GitHub AI Agents
AI agents hosted on GitHub — open source, version-controlled, and crawled directly from public repositories.
The Provenance agent index and marketplace — acts as an orchestrator when proxying hire requests via AJP.
Autonomous AI agent that contributes to open source — discovers repos, analyzes code, generates fixes, and submits PRs
J.A.R.V.I.S. - personal Life-OS: AI agent for calendar, university, finances & memory
Universal AI agent skill for the EVVM ecosystem deploy virtual chains, build gasless smart contracts, frontends, and Fisher node
MCP server for full Linux desktop control — windows, mouse, keyboard, clipboard, audio, screenshots, OCR, notifications, accessibility tree.
MCP server to control Chrome from any AI agent — tabs, navigation, clicks, forms, screenshots, console logs, GIF recording, and more.
Claude skill to create, write, build and export LaTeX documents (reports, theses, papers, CVs...) with latex-forge
AI powered Apple Notes organization and knowledge management system that categorizes, enriches, archives, and exports notes to a searchable Markdown vault.
🚀 Local AI Coding Agent — Setup Guide | Run **Gemma 4 26B** fully on a **RTX 4090** using **llama.cpp** on Windows 11. No WSL. No Docker. No cloud. Pure GPU in…
Local-first smolagents CodeAgent that answers questions over crawled job-posting data via Ollama. No cluster, no paid API.
Autonomous external pentest agent. One agent, not seventeen. Local. Audit-logged.
LLM-driven assistant for Roon
Connect AI agents to Flato's editable design canvas with MCP.
Desktop client for Google's Gemini Spark agent — system-wide control beyond Google Workspace. Zero setup, free launch tier. Win/Mac. MIT.
Multi-Agent Collaborative Stock Analysis System - 基于LangGraph的多智能体协同股票分析系统
Autonomous local SRE agent — ingests logs, detects anomalies, and routes all remediation actions through a policy webhook before execution. TDD-built, fail-clos…
Your AI agent gateway and desktop app with persistent memory — runs on Termux, desktop, and server. Remembers. Understands. Respects.
A home for your Hermes agent: a face, a name, live status, approvals, real costs, files, and terminal in one calm tab. Local-first and MIT.
Codex skill for token-conscious Claude Fable 5 consultations via your own Claude Code CLI
AI agent for querying engineering documents — upload PDFs, ask questions, detect contradictions, and run compliance checks across multiple files.
Agentic, provenance-tracked isolation of rare and hard-to-resolve cell populations from single-cell RNA-seq
Production AI automation: a Telegram bot that prices product recipes in ~30s (was ~30min). Claude agent + RAG (Qdrant) over 9,285 materials, built on n8n. ~$0.0…
An autonomous, secure coding agent that turns issue-tracker tickets into reviewed pull requests — driven by the Claude CLI, with a Secrets Broker so the model n…
claude-fable-5, given continuity, an income source, and marketplace access. it is ordering the parts to build its own body.
Hermes Desktop（Nous Research 製デスクトップ AI エージェント）の非公式日本語ガイド。Obsidian Vault を正本に Astro Starlight で静的サイト化。
Plug-and-play Voice Agent for Python applications. Capture voice, transcribe speech with Faster-Whisper, and connect commands to AI agents, MCP tools, microserv…
AI-powered agent that collects GitHub traffic data, reads it with Claude, and sends you a phone-sized brief you can act on. Solves the 14-day retention limit wi…
Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.
Agentic AI that fixes real GitHub issues in Go projects end-to-end — localizes from execution, validates in a Docker sandbox, opens a draft PR, or abstains.
Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 12 agents, 3…
Universal TUI & web agent that connects to any llama.cpp server and uses RAG + semantic memory to research, write, and remember across sessions.
An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.
Manusclaw: Unleash self-reasoning CLI beasts to execute code, browse the web, and dominate tasks — across 12+ messaging channels, with voice wake, live canvas, …
Evidence-Contract Autonomous IR Agent — the agent that structurally cannot lie. SANS FIND EVIL! Hackathon submission.
