LangChain is a comprehensive framework for building LLM-powered applications. It provides core abstractions for language models, prompts, chains, agents, memory, and tools, enabling developers to create complex AI systems like chatbots, question-answering agents, and retrieval-augmented generation pipelines. The architecture is modular with clear separation between core langchain_core foundations, legacy langchain_classic components (many deprecated), and partner integrations for specific LLM providers and vector stores. Key entry points include agent creation functions, chain constructors, and memory/retriever interfaces. The framework emphasizes composability through the Runnable interface (LCEL) and supports both synchronous and asynchronous operations. While extensive, the codebase shows strong maintenance practices with active dependency management and version consistency checks across integrations.
CodeGraph is a local-first, cross-language code intelligence engine designed to give AI coding agents structured knowledge of a codebase: symbols, references, call graphs, import graphs, inheritance, routes, and framework-specific dynamic dispatch. It indexes source with tree-sitter WASM grammars (or an optional native Rust kernel for speed), stores the resulting graph in SQLite with FTS5, then resolves cross-file references and synthesizes edges for indirect patterns like web frameworks, DI containers, callbacks, and event dispatch. The primary interfaces are a CLI (codegraph), an MCP server exposing tools for agents, an embeddable programmatic API, and a Svelte web viewer.
LangGraph is a production-grade Python framework for building stateful, resumable, multi-step LLM agent workflows, distributed as a monorepo of Python packages (core `langgraph`, `langgraph-sdk`, `langgraph-cli`, checkpoint backends, prebuilt agents) plus JS/TS SDK examples. The core is a Pregel-inspired execution engine: `StateGraph` compiles user-defined nodes and conditional edges into a `Pregel` runnable, where typed state channels (`LastValue`, `Topic`, `DeltaChannel`) apply reducer-based updates across supersteps. The engine supports durable checkpointing (in-memory, SQLite, Postgres), interrupts for human-in-the-loop, retry/timeout policies, subgraph composition, and v3 streaming. The CLI can scaffold projects and deploy graphs to LangGraph Cloud or self-hosted runtimes via Docker; the SDK provides sync/async clients that drive remote graphs over HTTP/SSE/WebSocket with typed stream projections (messages, tool calls, lifecycle). This is purely an application/framework repo; the `examples/` notebooks are usage demonstrations, not research pipelines. Primary data flow: user code builds a graph and compiles it; invocation reads channel state from a `BaseCheckpointSaver`, runs eligible nodes (with optional caching/retry), applies channel updates via reducers, writes the new checkpoint per superstep, and emits streamed events through a transformer pipeline (`StreamMux`). The SDK's v3 streaming protocol adds reconnection, subscription fan-out, and scoped subgraph handles over an SSE/WebSocket transport. External dependencies center on `langchain-core` (messages, tools, runnables), Pydantic, `httpx`, `psycopg`, `msgpack`, `orjson`, with optional `redis` and `pycryptodome` for cache/encryption. The codebase exhibits exceptional engineering: extensive unit/integration/conformance tests, a formal conformance suite that pins checkpoint-backend behavior across implementations, security-conscious serialization (strict msgpack/json module allowlists, a patched path-traversal vulnerability in the SDK), and benchmarks. Notable weaknesses are real but contained: heavy sync/async duplication in SDK clients and transports, a fast-moving deprecation path (many renamed APIs, `MessageGraph` slated for removal), and beta features (`DeltaChannel`, `ServerRuntime`) marked unstable. The `@task`/`@entrypoint` functional API, `create_react_agent` prebuilt, and conformance test framework are the most stable and reusable surfaces.
