Open Design is a local-first, open-source design-to-code platform that serves as an alternative to Claude Design. It detects installed coding-agent CLIs (26+ supported), runs design skills against brand-grade DESIGN.md design systems, and streams artifacts (prototypes, decks, images, video, HyperFrames) into a sandboxed preview. The architecture is a monorepo with pnpm workspaces, comprising a Node.js daemon (Express + SQLite), a React/Next.js web SPA, an Electron desktop shell, and an Astro landing page. Core capabilities include a plugin system with 277 official plugins, design system management, AI-powered artifact generation, collaboration (workspace, team resource sharing, presence), critique/theater scoring, media generation, and research integration (Tavily). The daemon acts as a local server that manages projects, conversations, agent runtimes, and SSE event streaming. The web client provides a rich UI for chat, project management, design system browsing, plugin marketplace, and real-time collaboration. The desktop app wraps the web client with native features like folder pickers, deep-link handling, and auto-updater. The codebase demonstrates high craftsmanship with clean abstractions (HTTP adapter pattern, plugin architecture, agent runtime definitions, SWR cache, backoff controller, singleton registries) and extensive test coverage (Vitest unit tests, Playwright e2e). It is actively maintained with a rapid release cadence and modern dependency management.
RAGFlow is a production-grade, open-source Retrieval-Augmented Generation (RAG) engine that combines deep document understanding with agentic workflows. The system ingests heterogeneous documents (PDF, DOCX, images, web pages, etc.), parses them using a multi-stage pipeline (layout analysis, OCR, table recognition), chunks the content with various strategies (token, QA, page, etc.), indexes into vector stores (Elasticsearch, Infinity, OceanBase, SereneDB), and provides retrieval-augmented chat with LLM integration. Beyond basic RAG, it features a visual agent canvas for building complex workflows (parallel subgraphs, loops, tool calls), a sandboxed code execution environment, knowledge compilation (wiki, knowledge graphs, timelines), multi-tenant model management, and chat channel integrations (WhatsApp, Feishu, Discord). The architecture is a full-stack application with a Go backend (Gin), Python API (Flask/Quart), React/TypeScript frontend, and NATS message queue for async tasks. It is designed for enterprise deployment with Docker Compose and supports multiple LLM providers and embedding models.
LibreChat is a self-hosted, multi-tenant AI chat platform that unifies access to major LLM providers (OpenAI, Anthropic, Google, AWS Bedrock, Azure, and custom OpenAI-compatible endpoints) through a single web interface. The architecture is a monolithic Express.js/Node.js backend serving a React (Vite) SPA, backed by MongoDB (Mongoose), Redis for caching/rate-limiting, MeiliSearch for full-text search, and PostgreSQL (pgvector) for RAG embeddings. The codebase is organized as a monorepo with shared packages: `data-schemas` (Mongoose models/methods with multi-tenant isolation), `data-provider` (Zod schemas, API types, React Query hooks), `api` (MCP management, streaming, auth, SSRF protection), and `client` (reusable React component library). Key data flows include: user requests hitting Express routes, middleware performing JWT/OAuth/LDAP/SAML auth and RBAC checks, agent orchestration via `@librechat/agents` with tool execution (MCP, code interpreter, web search), and SSE streaming with resumable stream support via Redis-backed job management. The system implements a sophisticated multi-tenant isolation layer using Mongoose plugins (`tenantIsolation`) that automatically scope queries by tenant, an ACL/permissions system with bit-flag-based permission checks, and SSRF protection with DNS resolution validation for MCP server URLs. The MCP (Model Context Protocol) subsystem is particularly well-developed, featuring OAuth flow management with reconnection tracking, tool discovery, and both stdio and HTTP/SSE transport support. The streaming architecture supports horizontal scaling with Redis-backed event transport and job stores, enabling resumable streams across multiple server instances.
