Open-source repositories gaining traction right now.
106 repositories
#ai-agents
AI You Control: Choose your models. Own your data. Eliminate vendor lock-in.

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

18 AI personas deliberate your hardest decisions across multiple LLM providers. Aristotle, Feynman, Kahneman, Torvalds & more — structured multi-round deliberation with genuine model diversity. One command: /council

Macro is a unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM — @-linked together with shared AI memory.

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

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

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

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.

Enterprise Architecture Governance & Vendor Procurement Toolkit

🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.

Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

Star open-mercato / open-mercato AI‑supportive CRM / ERP foundation framework — built to power R&D, new processes, operations, and growth. It’s modular, extensible, and designed for teams that want strong defaults with room to customize everything. Better than Django, Retool and other alternatives - and Enterprise Grade!

One brain for all your agents

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

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


Local AI anywhere, for everyone — LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. No cloud, no subscriptions.

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.