This repository is a meticulously crafted template for using AI coding agents to reverse-engineer live websites into clean, modern Next.js codebases. It provides a pre-configured Next.js 16 scaffold (with shadcn/ui, Tailwind v4, and TypeScript strict) alongside a sophisticated set of agent instructions that guide the AI through the entire cloning process: mapping URLs, observing the target, building components, and comparing results. The project is not just a code scaffold; it is a complete workflow definition designed for Claude Code, Codex, Cursor, and OpenCode. The architecture is elegantly split between the application scaffold (src/, public/) and the agent skill definitions (.agents/skills/clone-website/). The canonical skill (SKILL.md) and its references (inspection-guide.md, framer-and-motion.md) represent a masterclass in prompt engineering, providing concrete, actionable guidance for handling complex scenarios like Framer-generated pages, scroll-driven animations, and responsive asset extraction. The project structure enforces clean separation of concerns for multiple cloned sites. The codebase demonstrates exceptional craftsmanship and a deep understanding of both software engineering and AI agent capabilities. The highlighted components—the agent skills, the token-counting CI workflow, and the cross-platform agent configuration—are genuinely reusable patterns that solve non-obvious problems. This is a rare example of a template that is more valuable for its workflow and documentation than its application code, setting a high standard for AI-assisted development projects. Maintenance is active, technical drift is low, and the project is a strong 9.0 on the quality scale.
browser-use is a comprehensive Python framework that enables AI agents to automate web browser interactions. It provides a unified interface for controlling browsers through Playwright/CDP, integrates with multiple LLM providers for decision-making, and includes sophisticated features like structured data extraction, security controls, token usage tracking, and sandboxed execution. The architecture is modular with clear separation between agent reasoning, browser management, tool execution, and extensibility mechanisms. Key innovations include a flexible action registry system with special parameter injection, domain-aware security watchdogs, automatic LLM cost tracking, and MCP integration for extending agent capabilities. The project demonstrates strong engineering practices with extensive testing, CI/CD pipelines, and comprehensive documentation through examples.
oh-my-openagent (omo) is a massive, actively-developed TypeScript monorepo that ships as a multi-harness AI-agent orchestration plugin. Its production function is to instrument coding-agent runtimes (OpenCode, OpenAI Codex CLI, and adapters for Claude Code and other harnesses) with a rich layer of lifecycle hooks, background agents, multi-model routing, LSP/AST tooling, team-mode parallelism, and a curated prompt system — all installable via a single `bunx oh-my-openagent install` or `npx lazycodex-ai install` command. The architecture is a workspace of 20+ pure-TypeScript core packages (model-core, rules-engine, skills-loader-core, team-core, tmux-core, delegate-core, hashline-core, lsp-core, mcp-client-core, etc.) that are consumed by two main adapter packages: `omo-opencode` (the full-featured OpenCode plugin with 11 agents, 54+ hooks, team mode, ultrawork/ULW loop, background agents, Codegraph MCP, etc.) and `omo-codex` (a lightweight Codex CLI plugin that vendories a subset of components — rules, comment-checker, LSP, git-bash, ultrawork, ulw-loop, telemetry — as isolated Codex components). A large shared-skills layer provides cross-harness SKILL.md files for programming languages, frontend design, ultimate browsing, debugging, and more. The codebase is notable for its aggressive package layering refactor (documented in ROADMAP.md), its strict no-excuse TypeScript policy, extensive automated QA evidence (.omo/evidence/), and its depth of agent-facing features like hash-anchored edits, prompt-async-gate, runtime fallback with model-suggestion retry, and the start-work/ULW-loop goal orchestration systems. With 64K stars, daily commits, 790 open issues, and a sprawling CI matrix, it is one of the most ambitious open-source agent-orchestration projects in maintenance today.
The OpenAI Agents SDK (Python) is a production-grade library for building agentic AI applications. It provides a complete agent runtime (`Runner`, `Agent`, `RunConfig`) with support for tool calling, handoffs, guardrails, sandboxed execution (Docker, Modal, E2B, Cloudflare, Vercel, Unix-local), realtime voice/audio pipelines, MCP integration, and multi-provider model routing (OpenAI, LiteLLM, AnyLLM, custom). The codebase is async-first with extensive tracing/observability, session persistence (SQLite, OpenAI Conversations, Responses Compaction), and a rich lifecycle-hook system. It includes a large test suite covering unit, integration, and sandbox security scenarios, plus internal tooling skills for release management and code review. The SDK is actively maintained with a 0.23.x version, release automation via release-please, and comprehensive docs in English and Japanese.
