Open-source repositories gaining traction right now.
50 repositories
#ai-agents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

12 Lessons to Get Started Building AI Agents

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

Sponsor Star Mintplex-Labs / anything-llm The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

from vibe coding to agentic engineering - practice makes claude perfect

Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.

Never stop coding. Free AI gateway: one endpoint, 231+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline & Copilot to FREE Claude/GPT/Gemini. RTK+Caveman stacked compression saves 15-95% tokens, smart auto-fallback, MCP/A2A, multimodal APIs, Desktop/PWA.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Learn it. Build it. Ship it for others.

"🐈 nanobot: The Ultra-Lightweight OpenClaw"

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Clone any website with one command using AI coding agents

Perplexica is an AI-powered answering engine.

A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

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

JavaScript in-page GUI agent. Control web interfaces with natural language.

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

Star google / adk-python An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.


Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!

Open-source AI coworker, with memory

Incremental engine for long horizon agents 🌟 Star if you like it!

Open-source All in One AI agent workspace. Run any agent — Claude Code, Codex — across your tools (100+ integrations + MCP), apps, browser, and files, with shared memory. Built-in models or BYOK.

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

Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executable todos, evidence logs, and verifiable handoffs.

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

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

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


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

An open-source AI assistant framework like openclaw


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

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

Recursive reasoning engine for AI agents and vector databases. Powered by MIT's RLM.
Paste a github.com URL. Submissions are reviewed before they are tracked.