Oh-My-ClaudeCode (OMC) is a multi-agent orchestration layer for Claude Code, Anthropic's AI coding assistant. It extends Claude Code with a plugin system, custom MCP tools, a team collaboration engine, a real-time HUD, and a rich hook system. The system is implemented in TypeScript and runs as a CLI tool (`omc`), an npm package (`oh-my-claude-sisyphus`), and a Claude Code plugin. It manages autonomous coding pipelines (autopilot, ralph), multi-worker team sessions via tmux, skill learning and injection, and provides extensive tooling including LSP integration, AST analysis, Python REPL, and git-based checkpoints. Architecturally, OMC is a modular monolith with clear separation: a CLI entry point (Commander-based), a hook registry with ~20+ lifecycle hooks (session-end, pre-tool-use, persistent-mode, etc.), a team subsystem with state machines and tmux-based worker management, a HUD rendering engine, and a standalone MCP server exposing 33+ tools. The system integrates with multiple AI providers (Claude, Codex, Gemini, Grok, Cursor) and git hosting providers (GitHub, GitLab, Azure DevOps, Bitbucket, Gitea). External dependencies include `@anthropic-ai/claude-agent-sdk`, `@modelcontextprotocol/sdk`, `better-sqlite3`, `zod`, and `commander`. Key data flows include: user input → CLI or Claude Code hook → hook dispatcher → feature modules (autopilot, team, skills) → tool execution → state persistence (filesystem, SQLite). The system maintains extensive state on disk (`.omc/state/`, session transcripts, team events, skill files) and uses file-based locking for concurrency safety. The JEV shadow judgment system provides non-blocking evaluation of heuristic decisions against an external API for quality monitoring. The codebase demonstrates strong engineering practices: extensive test coverage (~3000+ tests), modular architecture with clear interfaces, atomic file operations, and security-conscious utilities (SSRF guard, token redaction, path traversal prevention). It is actively maintained with frequent releases and responsive issue triage.
Sim is a comprehensive AI agent and workflow platform built as a TypeScript monorepo. The core application (apps/sim) is a Next.js 16 App Router application providing a visual/conversational workflow builder, real-time collaboration via Socket.io, and API endpoints for workflow execution. It integrates 1000+ external services through a block/tool/trigger system, supports knowledge bases with RAG (pgvector), file processing, and structured table workflows. The platform self-hosts via Docker Compose or Helm (Kubernetes), with background jobs handled by Trigger.dev and code execution via isolated-vm or E2B. A separate PII detection service (apps/pii) uses Microsoft Presidio. Internal packages provide reusable infrastructure: structured logging (@sim/logger), utilities (@sim/utils), security primitives (@sim/security), database layer (@sim/db), workflow persistence (@sim/workflow-persistence), rate limiting, idempotency, async job queues, file upload handling, tokenization, and a virtual filesystem for the Copilot agent. The codebase demonstrates strong architectural discipline with clear package boundaries, comprehensive testing infrastructure, automated documentation generation from source, and enterprise features cleanly separated in apps/sim/ee/.
This repository is the official home of the Model Context Protocol (MCP), an open standard defining how AI assistants discover and invoke external tools, resources, and prompts over JSON-RPC. In production it operates as a specification and governance hub: versioned TypeScript protocol schemas (2024-11-05 through 2026-07-28 plus draft) are compiled into JSON Schema artifacts, human-readable specification docs are generated and published, and a SEP (Specification Enhancement Proposal) process is automated by a GitHub bot that detects proposals, enforces lifecycle transitions, pings authors, and sends Discord notifications. The architecture is not a monolithic service or microservices; it is a mixed content-plus-tooling repository. The primary code components are the TypeScript schema sources, the schema/doc generation scripts (scripts/generate-schemas.ts, scripts/render-seps.ts), and the sep-automation Node.js application (tools/sep-automation), which uses explicit interfaces for the GitHub client, hooks, and workflow rules. Core data flows are: TypeScript interfaces -> JSON Schema -> published schema files and examples; SEP markdown -> rendered MDX documentation; and GitHub issue/PR events -> SEP state machine -> comments and Discord webhooks. External dependencies include Octokit/GitHub App auth, Discord webhooks, TypeDoc/typescript-json-schema, Mintlify for docs, and Hugo for the blog. Although classified as an application repo because of its runnable tooling, CI/CD, and unit tests, the dominant character is an open-standards documentation and governance project. It is actively maintained, enforces a conformance-testing mandate for SDKs, and contains well-crafted modular code. The main risks are content-version overhead (six dated spec snapshots plus draft, duplicated docs, frozen historical SEPs) and process/doc drift, not software decay.
