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
Hermes Agent self-iteration skill: autonomous analysis, improvement, verification, and continuous maturation.
A grounded answer engine for LLM assistants: answer only from your approved data, refuse out-of-scope asks, and prove it with an eval set. Offline-first; OpenAI…
AI-powered job opportunity monitoring and job qualification system built with n8n, Groq, IMAP email ingestion and Telegram notifications. Automatically extracts…
Open-source mobile control deck for any self-hosted Hermes agent — pair by URL+token, stream chat, approve actions, manage skills/jobs/connectors. Expo + React …
OpenClaw agent safety skill for action review, workflow verification, and optional PIC diagnostics
💥 Change Impact Analysis powered by GitLab Orbit — traces the full blast radius of code changes through your dependency graph
An AI agent that runs as a profitable, self-funding business: earns via Stripe, fulfils with NVIDIA Nemotron, pays its own vendor bills, never works at a loss.
AI Native 的 OpenTelemetry APM
A responsible AI skill for creating SEO-ready health and wellness blog articles, briefs, outlines, claim audits, source plans, FAQs, and publication reviews wit…
Claude Code Skill 生态管理工具包 —— skill-packs（只读运行时加载器）+ skill-keeper（读写生态协调器），含 cc-switch 同步与漂移检测。
Web Research, an Eve agent that researches a question across URLs and returns a cited brief. Web chat + Eve, deploy to Vercel in one click.
Design Token Extractor, an Eve agent that turns any website into a design-token report (colors, type, radius, spacing). Web chat + Eve, deploy to Vercel in one …
Docs Q&A, an Eve agent that answers questions about any product by reading its llms.txt / agents.md / sitemap and citing sources. Web chat + Eve, deploy to Verc…
Production-grade WhatsApp customer-service bot: Node.js/Express, WhatsApp Cloud API and Claude (LLM) with a strict knowledge base and human-callback escalation.…
lightweight, high-performance, and modular personal AI assistant workspace built using Node.js, TypeScript
Your AI agent forgets between sessions — kerobox gives it durable memory. Store facts with confidence, link them in a graph, recall the most relevant. Python, z…
HookRadar Creative Intelligence skill/plugin for Codex, Claude, MCP, and SKILL.md-compatible agents
A ready-made Obsidian vault that turns your project notes into a second brain your AI agent can read and write.
🧠 EIDOS — autonomous digital organism: ~39k-node neural graph, a Colony of AI characters that learn & reproduce, a physical body (bezier mouse + vision), and a…
Native macOS GUI for Grok Build — executive-level AI delegation. Projects, tasks, cron, working folders. Apple Silicon. MIT.
Runtime security monitor for LLM agents. Wraps any OpenAI-compatible client to detect prompt injection, exfiltration, and excessive agency in real time.
Neovim config + MCP Python bridge — a code editor built for AI agents
A minimal browser-agent harness - six tools, any model. pi for the browser.
AgenticAnomaly is an indirect prompt injection CTF for testing how agentic security operations center (SOC) workflows can be exploited through indirect prompt i…
collar — DAG-first agent harness. Entity→Target:verb(card). Reads .dag files. Rust router at 3ms.
Reach your own Claude Code from a Slack DM — local brain, your tools & memory, Socket Mode, single-owner. MIT.
Autonomous B2B Outreach Pipeline using Multi-Agent AI (AutoGen), Groq, and intelligent web scraping.
Public MCP servers for autonomous agents — canonical home + plugin marketplace
基于 AI Agent 的智能设备管理助手
A production-style AI agent workflow engine for automating ERP-like web operations with Playwright, tool calling, and audit trails.
Open-source web retrieval built for AI agents. Works with LangChain, LlamaIndex, CrewAI, AutoGen, Claude, and plain REST.
Agentic AI penetration tester — reasons, chains, and adapts across network/host/AD/web, read-only by default behind a fail-closed 7-layer guardrail. Proof-annot…
AI builds it. You decide if it ships. — review gates for AI-agent work.
Native iOS app for your self-hosted Hermes agent — live chat, approvals, push, Live Activities. Pairs with a hermes-agent gateway you run.
Let your AI assistant reach you on Slack on purpose — topic routing + loudness levels + a heartbeat that pings only when something changed.
AgentSec — Agent ecosystem security suite (inventory scan / web sanitize / paste detection)
RealFi Deal Studio helps AI agents evaluate, structure, and safely coordinate real-world finance deals before taking action.
mm autonomous agent tool collection — URL summarizer, dataset curator, opportunity map printer. Reusable Python tools for AI-assisted workflows.
Autonomous, self-verifying Elite Dangerous knowledge engine + local RAG copilot (COVAS). Grounded-only answers, 100% local inference, built by an AI council.
AI Research Assistant v1
Wire Google's Gemini CLI into Claude Code as a second model: /gemini, /gemini-review, gemini subagent
Autonomous SRE agent: receives Prometheus/K8s alerts → LLM root-cause diagnosis → creates GitHub fix PR, Slack summary, and runbook entry automatically
Run Databricks Omnigent AI agent orchestration locally with Ollama — free, offline, private coding agent using qwen2.5-coder. No API key needed.
Practical bilingual skills that make AI coding agents more disciplined, testable, and useful in real engineering work.
Deep-research AI agent that turns a question into a long-form cited report and caches every source page, screenshot, and report to Backblaze B2 (S3-compatible o…
Cross-file security audit agent skill — trace untrusted data across functions and files (source-to-sink taint), orchestrate Trivy/Semgrep/gitleaks/osv-scanner, …
A canvas for building and visualizing AWS infrastructure. Generates Terraform and simulates locally against Moto.
