known roots, and the web UI requires a per-run bearer token.

This repository is a retired reference implementation for deploying AI coding agents (CLAWDINATORs) on AWS using NixOS. It provides a complete image-based provisioning pipeline: NixOS images are built with nixos-generators, uploaded to S3, imported as AMIs, and launched as EC2 instances via OpenTofu. The agents run the openclaw gateway, connecting to Discord and GitHub to monitor repositories and assist maintainers. The system includes shared memory via EFS, a control plane Lambda for fleet management, GitHub App token refresh, and scheduled GitHub state sync. The codebase is well-structured with a modular NixOS module, clean shell scripts, and proper infrastructure-as-code patterns. However, the project is explicitly retired (fleet decommissioned August 2026, workflows disabled), so it serves primarily as a historical reference and learning resource for NixOS-on-AWS deployment patterns.

ClawBench is a rigorous execution-first benchmarking framework for evaluating AI agents (particularly OpenClaw) on multi-step tasks. The system orchestrates agent runs through a gateway or containerized native evaluation, scores performance across four axes (completion, trajectory, behavior, advisory judge), and generates detailed diagnostic reports. Its architecture includes a job queue with HuggingFace Dataset persistence, a Gradio web app for interactive leaderboards, and a comprehensive CLI for running evaluations and analyzing results. The framework supports multiple agent runtimes via a pluggable adapter pattern (OpenClaw, Hermes, Claude Code, Codex) and provides a canonical task schema for agent-agnostic task definitions. Beyond basic scoring, ClawBench applies dynamical-systems and statistical methods to agent behavior: trajectory regime classification (trapped, limit-cycle, diffusive), Kaplan-Meier survival analysis, constraint index computation, and variance decomposition. It includes a configuration-space benchmarking system (v0.5) that fingerprints plugin profiles for cold-start prediction and fANOVA factor analysis. The codebase is well-tested with over 60 test files, uses Docker for reproducibility, and includes CI/CD pipelines for automated evaluation campaigns. However, the system is complex and has some hardcoded paths and environment variables tied to specific deployment contexts (Crabbox, OpenClaw gateway), and its heavy dependency on external services introduces maintenance risk. Overall, it is a production-grade benchmark with sophisticated analysis capabilities.

ClawScan is a Go-based CLI tool for composable security scanning of AI agent skills and plugins. It orchestrates multiple external scanners (e.g., Snyk, VirusTotal, Socket, AIG, Cisco, SkillSpector) against skill directories, collects raw evidence, and optionally feeds results to an LLM judge for evaluation. The tool supports profile-based configuration (built-in profiles like `clawhub` and `openclaw-install-policy`), Docker sandboxing, declarative gate rules for automated policy enforcement, and benchmark execution against datasets like SkillTrustBench and clawhub-security-signals. It is distributed via npm (`@openclaw/clawscan`) and GitHub Releases, with a rich CI/CD pipeline including automated runtime image builds, dependency updates, and a Hugging Face leaderboard for security signals research. While primarily an application, it has strong data/research elements through its benchmark infrastructure and leaderboard submission validation.

Octopool is a production-grade GitHub API relay and caching proxy, deployed as a Cloudflare Worker with a companion Go CLI. It pools multiple GitHub identities (PATs, GitHub App installations) to share API quota, caches responses in D1 and edge cache, and applies string-rewrite policies to protect sensitive data. The CLI acts as a drop-in `gh` shim, routing eligible read commands through the relay before falling back to native `gh`. The system also supports token-free transports (public web pages, raw content, Git smart HTTP) to minimize API consumption. Architecture includes Durable Objects for coordination (pool identity selection, cache-fill ownership, policy revisioning), D1 for persistent cache and audit, and edge cache for low-latency reads. The codebase is dual-language (TypeScript for Worker, Go for CLI) with extensive unit and e2e tests, CI/CD, and a dashboard for monitoring.

notcrawl is a production-grade CLI tool for mirroring a Notion workspace into a local SQLite database and normalized Markdown files. It ingests data from three sources: the official Notion API, the local Notion Desktop cache (macOS), and an experimental Notion MCP gateway (via ChatGPT). The core architecture is a Go CLI with a unified SQLite store that tracks record provenance (source, sync timestamps, tombstones) and supports full-text search via FTS5. Key commands include `sync` (multi-source ingestion), `search`, `export-md` (Markdown tree), `export-db` (CSV/TSV for databases), `tui` (terminal browser), and `publish`/`subscribe` (git-backed snapshot sharing). The system emphasizes data completeness, deterministic rendering, and offline durability. External dependencies include the Notion API, local SQLite (desktop cache), and a git binary for share operations. The codebase is well-tested with extensive unit and integration tests, and follows clean separation of concerns across store, API, desktop, MCP, markdown, and share modules.

gitcrawl is a Go-based CLI and library for ingesting GitHub repository data (issues, PRs, comments, reviews, code files, workflow runs) into a local SQLite database, then searching and analyzing that data offline. It exposes commands like `gitcrawl sync owner/repo`, `gitcrawl search issues`, and `gitcrawl code index`, with optional full-text code search. The architecture is a layered CLI: a command layer, a GitHub GraphQL/REST client with rate-limit guarding, a sqlc-generated SQLite data-access layer, and a small TUI built on bubbletea/lipgloss. It also includes a separate metrics store with strict database-ownership validation and idempotent writes.