pgGraph is a PostgreSQL extension written in Rust (via pgrx) that adds high-performance graph query capabilities directly into PostgreSQL. It allows users to model graphs by registering existing relational tables as nodes and edges, building a compressed sparse row (CSR) adjacency index for sub-millisecond traversals, shortest paths, and connected components. The extension exposes SQL functions (`graph.traverse`, `graph.shortest_path`, `graph.search`, `graph.gql`, `graph.cypher`) and supports both openCypher and a subset of GQL for querying property graphs. It integrates deeply with PostgreSQL security (row-level security, multi-tenancy, ACLs), provides resource governance (memory, disk, work unit budgets), and includes a durable projection layer with atomic manifests, delta segments, compaction, and crash recovery. The codebase is structured as a pgrx extension with a Rust core, SQL bootstrap scripts, background workers for build/maintenance jobs, and an extensive test suite including fuzz targets, property-based tests, and heavy integration tests for concurrency, crash recovery, and performance gates.
Orca is a production-grade Electron desktop application that functions as an integrated development environment (IDE) and orchestrator for multiple AI coding agents (Claude Code, Codex, Gemini, etc.). It manages isolated worktrees (Git, SSH, WSL) as execution environments, provides a full-featured terminal emulator (xterm-based), a browser pane, rich markdown editing, and deep source control integration (GitHub, GitLab, Linear, Jira). The system is architected as a monorepo containing the Electron desktop app (main/renderer/preload), a React Native mobile companion, a Node.js CLI, and cloud services (relay, push) for mobile pairing and notifications. Communication between processes is handled through a strict, Zod-validated RPC contract, ensuring type safety across the wire. The codebase demonstrates exceptional engineering discipline with a massive test suite (Vitest, Playwright), extensive CI/CD pipelines, and a strong emphasis on platform compatibility (macOS, Windows, Linux, WSL, Wayland). It is actively maintained with daily releases and a clear focus on managing technical debt through explicit legacy compatibility shims and migration paths.
The Front-End Checklist is a comprehensive, open-source platform for front-end quality assurance, targeting both human developers and AI agents. It delivers a curated corpus of 386+ best-practice rules across 11 categories (HTML, CSS, JavaScript, Performance, Accessibility, SEO, Security, Images, Testing, Privacy, i18n) via a Next.js web application, a Model Context Protocol (MCP) server, and a standalone CLI. The architecture is a pnpm monorepo with shared packages for authentication (Better Auth + Prisma), design system (Radix UI), analytics (OpenPanel), state management (Zustand), search (FlexSearch), storage (IndexedDB), and validation. The MCP server exposes 11 tools (audit_url, review_code, search_rules, etc.) for AI-assisted code review and URL auditing, while the CLI provides offline audit capabilities. The web app offers rule browsing, user checklists with progress tracking, guides, and public profiles. The system is production-deployed on Vercel with PostgreSQL, Sentry error tracking, and Upstash rate limiting.
This repository is a production-grade meta-framework for building and managing AI agent plugins across multiple coding assistants (Claude Code, Codex, Cursor, OpenCode, Gemini, Copilot). It establishes a single source of truth in Markdown (`plugins/`) that is compiled into harness-specific artifacts via Python adapters. Key features include a security layer using Cedar policies for tool-call authorization and signed audit receipts, a project management system (`conductor`) for track-based development, and a quality evaluation framework (`plugin-eval`) using static analysis and LLM-based scoring. It solves the fragmentation problem of AI agent ecosystems by enforcing portability and governance.
Chroma is an open-source vector database designed for AI applications, providing efficient storage and retrieval of embeddings with metadata. The system supports both single-node (SQLite) and distributed deployments (Spanner, S3, gRPC microservices) with a multi-language architecture: Python for the client API and embedding function ecosystem, Rust for high-performance data-plane services (frontend, worker, log, compaction, garbage collection), Go for the control-plane sysdb, and TypeScript/JavaScript for web clients. Key features include HNSW, SPANN, and MaxScore sparse indexing; RaBitQ quantization; write-ahead log replication (WAL3); conditional transactions for optimistic concurrency; authentication/authorization (basic, token, RBAC); rate limiting and quota enforcement; OpenTelemetry observability; and a CLI with TUI. The repository also contains an AI agent subsystem (Anthropic integration, trajectory storage) and a foundation API for hosted service capabilities. While the codebase is well-structured with extensive property-based testing and reusable patterns (operator/orchestrator, component system, configurable backends), it suffers from multi-language duplication and ongoing client migration (old vs new JS packages).