This repository implements a 'Repository Harness'—a Rust-based CLI framework designed to make software codebases legible and operable for AI agents. It functions as a control plane for agent-assisted development, managing project state (stories, decisions, traces) through a combination of Git-native documents and a durable SQLite layer. The system enforces architectural rules and invariants via mechanical validation rather than process bureaucracy, distinguishing between a generic 'Core' payload and product-specific 'Consumer' work (e.g., Symphony). Key capabilities include self-updating binaries, semantic changeset replay for auditability, and explicit agent skills for onboarding and auditing. Architecturally, the codebase follows a clean separation of concerns with a Rust workspace containing `harness` (core logic) and `harness-cli` (interface). It utilizes a repository pattern to decouple business logic from database access, implementing transactional logging via JSONL changesets that support idempotent replay. The tool manages its own lifecycle through a robust installer that supports cross-platform profiles (Core vs. Core+CLI) and handles file conflicts via deterministic three-way merges. Evidence capsules and epoch fencing ensure data integrity during agent interactions and state transitions. The project demonstrates a high level of engineering maturity through its focus on reproducibility and trust boundaries. It includes extensive documentation (ADRs, execution plans, stories) and a comprehensive test suite covering installer contracts, changeset rebuilds, and boundary checks. The separation of the 'Symphony' product into a distinct repository while retaining protocol primitives in the core highlights a mature approach to library vs. application boundaries.
Graphify is a CLI tool and library that extracts structural and semantic knowledge graphs from source code across 36+ programming languages. It parses files using tree-sitter grammars, builds a graph of nodes (functions, classes, modules, etc.) and edges (calls, imports, inheritance, etc.), performs community detection via Leiden/Louvain, and generates reports, wikis, and exports to formats like Obsidian, Neo4j, and FalkorDB. The system integrates with AI coding assistants through an MCP server (stdio/HTTP), skill files (SKILL.md, CLAUDE.md), and git hooks for automatic graph updates. Key entry points include `graphify extract`, `graphify query`, `graphify serve`, and `graphify install`. External dependencies include tree-sitter grammars, LLM APIs (OpenAI, Anthropic, Gemini, Ollama), and optional databases. The architecture is modular: per-language extractors in `graphify/extractors/`, graph assembly in `build.py`, clustering in `cluster.py`, and export in `export.py`. The codebase demonstrates strong engineering practices with extensive tests, atomic file writes, security validation (SSRF, path traversal), and cross-platform support.
Crawl4AI is a production-grade, async-first web crawling and scraping library designed to transform any website into clean, LLM-ready Markdown or structured data. It serves as both a Python library and a self-hosted Docker API server, making it suitable for RAG pipelines, AI agents, and data extraction workflows. The architecture is built on pluggable strategies: extraction (CSS, XPath, LLM, Regex), content filtering (BM25, pruning, LLM), chunking (topic, regex, sentence, sliding window), deep crawling (BFS, DFS, Best-First), and proxy rotation. Key entry points include the `AsyncWebCrawler` class with `arun()`/`arun_many()` methods, configuration objects (`BrowserConfig`, `CrawlerRunConfig`), and a CLI (`crwl`). The data flow progresses from URL → browser/HTTP fetch → raw HTML → cleaned HTML → Markdown → filtered content → structured extraction, with caching and cache validation as first-class features. External dependencies include Playwright for browser automation, httpx/aiohttp for HTTP, lxml for fast parsing, and optional LLM providers (OpenAI, Anthropic, Groq, etc.) and ML models (sentence-transformers). The Docker deployment adds a FastAPI server with JWT auth, Redis-backed job queue, webhook support, MCP bridge, and a monitoring dashboard, all hardened against SSRF, XSS, and file-write attacks. While primarily an application, the repository also contains data-research elements such as adaptive crawling with embedding-based relevance scoring, anti-bot detection heuristics, and content filtering research, reflecting a hybrid character dominated by the application/library use case.