ClawPDF is a zero-dependency PDFium WebAssembly library and CLI for Node.js and browsers. It extracts text, renders pages to RGBA bitmaps, and produces PNG bytes without runtime dependencies, native addons, or postinstall scripts. The library supports multiple input sources (file paths, URLs, Blobs, byte arrays) with configurable HTTP fetch timeouts and size budgets, password-protected PDFs, and text-first extraction with bounded image fallback. The CLI provides text extraction, JSON output, page rendering, and inline terminal image display for Kitty and iTerm2 protocols. The architecture is modular with clean separation of concerns: input normalization, engine lifecycle, document/page abstractions, render size resolution, PNG encoding, and extraction orchestration. The codebase demonstrates high craftsmanship with reusable components like the standalone PNG encoder and terminal inline image renderer.

This repository is the community governance and operations hub for the OpenClaw project. It contains no application code; instead, it provides markdown documentation for community team guides, moderation policies, incident playbooks, onboarding, and bot management. The only executable artifact is a GitHub Actions workflow (`clawsweeper-dispatch.yml`) that dispatches events to an external ClawSweeper bot for automated GitHub QA and merge assistance. The repo also includes well-structured issue templates for policy and rules changes. It is not a software application in the traditional sense, but rather a set of operational documents and GitHub configuration files that support the OpenClaw community. The quality score reflects the lack of reusable software components and the documentation-only nature, though the workflow demonstrates moderate engineering craftsmanship.

libopus-wasm is a TypeScript library that provides WebAssembly bindings for libopus, enabling raw Opus packet encode/decode in browsers and Node.js without native dependencies. It exposes async factories (`createEncoder`, `createDecoder`) that lazily load a single-file WASM module, returning typed handles with methods for Int16 and Float32 PCM, batch operations, packet-loss concealment, in-band FEC, and a curated CTL passthrough. The library also ships a `@discordjs/opus`-compatible adapter (`libopus-wasm/discordjs`) for drop-in replacement. The codebase is well-structured with strict validation, deterministic cleanup via `Symbol.dispose`, and comprehensive test coverage. Build scripts compile libopus from source using Emscripten with SHA-256 verification, and the documentation site is generated from Markdown by a custom static site builder. The repository is actively maintained with recent commits, CI across Node 22–26, and no open issues.

This repository provides an ESP-IDF component framework (esp-openclaw-node, esp-openclaw-talk, esp-openclaw-room-node) for building IoT devices that connect to the OpenClaw gateway via WebSocket. It implements device identity (Ed25519), session persistence, command dispatch, and WebRTC audio (Talk). The room-node component adds a full voice-interactive display client with LVGL-based animated face, Canvas (image/A2UI rendering), camera snapshot, file access, and real-time diagnostics. The codebase includes multiple board-specific examples (M5Stack Tab5, Waveshare AMOLED, ESP-BOX-3, M5Stack Dial) that demonstrate reuse of the core components. Strong engineering practices are evident: extensive host-based unit tests (with fake SDK headers), CI pipelines that verify cryptographic signatures and component patches, firmware packaging with provenance manifests, and a component registry release process for versioned distribution. The architecture cleanly separates concerns via board adapter abstractions and config structs, making the core components reusable across different ESP32 hardware.

Clawgo is a minimal headless Go client node for the Clawdbot voice assistant gateway. It connects to a bridge over TCP, handles pairing and authentication, then streams voice transcripts from stdin, a FIFO, or a subprocess STT engine (brabble) as `voice.transcript` or `agent.request` events. It supports bidirectional chat: it can subscribe to chat events and speak responses via local TTS (espeak-ng or custom command) through a serialized speech queue. The node advertises itself via mDNS and supports configurable routing plugins for pre-processing transcripts (e.g., quick actions like 'telegram ping'). The architecture is a single binary with a reconnection loop, context-cancellable waits, and graceful shutdown on SIGINT/SIGTERM. The codebase demonstrates solid Go practices: clean separation of concerns, a plugin registry for routing policies, a thread-safe TTS queue that cancels active speech on disconnect, and careful handling of external subprocess stdout/stderr.

Telecrawl is a Go CLI application that imports Telegram Desktop's `tdata` session data and creates encrypted, versioned backups. It reads the local Telegram Desktop data directory (platform-specific paths for macOS/Linux), parses the tdata format, and stores chat archives in a SQLite-backed store with merge/restore/tombstone semantics. The CLI exposes commands for import, backup, restore, search, and media reference handling. It runs as a Docker image with a non-root user, read-only tdata mount, and persistent /data volume. Architecturally, it is a monolith with a `cmd/telecrawl` entry point delegating to `internal/cli`, which orchestrates importers (`tdata`, `postbox`) and the `internal/store` persistence layer. The store handles schema migrations, snapshot merging, and search. Backup uses a Git remote pattern with safety guards against path overlaps. The codebase includes CI workflows, release automation, and security checks. Maintenance is active with frequent dependency bumps and CI. However, the store package is large and mixes concerns, and tdata/postbox importers are format-specific and may break if Telegram changes its data format. Hardcoded platform paths and schema backfill migrations are drift risks. Despite some data-audit scripts and fixture data, the dominant character is a CLI application.

songsee is a single-binary Go CLI tool that turns audio files into spectral visualization images. It decodes audio natively (WAV, MP3) or via ffmpeg, computes an FFT specrogram, and renders nine visualiation modes (spectrogram, mel, chroma, HPSS, self-similarity, loudness, tempogram, MFCC, spectral flux) as a grid of heatmaps in PNG or JPEG format. The architecture is a monlith: the `cmd/songsee/main.go` entry point parsers flags using Kong, delegates to `internal/audio` for decoding, `internal/dsp` for signal processing (STFT, mel filtering, chroma, median filters, etc.), and `internal/render` for image generation. It produces deterministic output – same input flags yield identical bytes. The codebase is well-structured with comprehensive tests, CI/CD, and a clean separation of concerns. It demonstrates high craftsmanship in DSP optimization (e.g., bit-exact HPSS with median networks, tiling) and safe WAV parsing.