Mem0 is a production-grade memory layer for AI agents, providing persistent, searchable, and updatable memory across sessions. It operates as both an open-source Python/TypeScript SDK and a hosted platform (api.mem0.ai). The core library abstracts away LLM providers (OpenAI, Anthropic, Groq, vLLM, etc.), embedding models, vector stores (over 20 backends including Qdrant, Pinecone, PGVector, Chroma, Weaviate, and many more), and rerankers behind a consistent config-driven interface. Memory operations (add, search, update, delete) support scoping by user, agent, session, or run, and leverage hybrid search combining semantic, BM25, and entity-boost signals with configurable reranking. The repository is architected as a monorepo with a clear separation of concerns: the core SDK packages (`mem0/` for Python, `mem0-ts/` for TypeScript), a self-hosted FastAPI server with a Next.js dashboard, CLI tools in both Python and Node.js, and a comprehensive plugin ecosystem for AI coding agents (Claude Code, Cursor, Codex, Kimi, Antigravity, Pi Agent, OpenClaw, etc.). Each integration follows a uniform hook adapter pattern, translating native agent events into memory operations via MCP servers or shared core modules. The platform backend includes authentication, API key management, telemetry via PostHog, and a webhook system for event-driven workflows. Key data flows: An application calls `memory.add()` with messages and metadata → the SDK extracts facts via an LLM → embeds them using the configured embedder → stores vectors and metadata in the chosen vector store. On `memory.search()`, the query is embedded, hybrid-scored against stored vectors (with optional reranking), and results are returned with relevance scores. The system supports temporal reasoning (timestamp filtering, memory decay), entity-based partitioning, custom categories, and feedback mechanisms to refine future retrievals. External dependencies include LLM APIs, vector databases, embedding services, and optionally Redis/SQLite for local history.
The skills CLI is a tool for managing reusable instruction sets (skills) for AI coding agents. It enables users to discover, install, update, and remove skills from various sources including GitHub, GitLab, local paths, and well-known endpoints. Skills are installed to agent-specific directories (e.g., for Claude Code, Cursor, GitHub Copilot) via symlinking or copying, with tracking via lock files to support updates and reproducibility. The application follows a modular command-based architecture, with each command (add, remove, list, etc.) implemented in separate files. Key reusable components include a provider pattern for extensible skill sources, a lock file system for tracking installed skills, a secure installer with path safety checks, and input sanitization to prevent terminal injection vulnerabilities. The tool also collects anonymous telemetry (with opt-out) to improve the ecosystem.
Invisible Dots is a self-hosted, open-source platform for deploying and managing persistent AI agents ('Dots'). Each Dot operates within its own dedicated QEMU virtual machine, providing a secure, isolated environment with a full Linux desktop, browser, and file system. The platform is designed for undetectability and long-running autonomy, serving as an open-source alternative to proprietary agent services. The system is a polyglot monorepo with a strict separation between the host control plane (TypeScript) and the guest agent (Go) and engine (Python). The host manages VM lifecycle, scheduling, a web UI, CLI, and messaging channels (Telegram/WhatsApp). The guest runs a Go daemon for low-level system access and a Python engine (forked from nanobot) that orchestrates LLM calls, tool execution, and permissions. Key features include a granular permission system with approval workflows, a cron-like task/automation system, cost capping per task, and a comprehensive benchmark suite for evaluating agent capabilities. The codebase demonstrates exceptional engineering craftsmanship with clean abstractions (Database, Channels, Computer), robust testing strategies (contract tests, fakes, e2e), and reusable utility libraries (ISO writer, SSE parser, atomic file operations). While primarily an application, the project includes a significant research-oriented benchmark suite (tests/bench) and the engine itself is a research fork (nanobot), giving it a hybrid character. The core value, however, is as a production-grade application platform.