Nanobot is a self-hosted, open-source personal AI assistant framework that operates as a full-stack application. The Python backend provides an agent loop with tool execution, session management, multi-provider LLM orchestration (OpenAI, Anthropic, etc.), and a plugin system for 18+ messaging channels (Telegram, Discord, Slack, WeChat, Feishu, etc.). It exposes a WebSocket-based gateway, an OpenAI-compatible API, and a CLI. Two frontends exist: a rich WebUI built with React/TypeScript/Vite/Tailwind and a terminal TUI built with Bun/OpenTUI. The architecture is event-driven via a message bus, with decoupled channel adapters, provider abstraction, and a config system supporting hot-reload. It includes security features like workspace sandboxing, credential redaction, and SSRF protection. The codebase is extensively tested (hundreds of unit/integration tests) and demonstrates strong engineering practices with clean abstractions, though its large dependency surface and multiple frontends introduce some maintenance surface area.
Herdr is a terminal workspace manager designed for AI coding agents. It features a client-server architecture where a persistent background server manages terminal panes, workspaces, and tabs, while thin clients (TUI and CLI) connect via Unix sockets/named pipes. The system enables detaching and reattaching sessions without losing agent state, provides agent-native control through CLI/socket API for spawning and managing AI agents (Claude, Codex, Copilot, etc.), and maintains session persistence across restarts and network disruptions. It includes a plugin system for extensibility, comprehensive AI agent integrations, and a rich terminal interface built with Ratatui.
OpenViking is an agent-native context database that unifies memories, resources, and skills under a virtual filesystem paradigm (viking:// URIs). It provides a three-tier context model (L0 abstract, L1 overview, L2 full content), recursive directory-based retrieval with visualized trajectories, and automatic session memory extraction. The system consists of a FastAPI HTTP server with embedded Rust components (RAGFS filesystem, vector index engine), a Rust CLI (ov), Python SDKs, a React/Vite Web Studio dashboard, and VikingBot - an agent framework with multi-channel support (Telegram, Slack, Feishu, etc.) and MCP integration. It integrates with OpenClaw, Claude Code, Codex, OpenCode, Hermes, and LangChain/LangGraph. The codebase demonstrates strong engineering: clean separation of concerns, async-first design, comprehensive test coverage (unit, integration, e2e), and production-ready deployment artifacts (Docker, Helm, multi-arch builds). Benchmarks show significant improvements over baseline agents on LoCoMo (82% vs 24-57% accuracy), tau2-bench (+6-12pp), and HotpotQA (91% at top-20).
Composio is a production-grade, dual-language SDK monorepo that connects AI agents to external services (Gmail, GitHub, Slack, Notion, Salesforce, and hundreds more) through a unified tool abstraction. In production it operates as the client layer of the Composio platform: applications create a Composio session bound to a user_id, discover toolkits, manage OAuth auth-configs and connected accounts, and execute tool calls either remotely or via a session-scoped Tool Router that also exposes hosted MCP endpoints. The repository ships a TypeScript SDK (@composio/core), a Python SDK (composio), a standalone Effect-TS-based CLI, 15+ framework provider adapters (OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI, AutoGen, Mastra, Vercel AI, Google/ADK, etc.), and a Next.js documentation site. It is unambiguously an application/developer-platform repo rather than data research, although it contains data-adjacent engineering assets: a cross-SDK JSON Schema conversion corpus, OpenAPI dereferencing tooling, a knowledge-base hybrid-search index, and telemetry redaction utilities.