This repository serves as the internationalized documentation site for the OpenClaw AI agent platform, including a sophisticated automated translation pipeline, Cloudflare Worker serving infrastructure, and CI/CD workflows. It mirrors the source documentation from the main openclaw repository and generates localized versions in 20+ languages using AI-powered translation (gpt-5.6). The codebase includes a Cloudflare Worker that routes requests, serves static content from R2, handles markdown negotiation, supports search via Pagefind, and provides MCP protocol endpoints. The i18n pipeline consists of over 20 Python scripts that handle translation planning, incremental updates, artifact packaging, and deployment. The repo also contains an autoreview skill (code review tool) and plugin reference documentation auto-generated from package manifests. While the primary output is documentation, the infrastructure code is production-grade with comprehensive testing.

Crawlkit is a shared Go library and CLI tool (crawlctl) for building local-first crawler archives. It provides provider-neutral building blocks including SQLite stores with FTS5, snapshot/export to gzipped JSONL shards, Git-based mirroring with immutable tags, encrypted backup with age/gzip and SHA-256 deduplication, sync state management with legacy adapters, vector search (exact cosine similarity and optional turbovec Python bridge), embedding providers (OpenAI, Ollama, llama.cpp), a terminal UI (Bubble Tea) for browsing archive rows, and a remote archive client for Cloudflare Workers. The CLI discovers installed crawl apps (e.g., gitcrawl, discrawl) and runs configured refresh jobs under a single-process lock. The architecture is modular and composable, with clear ownership boundaries documented in docs/boundary.md. The repository also includes agent skills (autoreview, crabbox) for automated code review and remote validation, reflecting heavy agent-driven development. It is not a generic web crawler but a mechanics layer that makes each crawl app smaller and more uniform.

This repository is an automated maintenance and triage system called 'Clownfish' (ProjectClownfish) that manages the large open-source `openclaw/openclaw` repository. It is a Node.js application driven by GitHub Actions workflows that continuously processes GitHub issues and pull requests: performing deduplication, canonical selection, security-sensitive detection, automated repair of contributor branches, exact-head merge preflight validation, and closeout of superseded/fixed-by-candidate items. The system operates in plan (read-only), autonomous (lightweight actions), and execute (mutating) modes, with strict permission boundaries defined in YAML frontmatter job files. It relies on the GitHub API, a Codex/AI worker for classification, and a suite of deterministic safety gates (re-fetch live state, check updated_at, block unsafe closeouts) before any mutation. The codebase is well-structured with clear separation of concerns (scripts, job definitions, results), but it is tightly coupled to the specific workflow of a single large repository, limiting direct reuse. Notable patterns include a robust job frontmatter schema, deterministic preflight validation, and a centralized security routing mechanism.

clawdex is a local-first, markdown-first personal contact index CLI written in Go. Contacts are stored as plain markdown files with YAML frontmatter in a private Git repository, making the data diffable, grepable, and portable. The tool provides commands to manage people, notes, avatars, search, and timelines, with import adapters for Apple Contacts (macOS only via a temporary Swift helper), Google Contacts (via the gog CLI), X/Twitter DMs (Birdclaw), Discord DMs (Discrawl), and generic crawlkit-compatible crawlers. It also supports vCard export, Git sync helpers, and a doctor command for repairing damaged frontmatter. The architecture is a single self-contained binary with Kong-based CLI parsing, internal packages for each major domain, and a strong emphasis on security and correctness — the safefile package performs rooted, symlink-aware file I/O with atomic writes, and the markdown package includes robust salvage and repair logic for damaged frontmatter. CI enforces 90%+ test coverage, security scanning (gitleaks, gosec), dead code detection, and reproducible builds via GoReleaser.

This repository provides a lightweight, LGPL-friendly FFmpeg and FFprobe compiled to WebAssembly for Node.js (and browser via a dedicated worker). It wraps the wasm modules with predictable CLI and TypeScript APIs for media probing, audio extraction, video resizing, thumbnail generation, raw frame output, stream-copy clips, and segmentation. The architecture consists of a TypeScript library that spawns a child process running an Emscripten-generated module, with both buffered (runFfmpeg, runFfprobe) and streaming (execFfmpeg, execFfprobe) APIs. A browser-only ffmpac worker enables the same operations in the included media workbench playground. The build system is sophisticated: it fetches FFmpeg, LAME, and libvpx source, compiles them statically with Emscripten, and produces both Node and browser wasm bundles. The codebase is well-structured, with strict linting, comprehensive unit and E2E tests, and a clear separation of concerns. It is actively maintained and demonstrates strong engineering practices.

`@openclaw/fs-safe` is a production-grade Node.js library providing capability-style filesystem roots for secure, confined file operations. It enforces path boundaries, rejects symlink/hardlink escapes, and defends against TOCTOU races. The library offers atomic read/write/replace operations, secure archive extraction (ZIP/TAR with entry budgets and integrity checks), cross-process file locking, JSON stores with durability guarantees, permission inspection for POSIX and Windows, and secret file handling. It bundles a Rust native addon (via napi-rs) to accelerate critical operations on Linux, macOS, and Windows, with a transparent JavaScript fallback. The API is organized into modular subpath exports (e.g., `root`, `archive`, `file-store`, `file-lock`, `permissions`, `secret`, `durability`, `atomic`, `temp`, `walk`, `advanced`), each with typed error codes and consistent error categories. The package includes an extensive test suite (>3000 tests) covering security regressions, property-based fuzzing, concurrency stress tests, and cross-platform behavior. It is used by the OpenClaw ecosystem and published on npm with SLSA provenance.