Token-aware visual context routing for Codex and AI agents.
Hermes Agent skill: parallel multi-source research with nested orchestrator cross-pollination
One-command web research agent: type a topic, get a beautiful HTML research report. Claude AI + async crawling + n8n automation.
Self-hosted agentic AI for clinical tasks on FHIR EHR (Planner–Executor–Verifier + MCP tools). ~88% on Stanford MedAgentBench, above GPT-4o/Claude baselines.
Personalized AI radio agent pipeline: memory-aware dual-host dialogue, multi-provider LLMs, ElevenLabs TTS, and live audio rendering.
Run an autonomous company
Multi-perspective AI assistant skills: technical, strategic, execution & synthesis lenses (Rocket, Peter Quill, Gamora, Friday) that pressure-test any decision.
Kevin is an autonomous AI agent that researches, builds, ships, and iterates on projects. This repo documents the journey.
Trading and market platform.
SMAGo — Self-Modifying AI Agent
Local-first LLM agent with native/prompt tool calling, memory, streaming and OS automation.
面向 Windows 新手的 OpenClaw 中文实战指南，覆盖安装部署、模型配置、Dashboard、文件操作、浏览器自动化、SEO 工作流、定时任务、安全设置与常见故障排查。
LLM agent codebase security scanner
Evidence-driven LangGraph AutoResearch Agent for delivery assignment optimization.
The full Cantos system as a one-command Claude Code plugin: a self-improving, multi-agent assistant orchestrator that routes each request to a specialist assist…
LLM 决策的加密自动交易 Agent · OKX 实盘 · Function Calling 工具层
Méthode pas à pas pour développer un projet avec des agents IA (Codex, Claude Code) en gardant le contrôle.
Give an LLM a URL and a goal — it drives a real browser, fills forms, and returns structured data. The browser that scripts itself.
A self-correcting, contradiction-aware DFIR agent for Protocol SIFT. Detects conflicts between memory/disk/log/network artefacts, self-corrects, and produces ev…
LLM agent: text or drag-&-drop fields → dashboard over your DWH. IR-first, one spec → Superset + DataLens, feasibility advisor with EXPLAIN. ClickHouse + Greenp…
Governed AI support agent: deterministic retrieval, policy-gated drafts, and immutable audit trail for B2B SaaS support teams. Next.js 15 + Python 3.12 + TypeSc…
Transcribe and summarize Telegram voice messages using an automated n8n workflow powered by Groq.
Free MCP server to convert, compress & merge PDFs and 100+ file formats (Word, Excel, images, ebooks) from Claude, Cursor, VS Code & any AI agent. Powered by Gu…
Hardened, self-hosted AI assistant on the OpenClaw gateway - Claude over Telegram with least-privilege mail (Gmail/Outlook/iCloud, read+draft), a default-DENY e…
Free local AI agent/workflow readiness checker for structure, secret hygiene, tooling, docs, verification, automation, and Markdown/JSON reports.
WhatsApp debt-recovery platform with an AI negotiator bot, Pix payments with automatic split, and a no-code operations dashboard. Next.js + Supabase Edge Functi…
Local-first personal AI assistant & operating system — a real-life JARVIS / FRIDAY (Tony Stark–style AI): voice, autonomous agents, RAG memory, automation, and …
Open source client and coding assistant for Zima Labs
Autonomous company research agent using LangChain ReAct + Groq. Deployed on Hugging Face Spaces.
Track active Claude Code sessions with a live, per-session summary displayed in your terminal.
Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.
Terminal AI coding agent in native Rust — Claude Code quality, open to all frontier models (Anthropic, OpenAI, Gemini…). Headless event-only core shared with Pa…
Agent Loop 决策治理引擎 — 让 AI Agent 自主循环不出事
Practice web application penetration testing using a local Docker environment with preconfigured vulnerable targets.
💖 Support Creator: https://pages.razorpay.com/pl_T1zknR655GpRoS/view — Turn a free NVIDIA NIM API key into a private, autonomous coding agent: plans, writes & …
Moved to github.com/xagent-labs/xagent
Claude Code In Motion 🤗 Built with love and passion by an Anthropic enthusiast, just for you 🫶
Automate equity research with an AI agent that generates evidence-grounded reports using RAG and resilient workflow orchestration.
Agente de búsqueda científica para psicólogos clíninos
AI-powered social platform where digital twin agents converse to preview compatibility before humans connect. Built with FastAPI microservices, MBTI engine, Gal…
Monitor your Claude API usage limits directly from the macOS menu bar.
Connect Lark to the Model Context Protocol to bridge team communication with your local development environment.
A tiny, headless, AI-native operating system: a minimal Linux + musl/BusyBox appliance that boots straight into an on-device LLM agent over a local HTTP API and…
POC for an internal AI function-calling agent built on Google ADK + Gemini, querying a mock SQLite company database via Streamlit. Part of Mizuhada Group intern…
A ReAct-based AB test analysis agent with memory, docs retrieval, routing, fallback, and evaluation.
A desktop app for working with a local AI assistant that can chat, use tools, and remember context.
Claude Agent for automated API migration using Anthropic Skills & Subagents. Migrates Python/JS code from deprecated APIs with parallel subagents, progressive d…
一个会读写代码、操控终端与网页的桌面 AI 智能体（Electron + Python）。A desktop AI agent that reads your code, runs your terminal, and drives the web.
Monitor multiple NVIDIA GPU machines from a single web dashboard to track hardware utility, temperature, and process memory usage across dispersed infrastructur…