Vigil is an open-source AI SOC (Security Operations Center) platform that orchestrates autonomous threat hunting, incident response, and case management through a multi-agent architecture. The system ingests security findings from SIEMs (Splunk, Elastic, Azure Sentinel), EDRs (CrowdStrike, Microsoft Defender), and other sources via Kafka or webhooks, then uses LLM-driven agents (hunt, root_cause, adjudicate, investigate, compose, chat) to analyze, enrich, and respond. A TypeScript agent layer with event-sourced ledgers and budget enforcement runs investigations, while a Python daemon handles polling, deduplication, and orchestration. The platform exposes its own tools via MCP (Model Context Protocol) and integrates with 30+ external security tools through a descriptor-based plugin system. The frontend is a React SPA with a setup wizard, dashboards, and case management UI. Deployment is via Docker Compose or Helm, with PostgreSQL, Redis, and optional Kafka as backing services.
Ruflo is a large, modular AI agent orchestration platform that extends Claude Code with a plugin ecosystem, swarm coordination, memory systems, neural learning, security enforcement, and federation. The core is a CLI tool (`npx ruflo`) that provides 26+ commands and 215+ MCP tools for managing agents, memory, security, hooks, and deployments. It includes a console UI inside Claude Code, a Svelte-based chat UI (ruvocal), and a React-based goal UI. The architecture is ADR-driven with clean separation into domain, application, and infrastructure layers across 35+ plugins and 20+ core packages. The system implements advanced patterns: CQRS for memory and swarm, circuit breakers for resilience, capability envelopes for security, Ed25519 signing for release integrity, and a harness loop for automated champion selection. It supports multi-model routing, hybrid vector search (HNSW + SQLite), watermarking (WASM-based Gumbel scheme), and neural learning (PPO, DQN, Decision Transformer). Federation enables cross-installation agent collaboration with zero-trust, HMAC-signed envelopes, and PII-gated data flow. While the codebase is well-structured and actively maintained, it has some maintenance risks: duplicate helper scripts across multiple directories, hardcoded version numbers in smoke tests, experimental alpha plugins, and a large regression test suite that requires ongoing upkeep. The plugin ecosystem is extensive but some plugins may be aspirational rather than production-ready.
OfficeCLI is a cross-platform CLI application written in C#/.NET that creates, reads, and mutates OOXML Office documents (Word .docx, Excel .xlsx, PowerPoint .pptx) without requiring Microsoft Office. It is explicitly engineered as an agent-facing tool: every document element is addressable through a uniform path syntax (e.g. /slide[1]/shape[2]), all commands emit structured JSON with error codes and suggestions, and it ships AI-skill files for Claude/Copilot/Cursor/Codex, an MCP server, plus Python and Node SDKs. The core operation model is a batch command language: documents are mutated by replayable JSON items (add/set/remove/get) executed atomically through the CLI or over a named pipe to a resident process. Architecturally the repo is a single .NET binary (embedded runtime) with a CommandBuilder layer, a DocumentHandlerFactory dispatching to three large partial-class handlers (WordHandler, ExcelHandler, PowerPointHandler), and a shared Core layer containing chart-to-SVG rendering, a formula evaluator implementing 350+ Excel functions with statistical distributions, pivot table construction, Mermaid diagram parsing, OOXML theme/table-style resolution, HTML/PNG/SVG preview rendering, and a plugin protocol for foreign-format dump-readers and exporters. Security is taken seriously: SsrfGuard validates remote fetch targets, HyperlinkUriValidator allowlists URI schemes, XmlTextValidator and DocumentLimits guard against decompression bombs and DOM sprawl, and AtomicPackageWriter prevents torn file writes. Quality is strong but carries real maintenance debt. The code demonstrates deep OOXML craftsmanship - schema-order-correct XML insertion, exact EMU unit round-trips, Lanczos-based gamma functions, and curated chart-style galleries. However, handlers are split across dozens of partial-class files that evolved from former god methods, the property API is stringly-typed (props dictionaries parsed per key), examples must be maintained in parallel shell and Python twins, and the tool deliberately tolerates 'UNSUPPORTED props' warnings (exit code 2), which can mask incomplete feature coverage. The best reuse targets are the self-contained Core utilities rather than the format handlers. The project is actively maintained with multi-platform CI publishing to npm and PyPI.