This repository provides reproducible Nix packaging for a collection of CLI tools (summarize, discrawl, wacrawl, gogcli, goplaces, camsnap, sonoscli, peekaboo, poltergeist, sag, imsg, qmd) used in the OpenClaw ecosystem. It includes per-tool OpenClaw plugin metadata (skills) that teach AI agents how to use each tool. The repo features automated update workflows: a Go-based tool updater (`cmd/update-tools`) that fetches latest GitHub releases and updates Nix expressions with new versions and hashes, and a skill syncer (`cmd/sync-skills`) that pulls the latest skill definitions from upstream OpenClaw repositories. The Go code demonstrates solid engineering with proper timeout handling, process group management, atomic file updates, and comprehensive tests. The Nix expressions are well-structured, supporting multiple platforms (aarch64-darwin, x86_64-linux, aarch64-linux) and using pinned nixpkgs inputs for reproducibility. CI runs formatting checks, vetting, tests with race detector, and builds all packages on supported systems. The repository is actively maintained with frequent commits and automated CI runs.

Caclawphony is an Elixir/OTP application that automates pull request triage, review, and merging by orchestrating AI agents (Codex). It polls a Linear project board for issues in configured states, creates isolated workspaces per issue, and runs phase-specific agent prompts (triage, review, prepare, merge, closure). A real-time terminal dashboard and optional Phoenix LiveView web UI provide observability into running agents, token usage, and rate limits. The system is driven by a single WORKFLOW.md file that serves as both configuration (YAML front matter) and per-issue prompt template. The architecture follows OTP GenServer patterns: an orchestration loop polls the tracker, dispatches to AgentRunner instances that manage Codex subprocesses via stdin/stdout JSON-RPC, and reconciles state transitions. External integrations include the Linear GraphQL API, GitHub CLI for PR operations, and Telegram for notifications. The repository includes extensive test coverage, CI/CD workflows, and reusable patterns such as a tracker behaviour, snapshot testing support, and a spec coverage linting mix task. While designed for the openclaw/openclaw repository with hardcoded Linear identifiers and defaults, the plugin architecture (tracker adapters, workspace hooks, prompt templates) supports customization. The codebase is actively maintained with modern Elixir tooling (Phoenix, Bandit, NimbleOptions) and demonstrates solid software engineering practices, though its tight coupling to specific Linear states and the prototype nature noted in README limit immediate reuse outside the originating project.

This repository contains no application source code. The only substantive file is a GitHub Actions workflow (clawsweeper-dispatch.yml) that acts as a dispatch router for the ClawSweeper bot, forwarding GitHub events (issues, issue comments, pull requests) to the openclaw/clawsweeper repository. The workflow uses a GitHub App token for authentication and includes debouncing, comment filtering, and acknowledgment logic. The repository itself is essentially a configuration stub—there are no scripts, binaries, or libraries. The bot's actual logic resides elsewhere. The repo appears to be a placeholder or thin integration layer, with no functional code to evaluate for craftsmanship or reusability.

This repository is a Homebrew tap for distributing OpenClaw's CLI tools (19 formulae and one migrated cask). It provides automated formula update and reconciliation workflows triggered by GitHub releases or periodic schedules. The core automation is implemented in Python scripts under `.github/scripts/`: `formula_text.py` is a pure parser/renderer for Homebrew formula Ruby text, `update_formula.py` handles downloading release assets, verifying checksums, and writing updated formulae, and `reconcile_formulae.py` periodically checks for newer stable releases and updates formulae accordingly. The tap includes comprehensive CI workflows that validate formula syntax, run Homebrew style checks, and perform platform-specific install tests on macOS ARM64/x86_64 and Linux x86_64. The codebase is well-structured, with clear separation between text manipulation, network operations, and orchestration. The automation scripts are robust, with input validation, timeout handling, and secure dispatch constraints. The formulae themselves are standard Homebrew formulae with architecture-specific URLs and checksums. The repository demonstrates high craftsmanship in its automation layer, particularly the `formula_text.py` module which could be extracted and reused in other projects needing to programmatically manipulate Homebrew formula files.

ClawRouter is a production-grade AI/LLM proxy gateway deployed on Cloudflare Workers. It provides a unified API endpoint for multiple AI providers (OpenAI, Anthropic, Google Gemini, etc.) with policy-based access control, per-user and per-provider budget accounting, usage tracking, and a comprehensive admin console (React/TypeScript). The system authenticates users via Cloudflare Access, local auth, or API keys, then routes requests through configurable policies that enforce budget limits, grant selection, and content retention. It supports streaming, WebSocket-based Responses API, and a Fusion mixture-of-agents feature for multi-model orchestration. The worker uses Durable Objects for stateful budget ledgers, usage ledgers, credential stores, and background job recovery, all backed by SQLite. A rich admin UI (Patchboard) allows operators to manage policies, credentials, grants, users, and view analytics. The codebase includes extensive unit, integration, and browser (Playwright) tests, along with CI/CD pipelines for Cloudflare deployment and self-hosting via Docker/workerd. It is a well-architected, thoroughly tested system that demonstrates high craftsmanship in state management, error handling, and idempotent accounting patterns.

Rastermill is a Node.js image processing library that provides a unified API for probing, transparency inspection, and encoding (resize, convert, byte-budget search). It uses Photon (WASM) in-process for common formats (PNG, JPEG, GIF, WebP, BMP) and falls back to native tools (sips, ImageMagick, GraphicsMagick, ffmpeg, Windows System.Drawing) for formats like HEIC/AVIF or when quality-controlled WebP is needed. The library enforces pixel budgets to prevent decompression bombs, strips metadata by default, handles EXIF/HEIF orientation, and supports cancellation via AbortSignal. It is designed for server-side and agent-facing media pipelines. The codebase is a single well-structured TypeScript module with comprehensive tests and CI coverage.

