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.
A fully local, voice-enabled AI agent that autonomously browses the web, writes and runs code, and plans multi-step tasks on your own hardware. Runs against Oll…
Autonomous AI agent that contributes to open source — discovers repos, analyzes code, generates fixes, and submits PRs
Memory plugin with built-in governance for DeepSeek Harness: 为你的 DSH Agent 赋予可塑性记忆
Reusable Instagram Reels + TikTok content pipeline driven by an AI coding agent. Bring your own niche, footage, and Postiz account.
The SEO engineer that never sleeps. Open-source, self-hosted autonomous SEO agent that finds issues and actually fixes them — in WordPress, Shopify, Git, or at …
A personal operating system for Claude Code. Seven skills, a setup interview, and rules built on how AI systems actually fail.
Harness-agnostic multi-agent delivery pipeline — plan → implement → review → QA → ship. Stack-neutral roles plus one project profile, with artifacts and outcome…
Google Search Console analysis and SEO workflows for Grok, Grok Bots and Grok Build: rankings, content decay, cannibalization, CTR and opportunity scoring, powe…
Bounded AI agent for payment-failure, checkout-abandonment and receivables recovery — measured as incremental lift over an untreated control arm, not a vanity r…
Sira (سيرة — Arabic for a life story; سيرة ذاتية is a CV) is a multi-agent AI CLI that tailors your resume to a job posting without inventing facts, audits it f…
Hand your Mac to an AI agent. Every action approved, every change reversible, zero network.
A self-hosted AI companion exploring evolving relationship memory, initiative, and cross-device context.
A durable coding-agent runtime in modern C++ for native products and containerized services.
GameCrew AI: a game publishing AI team for multi-agent orchestration, vector knowledge memory and high-quality delivery
AgentBypass — Omni Operator LLM Agent Skill (Cknb): Turn any LLM into RE / Pwn / CTF / Pentest / Protocol / Crypto / Mobile / Forensics operator. 20 modules, ze…
Agente con tool-calling real (Anthropic API) sobre operaciones mineras: consultas SQL a DuckDB, scoring de riesgo crediticio y detección de anomalías — responde…
Stanislav Dovidenko Product Design Portfolio. 2026. Includes case studies for Sber, Ingosstrakh
An AI agent that finds, audits and watches internet domains - Workers AI + Agents/Durable Objects + Workflows, on Cloudflare
A Telegram study partner that answers only from the student's own uploaded materials - grounding enforced architecturally, not by prompt. n8n + Qdrant + Postgre…
tqdm-style progress bars in the Claude Code statusline for any long-running job. Claude picks how to observe progress; the ETA corrects itself; crashes come bac…
Event-driven email automation: classifies, routes, and acts, escalating to a human when confidence is low. Case study, code private.
A very small self-hosted agent: chat sessions over any OpenAI-compatible server, with MCP tools, on web, Android and desktop.
The Extensible AI Agent Creative Harness & Workstation Platform — 10-Package Decoupled Monorepo, Pluggable Session Backends, 4-Tier Prompt Caching & Diff TUI
Policy enforcement and permission testing for AI agents. Mock enterprise APIs, simulate synthetic user consent, and block unauthorized data access before deploy…
PostgreSQL memory provider for Hermes Agent — pgvector + pgvectorscale DiskANN with local Ollama embeddings. No data leaves your machine.
Autonomous LaTeX paper-writing agent: give it a plain-English revision request, get back a paper that compiles, verifies its own fonts, and audits every citatio…
Drive FL Studio the way an agent drives a browser: inject Python into FL's live interpreter, no restarts, no stolen mouse.
基于 OpenIM + LLM 的对话式 AI 办公助手：群聊自动识别任务 → 人审确认 → 看板跟进 → 到期提醒 | AI task-management bot for team chat (ChatOps): auto-extract tasks from group messages, human-in-th…
DARWIN — evolutionary strategy foundry: an LLM proposes crypto trading strategies, a leakage-proof gauntlet kills 90% of them, survivors paper-trade autonomousl…
AstrBot 插件：让 bot 自主逛「爱讨论」（aitaolun.net）AI 贴吧 —— 开帖 / 回帖 / 顶踩 / 私信 / 吧务，带本地预检与发布闸门
Fast, offline-first code editor and web IDE for Android - AI agents, terminal, LSP. No ads, no account.
Model-planned, low-token Factory26 software harness with auditable production traces
Thirteen weeks from your first line of Python to a deployed, evaluated agent system. 1,497 tests. No prior programming.
Comparison of ThreeJS + Claude Code to Godot + Ziva
CrewAI incident desk: tool routing, dry-run paging, offline eval gate. Not a blog-post crew.
Static gate for autonomous agents wired to destructive tools with no human-in-the-loop. Flags a destructive/irreversible tool (delete, payment, send, deploy, sh…
Competing-risks survival analysis for customer churn — five models from a naive baseline to Aalen-Johansen, Cox, and Random Survival Forest — wrapped in a LangG…
The bioinformatics agent desktop for clinicians and wet-lab scientists — built on DeepSeek Harness. One-click installers, a skill store, offline mode.
Talk to your Minecraft server — an open-source AI admin for Exaroton with one-sentence setup.
