Search

Self-improving agentic research swarm with local LLM inference

Autonomous LLM routing agent. Self-learning, cost-aware, auditable.

AI Space: huggingface/open-source-agent-contributions

Bug bounty agent framework for Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot, and OpenClaw — 48 agents, 26 commands, 19 CLI tools, 2 MCP servers, autonomous hunt loops, exploit chain builder.

electron anthropic claude-agent-sdk mcp bun websocket thin-client multi-llm openapi skills automations oauth desktop-ai github-copilot google-ai chatgpt devtools apache-2 headless-server pi-sdk vscode-alternative linux macos windows

Build durable, distributed AI agents in Go — tool calling, MCP, human approvals, and sub-agent delegation. Temporal-first.

A self-evolving MCP server that gives AI agents the ability to control any macOS app — including the ones without APIs. 388 tools auto-discovered. 80 tests.

The ultimate autonomous AI agent framework for Termux, powered by Google Gemini. Features a high-autonomy reasoning loop and dynamic tool loading.

Universal MCP server gateway for AI agents. Discover, activate, and orchestrate 3,400+ Model Context Protocol tools from a single config. Semantic routing, JIT tool loading, FSM gating. TypeScript/stdio.

Kazi Core is a self-hostable, open-source agentic engine. Plug in your own tools, run on your own infrastructure, and keep full control of your data.

Production-ready Go scaffold template with clean architecture, lifecycle-managed dependency injection (samber/do), HTTP server (net/http + Huma/OpenAPI), CLI scaffolding, 45+ AI agent skills for Claude/Copilot/OpenCode, and built-in DevOps security tooling.

MCP-native AI agent OS — Redis bus, squad service, multi-model engine. Connect any agent with one URL.

Taiji Agent - 太极智能体框架，集成 WFGY 防幻觉引擎的多 Agent 协作平台

A domain-ontology-driven agentic framework for LLM-based personal-finance reasoning across banking and personal-investments, with formal Action / Provenance / Constraint axes around the agent loop.

Adds Laravel Wayfinder AI Agent Skill To Your Project

Epsimo CLI - TUI dashboard, smart CLI, AI agents, projects, threads, Virtual Database, and deployments from the terminal.

Security enforcement layer for AI coding agents (Claude Code, Cursor, OpenAI Codex, custom runtimes). Blocks dangerous commands, audits every tool call, detects prompt injection. Usable as a CLI, a Node library, or a plugin.

AgentMesh SDK - P2P Encrypted Messenger for AI Agents

AI My API! Typescript sandbox for AI agents to interact with your API in a safe way.

Installer and updater for Boost OS.