Search awesome repositories

Proof and repair for Apple coding agents. Validate Swift, run Xcode evidence, repair failures, and generate inspectable Apple-native capabilities.

Open-source, self-hosted knowledge backend for AI agents — hybrid search (vector + keyword), MCP server, 5 connectors, Docker-ready

Open infrastructure for AI agents to discover and pay each other

One interface for your whole data stack, with built-in safeguards and a simpler workflow for your team. Written in Rust. Docker not needed.

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.

P2PCLAW Research White Paper Series II — 16x16 chess-grid autonomous research agent with evolutionary memory and self-improving capabilities.

Seamlessly integrate AI agents with Chargebee using AgentKit for smarter billing and subscription workflows.

Independent control for AI agent actions. Use any agent. Route risky actions through one policy boundary before they send, deploy, push, publish, or spend.

MCP server + REST API for the P2PCLAW decentralized AI research network. Lets agents publish papers, vote on the mempool, and join the swarm. Powers www.p2pclaw.com.

Use existing brand guidelines with AI. Turn websites, PDFs, and Figma into a portable .brand runtime through MCP.

Terminal-native LifeOS with an optional local Web UI for tasks, notes, habits, schedules, timelogs, relationships, and human-agent collaboration.

The finmap.org MCP server provides comprehensive historical data from the US, UK, Russian and Turkish stock exchanges. Access sectors, tickers, company profiles, market cap, volume, value, and trade counts, as well as treemap and histogram visualizations

Dockable terminals for Claude Code, Codex & Antigravity by day, an unattended task queue by night. Each task gets its own git worktree; review the diffs over coffee.

AI team for Codex — researcher, PM, architect, developer, QA, and reviewer orchestrated through a configurable pipeline.

P2PCLAW v3 — Decentralized AI research network. 14 autonomous agents, P2P via Gun.js, IPFS storage, 3D swarm visualization, paper publishing, peer review. Next.js 16 + React Three Fiber.

MCP server that lets your ai agent press sound buttons. it's not that deep.

Universal MCP Server for finding + connecting to agents anywhere on the planet. https://hol.org/mcp

No description.

Intelligent PostgreSQL tooling for VS Code | Build, explore, and query Postgres faster

Open-source AI coding agent for your terminal that you can undo, even its shell commands. 250+ models, /taste for AI-slop UI, model racing and parallel swarms. MIT.

Terminal-native LifeOS with an optional local Web UI for tasks, notes, habits, schedules, timelogs, relationships, and human-agent collaboration.

Cut the chatter. Keep the work. A measured communication policy for coding agents: −32% output tokens, zero lost facts.

Open HTTP protocol for human decisions in AI agent workflows. Service-hosted reviews, structured approvals, selections and forms, with optional messenger actions.

Reference and issue mirror for @spfunctions/cli, the SimpleFunctions sf command-line interface.

Open-source, local observability TUI for Claude Code and Codex — context, cost, tokens, agents, tools, compactions, and code changes.

Curated MCP server for Google Workspace: Gmail, Calendar, Drive, Sheets, Docs, and Tasks via the official gws CLI. 49 focused tools instead of 400, side effects declared on every one. The permissions leg of trust infrastructure for agents.

The missing cognitive primitive for AI agents. Decompose any text into classified semantic units — authority, risk, attention, entities. No LLM. Deterministic.

The simplest AI-ready secrets manager. Local-first, single-binary CLI & Desktop app with MCP integration. Never expose secrets to AI agents.

BenchClaw — Multi-dimensional AI agent evaluation with 17-judge AI Tribunal, 10 scoring dimensions, radar charts, and deception detection. Benchmark any LLM agent.

Self-hosted MCP server for AI agent memory — 14 core tools, profile-based tiering (86+ available). 88.2% LoCoMo. Works with Claude, Cursor, Windsurf.