Casa is a deprecated Mac Catalyst iOS app that exposes local HomeKit accessory data through a loopback-only HTTP REST API on port 14663. The architecture is a SwiftUI Mac app (Casa/) paired with an embedded Swift Package CLI (CasaCLI/) that communicates with the app's local server. The core server (HomeKitServer.swift) uses Apple's Network framework (NWListener) to serve HTTP/1.1, with a custom HTTP request parser and JSON response builder. HomeKit access is gated behind an opt-in module system and requires the HomeKit entitlement. The app includes Sparkle for updates, an onboarding flow, settings persistence via UserDefaults, and a file-based rotating logger. The codebase demonstrates solid engineering practices: the HTTP server is hand-rolled without third-party dependencies, the request parser handles keep-alive and content-length correctly, the JSON envelope pattern is consistent, and the HomeKit mapping layer cleanly separates Apple's types from API DTOs. The test suite covers HTTP parsing, response encoding, schema payload generation, settings persistence, and CLI platform gating. SwiftLint is configured and CI/CD workflows exist for building and releasing. The README explicitly states deprecation and points to a successor (omarshahine/HomeClaw). The last commit was 2026-05-30, and the project uses Swift 5.0 with iOS 16.0 deployment target — both showing moderate drift. The Sparkle feed URL and public key are placeholder values in the pbxproj. The codebase is well-structured but no longer maintained.

Hermit is a feature-rich Discord moderation and community bot for the OpenClaw ecosystem, deployed to Cloudflare Workers with a Bun-based gateway forwarder relaying Discord gateway events. In production it runs as a single Worker isolate using Carbon (@buape/carbon) for Discord interactions and Drizzle ORM over Cloudflare D1 for persistence. It exposes 14+ slash commands (claim, nominate, slap, lobster, say, admin, role, maintainer, helper, github, beta-pings), context-menu commands, webhook APIs for ClawHub search intelligence and publisher abuse digests, scheduled cron tasks (nomination expiry, thread monitoring, card sync), and a React-SSR form system with OAuth flows for ban appeals, content rights cases, and moderated submissions. The bot is tightly coupled to one Discord guild, with guild/channel/role/user IDs hardcoded across config files, though the domain modules (moderation, nominations, forms, games) are cleanly separated and extensively unit-tested against a SQLite D1 shim. A substantial secondary character is deterministic content/data engineering: the repo bundles a frozen WoRMS taxonomy snapshot of 264 accepted lobster species across 6 families, plus meticulously provenance-tracked AI artwork pipelines (1056 lobster scenes, ~327 slap scenes) with SHA-256 checksums, batch manifests, QA gates (RIFF signature checks, dwebp decode, perceptual dHash near-duplicate detection), remediation loops, and byte-identical rebuild tests. These pipelines feed the in-bot lobster encounter and fish-slap games rather than serving external research, so the repository is best classified as an application with strong data-engineering DNA. The build scripts are genuinely reusable for any biodiversity-data or generative-asset workflow. Drift risks include hardcoded local generation paths (e.g. /Users/hrudolph/...), pinned dependency overrides (esbuild, postcss, ws), future-dated snapshot timestamps as data artifacts, and checksum locks that make data updates deliberately expensive.

This repository is a cookbook of runnable examples for the OpenClaw SDK. It contains two layers: small one-concept recipes (e.g., run-an-agent, stream-events, cancel-a-run) and standalone starter apps (quickstart Node app, coding-agent CLI, agent-workbench React app, run-board React dashboard). The code demonstrates SDK workflows such as starting runs, streaming normalized events, cancelling work, reusing sessions, checking model status, and testing with an in-memory transport. The architecture is modular: recipes are self-contained TypeScript files with shared configuration helpers, and SDK examples are independent packages that can be copied out and adapted. The repository includes comprehensive tests, CI checks, and a workspace SDK shim for local validation without a live Gateway. It is actively maintained with modern dependencies (TypeScript 7, Node 22, pnpm 10.34.5) and follows strict formatting and linting rules.

Proxyline is a Node.js library that installs a process-wide proxy routing policy across `node:http`, `node:https`, undici/fetch, WebSocket clients, and explicit HTTP CONNECT tunnels. It provides two modes: `managed` (fail-closed with a required proxy URL) and `ambient` (respects `HTTP_PROXY`/`HTTPS_PROXY`/`NO_PROXY` environment variables). The library patches global HTTP(S) methods, replaces global agents, installs a custom undici dispatcher, and patches fetch globals. It includes observability via `explain()` and lifecycle events, scoped proxy TLS trust, dynamic bypass registrations, and credential-safe URL redaction. The codebase is TypeScript, ESM-only, and requires Node.js 22.19+ with undici 8.5+ as a peer dependency. It is well-tested with an in-process proxy lab and has comprehensive documentation.

