Open-source repositories gaining traction right now.
106 repositories
#ai-agents
One brain for all your agents

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/

Star 0x4m4 / hexstrike-ai HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

Star GH05TCREW / pentestagent PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.

"🐈 nanobot: The Ultra-Lightweight OpenClaw"

Star kestra-io / kestra Event Driven Orchestration & Scheduling Platform for Mission Critical Applications


Sponsor Star hummingbot / hummingbot Open source software that helps you create and deploy high-frequency crypto trading bots

Star Jeffallan / claude-skills 66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.

Run OpenClaw, (formerly Moltbot, formerly Clawdbot) on Cloudflare Workers

A lightweight alternative to Clawdbot / OpenClaw that runs in containers for security. Connects to WhatsApp, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

AI-powered development platform for the future

Sponsor Star mikeyobrien / ralph-orchestrator An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

Battle-tested Claude Code workflows from power users. Self-correcting memory, parallel worktrees, wrap-up rituals, and the 80/20 AI coding ratio.

A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.

Self-learning data agent that grounds its answers in 6 layers of context. Inspired by OpenAI's in-house implementation.

To provide AI with Mermaid chart rendering capability, supporting both SVG and ASCII output formats


Security harness for AI agents — egress proxy with DLP scanning, SSRF protection, MCP response scanning, and workspace integrity monitoring

Star asheshgoplani / agent-deck Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

kubectl for AI Agents

An open-source AI assistant framework like openclaw

One API call. Full Claude agent. Completely sandboxed.


File-based kanban board CLI and TUI for multi-agent workflows. Skills included.


Agent Finder — One TUI to find, resume, and manage AI coding agent sessions (Claude Code, Codex)

AI-powered character generator built with React. Create detailed TRPG/Novel characters, NPC system prompts, and visual tags using Gemini, OpenAI, or Local LLMs.

量化投資研究 AI Agent — 透過 CLI 互動介面,自動搜尋財經新聞、分析市場情緒、產生風險評估報告。

42 AI agents. 9-layer consensus. One prompt. | Multi-agent orchestrator with ONNX neural routing, semantic convergence, and cross-LLM validation. https://nothumanallowed.com

An example configuration of AGENTS.md and a set of skills for AI-assisted game development with the https://defold.com engine.

Open-source firewall for AI agents. Policy engine that controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.

fullbleed official PDF engine

True async agentic tools — the model keeps talking while tools run in the background

Custom OpenClaw skills for AI agent capabilities - memory systems, prompt injection defense, intent routing, and platform integrations

MCP server giving AI assistants direct access to network infrastructure. 35 tools for multi-vendor device management, routing, config backup/rollback, SNMP, NETCONF, compliance checks, and subnet/MTU calculators. Works with Claude Desktop and any MCP-compatible client.

Automated project documentation generator for Claude Code and AI coding agents. Scans any tech stack, asks clarifying questions, generates CLAUDE.md + memory files + validation hooks. Dual-mode: slash commands inside Claude Code + standalone npm CLI.

Recursive reasoning engine for AI agents and vector databases. Powered by MIT's RLM.

Package safety checks for AI agents before install via MCP

godot sim

🦪💰 Framework-agnostic A2A payment system with SHIB on Polygon. Works with LangChain, AWS Bedrock, OpenClaw, AutoGen. Trustless escrow, negotiation, reputation. 9,416x cheaper than traditional escrow.

Stop Claude Code from burning tokens. Agent spawn limits, cross-session messaging, conflict detection, and worker orchestration.

Go framework for building AI agents with tool use, multi-agent orchestration, and planning. Supports OpenAI, Gemini, Anthropic, and Ollama.

An autonomous vibe coding agent with both web and cli interfaces and capability to directly edit files.
Paste a github.com URL. Submissions are reviewed before they are tracked.