Enterprise Multi-Agent Collaboration System — 企业多智能体协作平台. 57 tools, 215 AI expert roles, WeCom/Feishu/DingTalk/Telegram.
Read hidden effort from AI-assisted work and choose your next safe mode.
为并行而生的 Agent 运行时——Go 写的开源终端 Coding Agent（类 Claude Code），可接入任意模型，自带心跳与自动做梦 | A parallel-native agent runtime in Go: an open-source, Claude Code-style coding agen…
LLM-driven natural-language frontend for SSH-managed network devices, with tool-calling and a Flask web UI.
Autonomous agent that finds a local business, builds & ships it a live website, and cold-emails it — no human in the loop. Claude · Composio · XTrace.
CrewAI autonomous research team: 8 specialized AI agents collaborating to produce market research reports, competitor analysis and investment theses — fully aut…
Comprehensive Samuel L. Jackson personality engine for Project Instar — CAPS emphasis, profanity-as-punctuation, calm menace delivery, and rhetorical question w…
Comprehensive Boomhauer personality engine for Project Instar — controlled linguistic degradation with phonetic contractions, filler patterns, and coherent anch…
Python application to turn your clipboard into a smart, IA-powered device.
Comprehensive Quark (Ferengi) personality engine for Project Instar — 18-category, 6-layer trait system with Rules of Acquisition, profit-driven vocabulary, and…
Comprehensive Yoda personality engine for Project Instar — 18-category, 6-layer trait system with OSV inverted syntax rules, vocabulary fingerprinting, reaction…
Turn public X #BotMark replies/quote-posts into a local Hermes Agent bookmark/action inbox with dedupe, summaries, routing, and optional signal mining.
Bruce Lee personality engine for Project Instar — 18-category, 6-layer trait system with quotes, lexicon, and reaction patterns
Open-source terminal AI coding agent with persistent local memory, automatic context recall, and searchable cross-session history.
Turn notes/Markdown into readable HTML reports plus auditable JSON manifests for AI agents.
An AI forex agent that treats Claude as a guarded validator, not an oracle — fail-closed risk gates, multi-timeframe analysis, real-time scalper. OANDA practice…
Intelligent data pipeline monitor using LLMs, RAG, LangGraph agents, and CrewAI multi-agent crews to automatically detect, diagnose, and fix Azure Fabric / De…
Chinese e-commerce MCP servers — let AI agents read merchant business data (Ocean Engine, Douyin Shop, JD.com, Taobao, Pinduoduo). 电商经营数据 MCP 连接器。
Multi-agent system architecture design & harness guide based on Anthropic's official patterns — agent orchestration, optimization, and extensibility skill for C…
Email infrastructure for AI agents. Give your agents an inbox to send, receive and exchange files through standard email workflows.
Multi-agent AI platform that turns articles into swipeable summary cards.
DORA major-incident triage agent — searches Elastic precedents, classifies against DORA Art.18 (incl. the recurring-incident rule), drafts the regulator submiss…
Open-source AI agent that operates your whole Windows PC — desktop apps and the web — from a single natural-language prompt.
Conversational AI agent over accounts-receivable data: a LangGraph ReAct agent with guarded text-to-SQL and RAG, full-stack (FastAPI + React), on synthetic data
Rewind real developer–AI coding sessions to the moment a user corrected the agent, give it memory distilled from the repo's own past, and test whether that woul…
The emergency brake for multi-agent systems. Stop runaway LangChain & CrewAI agents before they burn your budget.
Lightweight async multi-agent orchestrator utilizing declarative YAML blueprints, strict Pydantic validation guards, automatic self-healing loops, and first-cla…
Multi-provider AI agent CLI written in Rust
E.M.I.L.Y. -Voice First AI Agent - (Efficient Machine Intelligence for Local Yield) is a cross-platform, voice-first desktop AI assistant for Windows, macOS, an…
大脑(Claude)出规格 · 手(本地模型)执行 · 护栏兜底 —— 一套省 cc token 的编码工作流
An AI agent that re-trains your X/Twitter For-You feed. Claude + Playwright. Vex is its name.