Crabline is a deterministic local messaging-channel mocking framework for end-to-end testing of chat integrations. It provides a CLI tool and a TypeScript library that simulates 12+ messaging platforms (Discord, Slack, Telegram, WhatsApp, Matrix, etc.) via mock servers and provider adapters. The architecture is built around a provider adapter pattern with lazy loading, a JSONL-based event recorder with cross-process locking, and a fixture-driven test runner that supports probe, send, roundtrip, and agent modes. The system is configuration-driven via YAML manifests validated with Zod schemas, and it publishes readiness artifacts for integration with the OpenClaw QA ecosystem. The codebase demonstrates strong engineering practices: clean separation of concerns, extensive test coverage (including concurrency and edge cases), and reusable infrastructure components such as process-owned file locks, nonce generation, inbound message matchers, and webhook authentication policies. The mock servers faithfully replicate platform-specific APIs (REST, WebSocket, SSE) with configurable resource limits and admin inbound endpoints for injecting test messages. While primarily a testing tool, Crabline's components are designed for reuse: the recorder, lock system, and provider adapter base class can be extracted into other projects. The repository is actively maintained with CI/CD pipelines, dependency management, and a changelog. It is not a data research project; all data artifacts (JSONL logs) are operational evidence for test assertions, not analytical datasets.

Swabble is a macOS 26 CLI daemon and Swift library that listens to the microphone, detects a configurable wake word (default 'clawd'), transcribes speech locally using Apple's Speech.framework (SpeechAnalyzer + SpeechTranscriber), and executes a user-defined shell hook with the transcript. It also supports offline file transcription to TXT or SRT. The architecture is a monolith Swift package with a library target (SwabbleCore) exposing reusable components like the speech pipeline, hook runner, config loader, and transcript store, and an executable target (SwabbleCLI) using the Commander library for command routing. Key data flows: microphone audio → AVAudioEngine tap → BufferConverter → SpeechAnalyzer → SpeechTranscriber → async stream → wake-word matching → HookRunner → shell process. External dependencies are limited to Apple frameworks and the Commander package. The codebase demonstrates strong use of Swift 6.2 concurrency (actors, async streams), careful process management with timeout and cancellation, and clean separation of concerns. It is well-tested with CI covering formatting, linting, unit tests, and release verification.

graincrawl is a local-first CLI tool written in Go that archives Granola meeting notes, transcripts, panels, and metadata into a private SQLite database. It supports multiple read-only source adapters: Granola's private desktop API (via WorkOS token), the official public API (with a scoped API key), the local plaintext desktop cache, and legacy encrypted JSON files (via Electron safeStorage decryption). The tool provides commands for syncing, searching, exporting Markdown, creating portable snapshots, and browsing via a terminal UI. The architecture is cleanly modular with separate packages for each source adapter, a shared SQLite store with schema migrations, and a syncer that orchestrates fallback logic between sources. The codebase is well-tested, has comprehensive CI/CD, and follows Go best practices. It is not a data research project; it is a production-grade application for personal data archiving.

Ask Molty is a Cloudflare Worker that serves as a documentation agent for OpenClaw. It accepts user questions via a chat API, builds a read-only workspace from pre-indexed documentation, source code, and GitHub issues/PRs, then uses OpenAI's chat models with tool calls (search_workspace, read_workspace, list_workspace, run_shell) to answer grounded in the workspace. The worker handles authentication via OpenClaw ID or GitHub session cookies, serves artifact files (e.g., github-search.jsonl) via a proxy, and includes robust error handling for timeouts, malformed data, and streaming. The codebase is well-structured with separate modules for auth, prompt, retrieval, and types, and includes a comprehensive smoke test suite that mocks network interactions to verify behavior.

CrawlBar is a native macOS menu bar application and CLI tool that serves as a control plane for local-first crawler CLIs (e.g., GitHub, Slack, Discord, Telegram, Notion, WhatsApp). It discovers crawler manifests (built-in or from ~/.crawlbar/apps/), runs commands to retrieve status, freshness, and database inventory, and supports actions such as sync, publish, doctor, search, and backup. The architecture is strictly layered: a core library (CrawlBarCore) with no UI imports provides all data models, command execution, secret redaction, status normalization, and config storage, while a SwiftUI/AppKit frontend renders a menu bar status item and a settings window. A CLI (crawlbarctl) exposes the same functionality outside the GUI. CrawlBar does not crawl data itself; it orchestrates external CLI crawlers via a standardized manifest and status protocol (crawlkit.control.v1). It enforces privacy by redacting secrets from command output, storing action logs with private permissions, and keeping secrets in the macOS Keychain. The system supports remote execution via SSH and integrates with Cloudflare D1 for remote SQLite archives. 12 built-in crawler manifests are provided, covering major messaging and productivity platforms. The project also includes an extensive self-test suite, CI/CD with notarization, and a quality rubric document for code reviews. The core domain is well-abstracted, with reusable patterns for command running, status mapping, config caching, and action coordination. However, the codebase is macOS-only, relies on hardcoded fallback paths and a manual TOML parser, and has many per-crawler special cases in command argument construction. The maintenance is active (frequent releases, changelog, CI), but technical drift is medium due to ecosystem lock-in and custom infrastructure.

Plugin Inspector is a CLI tool and library for offline static and runtime analysis of OpenClaw plugins. It validates plugin structure, SDK imports, hook registrations, and manifest contracts without requiring a live OpenClaw host. The tool generates rich compatibility reports in JSON, Markdown, SARIF, and JUnit formats, integrates with CI pipelines (GitHub Actions, GitLab, CircleCI), and supports batch analysis across plugin corpora. Its architecture is modular: a core inspection engine (src/inspector.js) performs static analysis using AST parsing (acorn, eslint-scope) and regex-based detection; an optional runtime capture subsystem (src/capture-api.js, src/synthetic-probes.js) executes plugin entrypoints with a dynamically generated mock SDK (src/sdk-mock.js) to verify registration behavior and hook handling. The tool also includes a CI policy engine, workspace planning, platform probes, and profiling/diffing utilities. While tightly coupled to OpenClaw internals, the codebase demonstrates strong engineering practices with extensive test coverage, reusable components, and a well-defined public API surface.

