#ai-agents Repositories
1,514 repositories total
AI-native cross-platform sandboxes for developers, featuring multimodal cloud runtime and expert agents.
Ryugi (ryoo-ghee) โ artifacts for coding agents: mockup artboards, design docs, whiteboards, HTML benches, and verification reports you can comment on, with every comment sent back to the agent. Install artifacts only, or the full brainstorm โ spec โ TDD workflow. Claude Code, Codex, and more.
Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results: a clear view of whatโs done, in progress, parked, or blockedโwithout scrolling a marathon chat.
๐ค Awesome list of AGI Agents. Curated resource collection for Agents.
The first agentic payment network: policy-controlled, gasless, and real money-ready. OmniClaw CLI + Financial Policy Engine let autonomous agents pay and earn safely at machine speed.
๐ฅ๐ฅ๐ฅ A Comprehensive Collection of AI/ML Knowledge, Papers, Courses, and Tools.
Job board CLI for coding agents. Search and judge millions of worldwide postings from all white-collar sectors, refreshed hourly.
Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references โ English and Chinese.
A local-first inbox for long-running AI agents, built with DeepAgents and LangGraph.
Oracle3: open-source trading engine and MCP server for prediction markets. Finds fee-adjusted no-arbitrage violations across related event contracts and trades them live on Kalshi, Polymarket and Solana, or on paper, under pre-trade risk limits. 13 MCP tools, JSON CLI, agent skills, 600+ tests.
Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.
Lean Flask framework built for coding agents: Vue 3 + Vuetify with no build step, production-ready auth (2FA, passkeys, OAuth), AGENTS.md, an agent skill, and a read-only MCP server. No webpack, no node_modules, just Python.
Build a video template once, reuse it across coding agents: open-source, editable wedding video templates and an Agent Skill for 25+ agents, including Claude Code and Codex.
The agent control plane: run Claude Code, Codex and Gemini CLI agents in parallel with a shared task board, schedules and usage-limit recovery. Native iPhone, iPad and Mac apps plus a web dashboard. Self-host (Rust + SQLite, Tailscale remote access) or use amux Cloud. MIT + Commons Clause.
The self-improvement layer for AI agents. Ratel reads your agent's traces, finds what fails, recommends fixes, and runs evaluations on real sessions before you ship. Self-hosted: one app, one Postgres. Includes the TypeScript and Python SDKs.
Engineering workflow pack for AI coding agents: PRD interviews, task breakdown, and bespoke design.
Re-debugging Solved Failures? No Way. 1000+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.
The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI for deep Android security research, built for researchers and hackers. Powered by Python orchestration and a Rust-accelerated core, enabling AI agentโdriven hacking, credential recovery/cracking, APK analysis, intelligence gathering, runtime inspection.
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templates, Expert Agents with delegated sub-agents, proactive task management, media understanding - self-hosted with one setup script
An open-source graph engineering runtime that keeps orchestration in TypeScript and delegates semantic work to replaceable Agent runtimes.
Run AI agents in a sandbox that restricts what they can execute, read, write, and access on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon and Linux.
Agent tooling for building generative LEGO models, built with Astra and Opus 5.5, powered by Jev
omg.dev โ Remote control for Claude, Codex, Cursor, OpenCode, Pi, Grok, and JCode with a mobile client
The complete guide to Claude Code: CLAUDE.md, hooks, skills, MCP servers, and commands
One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.
DDC Converters 2.0: RVT/RFA to GLB, IFC4, and JSONL; IFC to Excel; DWG to Excel, DXF, and SVG. Offline CLI and desktop apps, n8n workflows, and AI agent instructions.
๐ฅ A visual web building platform based on large language models, an open-source alternative to Lovable.
Open workflow intelligence for discovering, validating, repairing, and generating automation workflows across frameworks โ starting with n8n.
Android automation from code. Test your apps on real phones, script the tasks you repeat, run a shelf of phones, or let an AI agent use oneโfrom Python, Node.js, the CLI, HTTP, or Appium clients. No ADB, no USB cable, no root.
55 rigorous skills for Claude Code, Codex, OpenCode 1 and 2, and Pi: code review, security audits, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.
103 paste-ready declarative agents for Microsoft 365 Copilot. No coding. No Azure. Deploy in minutes.
CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.
Official Code for OpenVLHarness: Real-World Visual Agentic Tool-Use with Multimodal Memory
๐ AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agents, ACL'24 Best Resource Paper.
A complete guide to help you integrate AI into your workflow, for both beginners and experienced users
Hardware mouse MCP server for AI agents on Windows x64. USB HID control and voice dictation; requires compatible uMouse hardware and firmware. Hardware mouse MCP for AI agents: USB HID control and voice dictation, requiring compatible uMouse hardware and firmware.
Profile-based coding runtime for Claude Code and Codex. Lean core; opt-in quality, context, memory, orchestration and dashboard.
BrainAPI is a knowledge graphโpowered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications.
Your AI engineering org, governed. Ship agent-built code safely to production.
Hand your SaaS growth chores to an agent: new-term radar, keyword-to-site discovery, competitor backlinks, directory submissions, plus a social analysis pack with a Douyin comments skill. Works with Grok Bot, Muse, Dot, Hermes, OpenClaw, Claude Code and Codex.
An AI agent that could talk to my girlfriend through my Mac went viral and got around 20 million views.