NanoClaw is a self-hosted, multi-agent AI orchestration platform that runs containerized agent sessions, integrates with a wide range of chat channels (Slack, Discord, Telegram, WhatsApp, iMessage, etc.), and provides a CLI-based admin interface. It is architected as a host service (Node.js/TypeScript, SQLite) that manages per-session agent containers (Bun runtime) isolated via Docker. The system features a typed guard/approval system for privileged actions, a plugin-based skill system for extensibility, and a structured migration framework for database schema evolution. Key operational flows include inbound message routing from channel adapters, session lifecycle management with two-DB mailbox split (inbound/outbound SQLite), container orchestration with credential injection via OneCLI vault, and host sweep for periodic maintenance. The CLI (`ncl`) provides resource CRUD with hooks, command guard integration, and a socket-based transport protocol. The project emphasizes a small, auditable codebase, skill-based feature installation over configuration, and deterministic setup/upgrade workflows with Claude Code fallback for error recovery.
Thunderbolt is a full-stack, cross-platform AI chat and agent client built by Mozilla Thunderbird. It ships as a React/Vite web app, a Tauri desktop shell (macOS/Windows/Linux), native iOS/Android apps, and a Bun-based CLI. The system provides chat with multiple LLM providers (OpenAI-compatible, Anthropic, custom Tinfoil enclave), a skills system for user-defined slash-command instructions, voice mode with STT/TTS, MCP tool integration, ACP (Agent Client Protocol) remote agent support, and a widget system for rich chat outputs (weather, maps, citations, document previews, link previews). The backend is an Elysia/Bun server handling OIDC/SAML/OTP auth, an inference usage ledger with signed receipts, a CORS-bypassing proxy with streaming, and PowerSync sync coordination. Data flows from local SQLite (wa-sqlite/bun-sqlite) through an E2E-encrypted PowerSync pipeline to PostgreSQL, with device registration, envelope key storage, and canary proof-of-possession for recovery. The CLI provides a separate agent harness with iroh P2P transport, device-grant auth, and a workspace jail for safe file operations. The repo also contains a substantial AI evaluation framework (scenario-based scoring with Wilson confidence intervals), a Pulumi/K8s/Docker deployment stack, and a marketing/docs site in Astro. While the dominant character is clearly an application, it has a notable data-engineering flavor in its inference usage tracking, eval harness, and telemetry pipelines.
Neuron AI is a PHP framework for building AI-powered applications with support for multiple large language model providers (OpenAI, Anthropic, Gemini, Mistral, Ollama, AWS Bedrock, etc.), tool integration, structured output, retrieval-augmented generation (RAG), and complex workflow orchestration. It provides a composable agent class that can operate in chat, stream, and structured output modes, a workflow engine with interrupt/resume and persistence, a built-in evaluation framework with LLM-based judges and assertions, and a Model Context Protocol (MCP) client for connecting to external tool servers. The architecture is modular: agents are built on top of workflows, tools are defined via PHP classes with JSON schema generation, and providers are abstracted behind a common interface with traits for shared logic.
Windows Copilot API is an unofficial Python library and OpenAI-compatible HTTP server that bridges the consumer Microsoft Copilot chat service. It uses a pure-HTTP driver with curl_cffi to impersonate Chrome and speak Copilot's WebSocket protocol, handling authentication, proof-of-work challenges, and Cloudflare Turnstile clearance in-process. A Playwright-based browser module enables interactive sign-in and scheduled clearance refresh. The server wraps the library behind FastAPI endpoints exposing /v1/chat/completions and /v1/models with full streaming support, rate limiting, and concurrency serialization to cope with Copilot's single-account constraints. Notable features include transparent token refresh, conversation persistence, and a diagnostic tool for session debugging. The codebase is well-structured, with clear separation of concerns across protocol constants, challenge solvers, models, and drivers. It demonstrates advanced reverse-engineering and browser-emulation skills.