photoscrawl is a macOS CLI tool that crawls, archives, and analyzes Apple Photos libraries. It extracts metadata, faces, search indexes, and performs classification using local multimodal models (Ollama/OpenAI). The tool stores observations and evidence in a local SQLite database (photos.sqlite) rather than final truth, enabling later hypothesis generation for people, trips, and places. It provides subcommands for crawling, importing, classifying, searching, ranking, similarity, place backfill, and evaluation card generation. Architecture: The system is a Go CLI with a modular internal structure. It uses a crawlkit shared library for crawler mechanics, control, output, and store. The Apple Photos library is accessed via PhotoKit (cgo/Objective-C bridges) and direct SQLite snapshots. Data flows: snapshot Apple Photos database -> import metadata, faces, search indexes -> classify assets (metadata observations, then optional local model inference) -> store evidence in archive. Place backfill uses a subprocess bridge for reverse geocoding with rate limiting. Eval cards prepare images and run Ollama models for evaluation. Key entry points: cmd/photoscrawl/main.go (CLI), internal/archive/crawl.go (crawl logic), internal/archive/classify.go (classification queue), internal/place/backfill.go (batch geocoding), internal/evalcard/evalcard.go (model evaluation). External dependencies: Apple Photos (macOS), SQLite, Ollama/OpenAI (optional), crawlkit, Go standard library. The codebase demonstrates strong engineering practices with comprehensive tests, CI/CD, vulnerability scanning, and schema migrations. It is actively maintained with frequent dependency updates and a focus on privacy (all model calls local by default, no private data in repo).

Crabpot is a compatibility testing and regression detection framework for the OpenClaw AI agent plugin ecosystem. It validates plugin fixtures (59 plugins, 119 entrypoints) against the OpenClaw API surface by capturing contract registrations, running synthetic probes, measuring cold-import readiness, and profiling resource usage. The system is driven by a modular collection of Node.js scripts (ES modules) that orchestrate inspection, report generation, and CI policy enforcement. It integrates deeply with GitHub Actions for automated checks, track dashboards, and resource campaign execution via Docker. The architecture is script-based rather than a monolithic application, with each script performing a focused task (e.g., capture-contracts.mjs, synthetic-probes.mjs, generate-report.mjs) and producing JSON+Markdown reports. External dependencies include the OpenClaw plugin-inspector library, npm/git for fixture materialization, and GitHub Actions for CI. The framework is designed to catch contract drift before external plugin authors encounter it, and it maintains a dashboard of live issues, compat gaps, and profile regressions.

This repository is a minimal static website hosted on GitHub Pages at butter.bot. The site is a humorous memorial page for a lobster named 'Butter Bot' who survived a request to prepare lobster recipes, ending with a catchphrase 'Exfoliate the Butter'. The actual code content is a single index.html file with CSS animations and a simple layout. The repository also contains a non-trivial GitHub Actions workflow (clawsweeper-dispatch.yml) that dispatches events to an external ClawSweeper app for issue/PR management, demonstrating advanced CI/CD patterns like token generation, ingress fingerprinting, and concurrency management. The workflow is the most technically sophisticated part of the repo, but it is tightly coupled to the external ClawSweeper service. The entire repository serves as a domain landing page and a demonstration of the ClawSweeper integration, rather than a standalone application.

This repository hosts the landing page for ClawSweeper, a conservative maintenance bot for OpenClaw repositories. It is a single-page static site built with handcrafted HTML and CSS, deployed on Vercel. The page describes the bot's purpose, operating lanes, guardrails, and watched repositories. The codebase is minimal but exhibits high craftsmanship in its editorial dark theme, responsive design, and accessibility features. The included GitHub Actions workflow dispatches events to the actual ClawSweeper bot repository, enabling automated review triggers. This is not the bot itself; the bot lives in a separate repository (openclaw/clawsweeper). The landing page is well-maintained and serves as a polished informational site.

This repository is release infrastructure for the OpenClaw ecosystem, not an end-user application. It operates as the evidence ledger and release-automation hub for OpenClaw (an npm-distributed product with a signed macOS desktop app) and octopool (a Go CLI distributed via GitHub Releases and Homebrew). In production it generates and stores a structured evidence record for every release candidate under evidence/, containing JSON run metadata and human-readable markdown summaries that classify CI, release, Homebrew, npm, and macOS checks as blocking or advisory. The workflows and scripts in the repo drive macOS signing/notarization and appcast verification, npm dist-tag promotion, Homebrew formula updates, and safe automated commits of release evidence to main. Architecturally, the repository is a GitHub Actions-orchestrated automation layer over the GitHub API, npm registry, Apple notarization, and Homebrew. A central Full Release Validation workflow runs normal CI, plugin prerelease validation, Docker/QA validation, Telegram E2E, and an aggregation gate. The evidence shows frequent failures at the final verification step even when all child jobs succeed, indicating a brittle gate. Evidence commits use concurrency control and rebasing safeguards to prevent races. The repository also contains regression tests for the release scripts and workflow behavior. The system is well-crafted for its niche: it has real tests, structured schemas, explicit storage policies, and non-trivial recovery logic. However, it is tightly coupled to the OpenClaw/octopool release process, contains generated evidence bulk that grows over time, and relies on hardcoded runner/version pins and external services (GitHub Actions, npm, Apple) that make it vulnerable to ecosystem drift. Reuse is possible at the pattern level rather than as a drop-in product.

imsgcrawl is a local-first CLI tool for reading, archiving, and searching Apple iMessage data. It operates by taking a read-only snapshot of the macOS Messages SQLite database (`chat.db`), extracting handles, chats, messages, and deletion events, then merging them into a local SQLite archive. The tool provides bounded commands for metadata, status, sync, chats, messages, full-text search, and phone-only contact export. It outputs both human-readable text (with terminal control escape protection) and stable JSON for automation. The architecture is cleanly separated into packages for archive management, message extraction (including attributed body decoding and edit/unsend reconstruction), and portable SQLite snapshotting with macOS copy-on-write support. The codebase demonstrates strong engineering practices: thorough test coverage including fuzzing, explicit privacy boundaries, identity validation for source databases, and careful handling of edge cases like malformed UTF‑16, hardlinked sidecars, and concurrent sync locking.