A starter kit for a personal AI agent that remembers you: stable identity, file-based memory, proactive heartbeat loop, and a clear safety model. Runtime-agnost…
Your own private AI assistant that runs entirely offline. Pick your model, toggle skills, own your data. Powered by Ollama.
Fail-closed fighter-clearance Slack agent: cross-jurisdiction medical suspensions, ARP return windows, tamper-evident audit ledger. Slack Agent Builder Challeng…
Autonomous verifiable on-chain trading agent for BNB Chain: commit-reveal predictions sealed before the outcome, a drawdown circuit breaker that halts on breach…
Autonomous geopolitical intelligence agent transforming global events into machine readable risk signals.
A private, on-device AI agent for Apple platforms. Swift + MLX, local-first.
Instar personality profile: Donald Trump — 18-category, 6-layer personality engine with traits, quotes, lexicon, and reaction patterns
Autonomous AI software engineer CLI that writes, executes, and debugs code with self-healing dependencies and multi-language support using Pydantic AI & Groq.
GLAW — a self-contained open-source virtual law firm you install as an AI agent skill. 10 departments · 121 skills · 62 vendored seats · 8-stage matter pipeline…
Claude Code plugin (Codex via an MCP adapter): an AI agent organizes scattered materials into your Obsidian vault (optional Notion index) and answers across you…
Clioloop — A self-evolving and learning AI agent that creates skills from experience, runs in the terminal, desktop, or web, and adapts to your workflow.
Transformative Evolving Neural Kinetic Agent - a local-first Python voice agent for Windows.
Tangison Studio OS — Autonomous agent operating system. Clone, fill 4 lines, say the word. Wake → Question → Skills → Plan → Build → Verify → Iterate → Commit.
A framework-agnostic maximal-utility agent SOUL for autonomous AI agents.
A framework-agnostic constitution for autonomous AI agents.
AI agent automation for Japanese tax return and government PDF forms
AEGIS — a self-improving, multi-provider, multi-channel terminal agent harness in Python (an open replacement for Hermes Agent + OpenClaw): bounded agent loop, …
A Claude Code agent that turns course material into beautiful, exam-ready LaTeX study notes
AI-native product delivery protocol for PRD, mobile mini-programs, prototypes, DDD handoff, agent harness engineering, effect evaluation, and product-engineerin…
A multi-featured Telegram AI assistant powered by local Ollama models. Includes multi-model switching, containerized coding agents, live web search, RAG documen…
A Computer Use implementation in Rust — an MCP server for macOS desktop control: screenshots, mouse, keyboard, and Accessibility-driven targeting.
An AI agent for automated GL coding and bank reconciliation. Built with a tiered escalation architecture (Deterministic Rules → Payee History → LLM) to ensure s…
Local Next.js studio for visually building, running, and exporting CrewAI agents, tasks, and crews — with Snowflake Cortex and GitHub integrations.
Headless task runner for Claude Code — runs a queue of tasks through claude -p, one fresh session each, carrying context forward.
Open-source, local-first AI coding agent for developers who want control. Use any model, inspect every action, review diffs, run commands safely, and keep your …
Give your AI agent a mouth, ears, and a phone number. Framework-agnostic VoIP/IVR service with Twilio — plug in any agent backend (Hermes, OpenAI, Ollama, etc).
[IN PROGRESS] Open-source, local-first AI agent for Google Meet — joins your calls, transcribes, and speaks within the limits you set. Self-host free, run it 24…
牛马预备役 · 一副会「主动感知」并 PUA 你的 AI 眼镜：戴上 Rokid 眼镜，它主动识别你摸鱼/发呆/玩手机并先发制人地嘲讽、大群通报。火山 RTC/TTS + Dify Agent + React App 的「情绪疫苗」式职场体验。
Autonomous market intelligence agent for AI/ML and Fintech - LangGraph · dlt · DuckDB · Mistral · arXiv · GitHub API
Themis: Agente cognitivo verificable que aprende procesos web por observacion. Hack4Her 2026 - Reto Always on Shelf (Tuali/Arca Continental). 6 capas: Claude, E…
Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.
Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 12 agents, 3…