planning-with-files is a persistent, file-based task-planning system for AI coding agents. It maintains task_plan.md, findings.md, and progress.md on disk and wires into agent lifecycle hooks (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, PreCompact, Stop) across Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, Pi, Hermes, and a dozen other assistants, re-injecting plan context into the model's context window on every turn. Plans survive context loss, /clear, compaction, and crashes; a session-catchup mechanism recovers prior transcripts. A v3 gated mode can block the agent from stopping until plan phases complete, backed by an append-only JSONL run ledger, stall detection, and SHA-256 plan attestation that makes hooks refuse to inject tampered content. Architecturally it is a distribution hub rather than a single application: a canonical skill under skills/planning-with-files is mirrored byte-identical into 15+ IDE-specific directories, with native TypeScript plugins (OpenCode, Pi, DSH), a Python plugin (Hermes), and shell/PowerShell hook dispatchers. Plan resolution is a fail-closed chain (PLAN_ID env → .active_plan pointer → newest plan dir → legacy root) guarded by slug validation, containment checks, symlink/junction rejection, and strict PWF_PLAN_ROOT pinning. The engineering is unusually rigorous for an agent-skill repo: 400+ pytest tests, byte-parity tests between shell/PowerShell/Python/TypeScript twins, a PATH-stub BSD userland simulation to catch GNU-only flags that silently fail on macOS, and heavy Windows PowerShell 5.1 / Git Bash portability hardening. Non-obvious patterns include KV-cache-stable injection output (no timestamps or free text in summaries, wall-clock normalization to T00:00:00Z) and an mtime-keyed attestation cache for performance. The repository is a developer tool, not a data/research project; although it ships benchmark and eval documentation (assertion pass rates, recovery-turn comparisons), those are verification evidence for the skill, not analysis artifacts. It is actively maintained at v3.24.0 with recent commits, 4 open issues, and 100+ releases; technical drift is low, with the main maintainability risk being deliberate duplication across 20+ canonical mirrors, mitigated by sync-ide-folders.py and parity tests but still a possible source of silent drift.
Gentle-AI is a CLI-driven application that manages AI coding agents through installation, configuration, and review workflows. It provides a deterministic engineering environment with features like persistent memory (Engramâ„¢), receipt-driven development (RDD) for verifiable code reviews, and telemetry collection. The architecture is modular, separating concerns into CLI commands, agent adapters, components (like Skills and Context7), review transaction logic, state management, and a text-based user interface. The system interacts with external AI agents (Claude Code, OpenCode, Cursor, etc.) via adapter patterns, manages state in $HOME/.gentle-ai, and supports cross-platform operation (Linux, macOS, Windows). Key entry points include the gentle-ai CLI command and TUI screens for interactive workflows.
Liveblocks is a real-time collaboration infrastructure platform providing SDKs and APIs for adding presence, storage, comments, and notifications to applications. The monorepo contains core CRDT-based synchronization logic, framework-specific integrations (React, Next.js, etc.), and numerous examples demonstrating usage. Key architectural elements include a custom protocol for real-time data sync, React hooks for accessing Liveblocks data, and a provider pattern for room scoping. The platform supports AI-enhanced collaboration features through copilots and knowledge integration. The SDKs are designed for extensibility, allowing developers to define custom presence and storage types while maintaining type safety. UI primitives (avatars, buttons, tooltips) are built with Radix UI and Tailwind CSS, offering consistent and customizable components. Authentication and room management are handled via secure endpoints, with examples showing integration with NextAuth, custom APIs, and various backend services. Examples cover a wide range of use cases from collaborative text editors (Tiptap, Lexical, Yjs) to whiteboards, spreadsheets, and AI-powered dashboards. Starter kits provide production-ready templates with authentication, organization management, and deployment configurations. The active maintenance and frequent updates ensure compatibility with modern frameworks and address evolving collaboration needs.
This repository contains a sophisticated COBOL modernization toolkit that uses AI agents to analyze, extract business logic from, and convert legacy COBOL code to modern Java (Quarkus) or C# (.NET) applications. The system features an agent-based architecture with specialized agents for structural analysis, business logic extraction, dependency mapping, and code conversion. It includes a web portal for monitoring migration progress, visualizing dependency graphs, and interacting with AI assistants. The toolkit handles large COBOL files through intelligent semantic chunking that preserves code context across chunks, and uses a hybrid persistence approach (SQLite for metadata, Neo4j for graph visualization) to store migration artifacts. Key innovations include a three-tier complexity reasoning system that dynamically adjusts AI effort based on code complexity, semantic unit-aware chunking, and cross-chunk consistency mechanisms for type mappings and signatures.
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.