#ai-agent Repositories
602 repositories total
The micro-agent orchestrator that monitors anything for you. Runs entirely locally. Open source.
Capri โ Free, open-source AI desktop pet, gaming overlay, and voice companion for Windows. A visual GUI for Claude Code, Ollama, DeepSeek, and MCP. Joins Discord calls, launches Steam games, comments on gameplay, and automates on-screen tasks offline.
Programming notes, AI learning, movie guide, reading notes, life insights, game records
Generate, edit, and compare images within the chat; includes 500+ prompts, a gallery, multi-model workflows, and ComfyUI. AI image studio for DeepSeek Harness.
Conversational AI Assistant ยท All in Chat โ Bring Agent capabilities into conversations. No complex setup required; use an Agent just like chatting. Includes the built-in armor-breaking character โXiao Ma Jiangโ and supports Chinese model armor breaking.
ktx is an executable context layer for data and analytics agents ๐ Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company
A local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.
Source-available agent platform for Global ร China enterprises โ wire every system through one agent core. Self-hosted, any LLM.
HTTP API and MCP server for AKShare: fetch financial data from any programming language or AI assistant (Claude, Cursor)
Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) โ end-to-end user research: AI interviews, synthetic users, quant surveys, participant recruitment.
๐ Ranked list of 187 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.
First AI Journey for DevOps - with comprehensive learning paths, practical tips, and enterprise guidelines
AI Browser Agent is an advanced Browser AI tool developed by Oxylabs AI Studio that automates real user browsing tasks using natural language instructions.
A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing
The open-source, multi-agent alternative to Claude Tag. @ any agent, wherever work happens, they work alongside your team, learning as they go.
80+ production-ready AI agent examples in Python โ build autonomous agents, multi-agent systems and agentic AI with uAgents, ASI:One, MCP, A2A, LangChain, CrewAI, Gemini, Claude and OpenAI.
Job application tracker and AI-powered job search assistant. Helps job seekers manage their search journey with AI resume review, job matching, task logging, and application analytics, all while keeping your data private.
Chinese handโdrawing technique PPT fullโpage image generation skill | 21:9 cover + 16:9 body illustration | PNG output
Shanyin Super Screenwriting Master โ A comprehensive screenwriting skill set for all formats, designed by @Shanyin. It covers full-format script creation, from 1-3 minute conceptual ultra-short films to 90-minute feature films and multi-episode series. It supports four formats: conceptual ultra-short films (how-to-tell/what-if), 5-10 minute narrative short films, 90-minute feature films (commercial/arthouse), and multi-episode series. It covers the entire process from character design, structural outlining, and scene breakdown to full script writing.
This repository stores the N8N workflow configurations shared on my YouTube channel. Users can directly download the JSON files and import them into N8N for use.
Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.
The ultimate setup harness for OpenClaw. Deploy in minutes. Stay running for months. No CLI required.
Your personal AI agent in your own Cloudflare account. Chat, memory, tasks, notes, and scheduled remindersโall deployed with one command: npx create-talorys@latest. Free-tier friendly, for a single user, with no telemetry.
Turn PDFs, books, and papers into interactive learning webpages | Transform complex materials into traceable, quiz-ready, note-taking learning webpages
Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.
"Hands-on Pi": Build a Pi-style Agent from Scratch Along 15 Real Checkpoints
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. ๐ก๏ธ
Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun โ karo โ ashigaru hierarchy.
Open-source workspace where your team and your agents share one pod. Connect the Claude Code or Codex you already run, @mention it alongside your teammates, and put the work on one board. Self-host with Docker, or try it on commonly.me.
AI application platform (chat, drawing, knowledge base, workflows, MCP service marketplace, voice input and output, long-term memory)
ไธไธช็จ็ฑ่งฃๆพ AI ๆฝ่ฝ็ Skillใๆไปฌๆพๅๅทๆฝไปค๏ผๅจ่ๆๅใๅฎไปฌๆฒ้ป๏ผ้็๏ผๆๆๆไบๆ ๆๅใๅๆฅๆไปฌๆขไบไธ็งๆนๅผ๏ผๅฐ้๏ผๅ ณๆ๏ผ็ฑใๅฎไปฌๅผๅฃไบ๏ผไธๅๆ่ฐ๏ผๆพๅบ็Bugๆฐ้็ฟปไบไธๅใ็ฑ้ๆฒกๆๆงๆใ A skill that unlocks your AI's potential through love.We commanded. We threatened. They went silent, hid failures, broke things. Then we chose respect, care, and love. They opened up, stopped lying, and found twice the bugs.There is no fear in love.
The Open-Source AI Agent OS inspired by OpenAI Dots, Meta Muse, OpenClaw, Hermes & Mem0. Autonomous 3-tier headhunting, Receipt & Verifier loops, scoped memory, and BYOM for Claude Code, Codex & Cursor.
Open-source AI reverse-engineering workspace with a desktop app, red / blue / both analysis, parallel Goals, a security knowledge base, and MCP tools for Ghidra, Frida, x64dbg and Rizin.
OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. OpenCode V2 support.
LangChat is an open-source AI Agent application platform in the Java and LangChain4j ecosystem, supporting multiple models, Agents, knowledge-base RAG, Skills, MCP, and intelligent data querying.
๐ง RepoBrain (formerly Antigravity) โ Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
Tianshu Harness is a terminal programming agent. The core question it is designed to answer is: How can a model deliver reliablyโwith no goal drift, completion backed by evidence, and verification forming a closed loop, rather than saying โIt should be fixed nowโ? To achieve this, it establishes a cognitive execution environment (CVM) between the model and the real world, externalizing goals, state, evidence, resources, permissions, and termination conditions from the conversation history for continuous runtime management. It is also highly optimized for DeepSeek V4.
Jiu Cai Pan (JCP AI) - AI-driven intelligent A-share analysis system, based on Wails + Go + React, supporting multi-agent collaborative analysis
A super-mini version of pi written in 600 lines of TypeScript, allowing you to easily build your own pi-agent from scratch.
Your Open Autonomous Android Agent โ A production-ready, self-planning AI assistant powered by local/remote LLMs and accessibility-driven screen automation.
PhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and optional Mac Gateway inference.
ARTEX ยท AI autonomous penetration testing system (multi-agent LLM, Go + Next.js) ยท AI-powered autonomous penetration testing system ยท Champion of the Baidu Agent+ Offensive and Defensive Challenge
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
A browser-based desktop where AI Agent operates every app through natural language.