LangGraph rigs 29
Agent setups committed in repos that use LangGraph. Median context tax 3.9k tok (index: 2.3k), average guardrails 0.5/5. Filter and sort these in the directory →
Top MCP servers
fastskills 1Context7 1openbrowser-ai 1mcp.arif-fazil.com 1python 1attune-help[plugin] 1inspeximus[mcp] 1factory 1
kayba-ai/agentic-context-engine
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
Pragmatist 1.6k tok · · Q15
agentic-community/mcp-gateway-registry
Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding assistants. Transform scattered MCP serve
Skill Collector 17.2k tok · · Q10
promptdriven/pdd
Prompt Driven Development (PDD): The Last Programming Language™. Prompt files are source; code is generated output.
Minimalist 1.4k tok · · Q5
voicetreelab/voicetree
The spatial IDE for recursive multi-agent orchestration. It's like an Obsidian graph-view that you work directly inside of.
Minimalist 1.3k tok · · Q18
wecode-ai/Wegent
Plan, build, and deliver with an open-source, self-hostable AI workspace for coding, collaboration, and automation.
Skill Collector 7.0k tok · · Q8
Cygnux-Labs/Tracekit
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
Skill Collector 3.9k tok · · Q56
sbhooley/ainativelang
AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower depende
Pragmatist 10.4k tok · · Q3
1mancompany/OneManCompany
Build Your Agent Company with OMC
Skill Collector 3.3k tok · · Q0
CronusL-1141/AI-company
Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC nat
Orchestrator 4.4k tok · · Q0
yonatangross/orchestkit
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stable (v9.x), or `ork-alpha` for the v10 line, which ships daily.
Skill Collector 10.2k tok · · Q3
billy-enrizky/openbrowser-ai
OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract
Pragmatist 2.6k tok · · Q0
MigoXLab/webqa-agent
Autonomous web browser agent that audits performance, functionality & UX for engineers and vibe-coding creators. 网站自主评估测试 Agent,支持 GUI/CLI 一键完成性能、功能使用与交互体验的测试评估
Pragmatist 4.2k tok · · Q0
martymcenroe/AssemblyZero
Parameterized multi-agent orchestration framework for Claude Code and Gemini
Minimalist 884 tok · · Q20
badhope/awesome-ai-devkit
Cross-platform scenario-based AI coding config ecosystem: turn Claude Code, Cursor, Codex, Gemini into full AI dev teams with plug-and-play roles, skills, workflows & quality gates. Prompt engineering + agent orchestration.
Skill Collector 4.2k tok · · Q3
ariffazil/arifOS
Independent policy kernel for AI agents: judge before execute. F1–F13 floors, VAULT999 receipts. Not a model. Not a chatbot.
Skill Collector 8.7k tok · · Q5
Cyrax321/CONTINUUM
CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as
Pragmatist 3.1k tok · · Q3
MnemeHQ/mneme
Architectural drift prevention for the agentic AI SDLC.
Minimalist 1.0k tok · · Q3
javded-itres/Holix
Helix is a powerful self-learning AI agent with memory, skills, and the ability to recall tools. It learns from successful tasks and creates reusable skills for the future.
Minimalist 289 tok · · Q3
protoLabsAI/protoAgent
Local-first agent that drives Claude Code and Codex over ACP. Desktop app, git-URL plugins, A2A 1.0. MIT.
Skill Collector 2.8k tok · · Q0
Smart-AI-Memory/attune-ai
Persistent memory and receipt-verified workflows for Claude Code — plugin, MCP server, and spec-driven dev framework in one pip install.
Skill Collector 27.0k tok · · Q52
DanceNitra/inspeximus
The self-correcting memory layer for AI agents. Zero-dependency Python memory and MCP server. Supersede, revert, or forget a value deterministically. Verifiable erasure, witness-backed tamper-evident receipts, EU AI Act ready.
Pragmatist 2.5k tok · · Q0
zrk222/code-factory
Evidence-first audits for AI-generated code: prove tests can fail, catch security and release gaps, and ship reviewable receipts across VS Code, JetBrains, CI, MCP, and App Store workflows.
Pragmatist 4.5k tok · · Q0
jazz1x/ohmyboring
Self-hosted personal memory RAG. Distills Claude Code sessions into a local, human-readable wiki and recalls on demand. Engine in Rust, hooks in Python, runs on Ollama. Zero cloud.
Pragmatist 4.6k tok · · Q0
techdeveloper-org/ai-native-sdlc-engine
Autonomous SDLC orchestration engine built on LangGraph with push-gate MCP, policies, and multi-agent coordination.
Pragmatist 7.9k tok · · Q0
Sandeeprdy1729/timps-swarm
160 specialist AI agents for Claude Code, Cursor & Codex — one npm install puts them all into your IDE as MCP tools and parallel sub-agents. Local-first, BYOK, works offline with Ollama.
Orchestrator 9.7k tok · · Q0
kisbi3/ContextTrail
Evidence-linked project history from local Codex and Claude Code transcripts
Pragmatist 17.6k tok · · Q8
matteopasseri407/NeXgen-Engine
One Git repo to configure every AI CLI — AGENTS.md, MCP, skills, memory rendered to each tool's native format, checked for drift and synced fail-closed. Linux & Windows released.
Skill Collector 914 tok · · Q3
bobbyaqlaar/AgentSmith
Governance for software built with AI coding agents, apps that call LLMs, and apps made of agents: design-before-code and recorded reviews in Claude Code and Cursor, CI security and eval gates, and runtime guardrails (budgets, PII, tool all
Automator tok n/a · · Q24
darrenpaine/harnessd
Spec-driven, traceable AI coding harness, demonstrated on a FastAPI + LangGraph + Redis agent service.
Minimalist 1.4k tok · · Q15