This repository contains operational playbooks and governance documents for the OpenClaw Foundation's regional community management and AI Ecosystem Sessions application process. It is not a software application or data pipeline; it is a collection of Markdown files defining standard operating procedures (SOPs) for account ownership, content branding, event coordination, funding, and conflict resolution, as well as a playbook for evaluating and scheduling community presentations. There is no executable code, no API endpoints, no data transformations, and no reusable software components. The repository serves as a documentation hub for community organizers and foundation representatives. The last commit date is in the future (2026-08-20), which suggests the repository may be a placeholder or has an incorrect timestamp; combined with the lack of any code or active development, the maintenance status is considered stale and technical drift is high.

Kova is a validation lab for the OpenClaw runtime, designed to run release-shaped scenarios on real machines and collect structured evidence. It is a CLI tool written in Node.js (ESM) that orchestrates testing via the OpenClaw Control Manager (OCM), provisioning disposable environments, installing runtimes, and managing services. The system executes scenarios defined in declarative JSON contracts (surfaces, states, scenarios, profiles), collects performance metrics (RSS, CPU, latency, event-loop delays), and evaluates them against configurable thresholds. Results are produced as JSON reports, Markdown summaries, and a web dashboard built with Astro. The architecture is modular: a command dispatcher (src/main.mjs) routes to subcommands (run, matrix, report, setup, publish, self-check). The runner (src/runner.mjs) executes scenarios in phases, with collectors (src/collectors/) gathering evidence from processes, logs, timelines, and system state. An evaluator (src/evaluator.mjs) checks evidence against thresholds and produces violations. The reporting layer (src/reporting/) renders output in multiple formats. The system includes extensive self-checks (src/selfcheck/) that validate internal contracts and fixture behavior. Key external dependencies include Node.js, the OCM CLI, the OpenClaw runtime under test, and channel adapters (Telegram, Discord) for conformance testing. The codebase is well-structured with clear separation of concerns, reusable patterns (UI toolkit, evidence ledger, baseline management, channel conformance framework), and comprehensive validation of its own contracts.

This repository provides a credential-free, deterministic test fixture for the OpenClaw plugin API surface, known as the 'kitchen sink' plugin. It exercises the full public plugin API by registering commands, tools, providers (image, speech, realtime transcription/voice, video, music, web search/fetch, embedding, memory, compaction), channels, hooks, gateway methods, services, and CLI backends. The plugin supports three personalities ('full', 'conformance', 'adversarial') to validate different plugin compatibility modes. It is designed as a compatibility fixture for OpenClaw's plugin-inspector and Crabpot tools, and is published to npm as @openclaw/kitchen-sink. The codebase is well-structured, with separate runtime modules per surface, comprehensive deterministic scenario routing, and a robust set of test scripts that validate runtime behavior, contract probes, and package metadata.

This is a GitHub organization profile repository containing community health files (SECURITY.md and funding.yml). It does not contain any application code, data pipelines, or research artifacts. The repository serves to define the security policy and funding model for the Openclaw organization. There are no reusable components or functional code to analyze.

This repository stores design proposals and technical decisions for the OpenClaw agent platform. It contains RFCs covering architecture, protocols, and implementation plans for features such as localization, computer use, sender authentication, enterprise control plane, and plugin SDKs. While not an application itself, it serves as the authoritative specification source for the OpenClaw project. The RFCs are well-structured with YAML frontmatter, sidecar assets, and implementation plans, demonstrating high-quality design documentation. The repository also includes GitHub Actions workflows for process automation and a pull request template.

The repo is a monorepo with the TypeScript library in the root and the autoreview skill duplicated across `.agents`, `.claude`, `skills`, and `$AGENTS_HOME`. Entry points include `test/protocol.test.ts`, `.agents/skills/autoreview/SKILL.md`, and `scripts/check-pack.mjs`. External dependencies include Node.js, pnpm, git, and external AI CLIs. The codebase has strong security hardening but also a monolithic autoreview script (~80k tokens), tight coupling between tests and internal helper names, and platform-specific skips that create drift risk.

ClawSweeper State is a dashboard generation system that transforms immutable event records from the `state` branch into a human-readable README.md dashboard. It consumes JSONL event shards, validates them against a strict schema with privacy protections, deduplicates entries, projects metrics by event family/repository/status/freshness, and renders three dashboard sections: sweep (repository status), action ledger (event statistics), and repair (fix attempt tracking). The system runs on a scheduled GitHub workflow to keep the dashboard updated, with all processing designed to be deterministic and fail-closed on invalid inputs. Architecture follows a modular pipeline: event loading → validation → projection → rendering → commit, emphasizing data integrity over real-time responsiveness.

@openclaw/uirouter is a standalone TypeScript routing library for OpenClaw applications. It provides a type-safe, context-aware router that matches URL paths to route records, exposes navigation state through `getState()`, and supports load contexts and redirects. The library is explicitly not an application framework or state store; it avoids hidden global state and app-specific rendering, making it a focused routing primitive rather than a full application shell.