#ai-agents Repositories
1,514 repositories total
A self-hostable AGPL workspace where humans and AI agents share chat, tasks, knowledge, approvals, and MCP context.
FPF (First Principles Framework) Library: methods and pattern languages for open-ended development and a shared culture of thinking and acting among people and AI agents. Use individual methods or combine them to solve difficult problems and expand capabilities.
ClawLess โ A serverless browser-based runtime for Claw AI Agents powered by WebContainers
A curated catalog of 230+ semantic anchors: well-defined terms like arc42, TDD London School, or tracer bullet that activate deep, consistent knowledge in LLMs. Use them in prompts, skills, and agent instructions instead of spelling out methods yourself.
MCP server for SSH: let Claude Code, Codex, and any MCP client run commands, transfer files, and manage servers over SSH, with human approval, an encrypted vault, and a live audit trail. Desktop app and CLI included.
Put thousands of live DOM nodes on an infinite canvas: the GPU draws them, an editor selects, moves and resizes them, shaders and transitions run on them, and an AI agent can read them and point at them.
Vicoa is the agentic IDE for running a team of coding agents from desktop, mobile, or VPS. Open-source and self-hostable.
Where terminal agents work together. Claude Code, Codex, Copilot CLI, and pi on the same task, in one mission, each keeping its own TUI in a real terminal.
200+ production open source Rails apps & engines in one repo. Search across real codebases with AI agents to research architectural patterns.
Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, audit trails. Works with LangChain, CrewAI, MCP.
Paxeer X is a Distributed HyperState Machine for payments, code execution and intent routing. Designed for Machines and the Users operating them.
Open-source software factory infrastructure for advanced AI coding workflows
A Unicode canvas for humans and AI. Draw diagrams, interfaces, and slides as editable text.
HackAgent is an open-source security toolkit to detect vulnerabilities of your AI Agents
Here are the Top 100 prompts on GPTStore, which we can use to learn and improve prompt engineering.
Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review.
The open-source agent system that writes research papers with verified citations. Every citation is checked against Crossref, OpenAlex, and Semantic Scholar.
Use MCP to let almost all your agents access QQ, WeChat, and Bilibiliโand even jump into group chats and send messages yourself!
Self-hosted web search for AI agents: a CLI + MCP server that wraps SearxNG to aggregate Google, Bing, DuckDuckGo, Brave, and moreโno API key or paid search API required. Works with Claude Code, OpenClaw, Antigravity, and any shell; optional Tavily backend. Self-hosted web search for AI agents (SearxNG).
Mega is an open-source implementation of Google Piper โ a Git-compatible monorepo engine built for the AI Agent era.
Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
๐ฅ A library based on Xcode Preview, for easy generation: Playbook view, Snapshot and Accessibility tests. SwiftUI and UIKit supported!
Official DESIGN.md files published by companies themselves. First-party design systems that AI agents read to generate consistent UI.
๐ A learning tutorial called โlangent,โ formed by combining โlangโ and โagentโ
Find which script, notebook, data, command, or AI agent produced a file โ locally, with evidence and honest uncertainty.
Turn your workday into structured workflows agents can execute. 100% local, served over MCP.
Open-source AI e-commerce image workspace: product hero images and detail pages, batch image translation, Xiaohongshu posts with images and text, and LangGraph agents. Supports Windows/macOS and local deployment; use your own model API. Open-source e-commerce image generator, translation, and agent workspace.
Open-source, self-hostable alternative to ChatGPT and NotebookLM โ agents, skills, MCP, and cited knowledge in one AI workstation. Your models, your infrastructure. Includes public MCP server and agent skills directories.
A Curated Collection of the Most Practical Claude Code Skills / Agents / Plugins | 50+ Picks | Organized by Use Case | Includes Recommendations | Copy and Install
ModelScope Purple Book | ModelScope Cookbook: A hands-on guide to open-source model applications for developers, covering model selection, inference, fine-tuning, evaluation, RAG, agents, and AIGCโfrom running your first model to building real-world applications.
An SDK for working with LLMs and AI Agents from Apache Airflow, based on Pydantic AI
Structural code intelligence for AI agents โ semantic search, knowledge graphs, and a built-in MCP server in one Rust binary. Give Claude, Cursor, and any MCP client a deep understanding of your codebase.
Harnessclaw is a powerful, Electron-based desktop application designed to manage, chat with, and operate AI agents and skills seamlessly.
Open-source mobile SSH/Mosh terminal and native AI workspace for Android and iOS.
๐ Capri โ an Edgerunners-inspired AI agent for your desktop. Works with Claude Code, Codex, Antigravity & more.
Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.
Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.