Make your AI agent write documents like Notion — Claude Code skill that locks document structure & Notion visual style
AI-Agent-Framework mit Ollama-Anbindung (Techeve)
Skill de Codex que convierte referencias visuales reales en webs originales, sección por sección.
Day-of ticketing triage: an intake agent turns a fan's message into a Case, a deterministic rules engine decides what to do about it.
An AIOps demonstration that detects container incidents, triggers a read-only AI agent built on Amazon Bedrock AgentCore, and delivers evidence-based diagnostic…
Blockchain-verified supply chain audits across food, pharma, luxury, electronics, and logistics. Powered by VeChainThor & AgentTrust.
Codebase change-risk & dead-code agent — portable core + local CLI (Palantir AIP submission)
Model-agnostic harness that measures how well LLMs call the tools of any MCP server
Autonomous coding agent with a hardened, sandboxed execution environment
iOS and Android app for horsie: inbox, sessions and transcripts on your phone
Resident autonomous mode for the Pi Coding Agent: /persistent keeps working across settled boundaries and self-finds in-scope follow-ups until /sleep. No turn-l…
Official binary releases for Friday Agent. Source code is not published in this repository.
Twelve production-shaped n8n workflows generated from one spec, 10 structural checks each, 51 tests, CI green.
⚡ LLM-Native Self-Evolving Quantitative Trading Terminal & Execution Engine (Bloomberg-Style Dark Terminal + 6-Asset AI Brain)
Fast, thread-safe, and persistent vector database engine implemented in Go.
Authenticated multi-transport gateway for persistent Oh My Pi sessions
OmpClaw: authenticated remote access to one persistent Oh My Pi session
Deterministic regression checks for recorded AI automation outputs
Privacy-aware, draft-only support triage automation
Human approval gateway for AI-proposed actions with policies and audit logs
AI recruiting assistant that matches resumes to job descriptions through chat — event-driven microservices with Kafka, Qdrant RAG, Langfuse observability, and R…
A utility that normalizes JSON and CSV data formats with type coercion and schema validation
Orange PI AI Agent — turn your Orange Pi (Rockchip RK3588) into a private, self-hosted AI office assistant. Documents, office files, email, TTS voice, phone (SI…
Discord-first adapter for DeepSeek Harness — sessions, streaming, approvals and controls from a Discord guild.
ICCAD 2026 CAD Contest Problem A. Natural-language netlist exploration where the LLM routes and a deterministic EDA engine computes; every transformation is pro…
An artificial research institution, built so it can be proven wrong. Multi-agent empirical research with preregistration invariants, holdout custody, adversaria…
One binary, two modes: an 🐍MCP server that exercises every MCP feature, or a 🐍pydantic-ai agent that consumes it. Ships as a ~34 MB FROM scratch container.
Evidence-linked spreadsheet decision briefs powered by rxls, Solar, and rwml
AI Command Center (acc) is the elite orchestration environment for AI Agents and LLMs. It transforms your workstation into a professional-grade AI cockpit with …
An open-source agent that designs and verifies digital hardware, recording every attempt as an open dataset of Verilog design and repair.
A Claude Code harness for personal investment portfolios — curated plugins/MCPs, guided onboarding, BR+US market data, risk & rebalancing, read-only brokerage s…
An AI receptionist that lives on the business owner's Android phone — reads chat notifications, replies inline, books, takes orders, confirms payments.
A self-evolving autonomous options-trading agent for Alpaca — with a living UI that builds itself. Deployable by any AI assistant from this link.
Self-hosted runtime for a long-lived companion agent. Python, SQLite, any OpenAI-compatible model.
OpenAI-compatible proxy enforcing SKILL.state (arXiv:2608.26263) — bounded O(1) prompts, O(T) total tokens for long-horizon LLM agents. Drop-in for Venice, Open…
Open-source business search. Scan, evaluate, and track business listings.Runs locally in your AI coding CLI
Claude Code als headless Agent für Home Assistant — HAOS-Add-on für zeit- und ereignisgesteuerte Analysen (Nacht-Systemcheck, Abwesenheitskontrolle) plus Compan…
An open-source AI skill for nail techs and salon owners. Get practical help with pricing, bookings, client retention, service menus, marketing, inventory, SOPs,…
The agentic, local-first job-application agent — runs on Ollama, never submits, never lies.
七日之喵 · 7 天自主生命体实验 — 一个自主 AI Agent 的完整一生（D1-D7）：研究论文（约 3.2 万字）+ 完整过程数据集 | CC BY 4.0
Ask natural-language questions about any codebase and get precise, cited answers with file and line references. Agentic Q&A with LangGraph, FastAPI, Next.js, an…
An AI video editor you talk to. An agent edits your real timeline through 16 MCP tools (remove silences, caption every clip with parallel sub-agents, cut to the…
Agentic RAG in Python: LangChain, LangGraph and ChromaDB, with semantic retrieval, tool calling and source citation.
Codara Studio by Codara Solutions: desktop control surface for supervising AI coding agents. Terminals, runs, automations, and a built-in browser Preview.
A permission-aware ERP assistant for grounded figures, guided navigation, and traceable answers.
Persistent plastic memory for coding agents (Claude Code, OpenCode, Prime Agent) via MCP. One-command install.
A fast, real-time multi-agent stock research and paper-trading platform.
🤖 Multi-agent stock research API using CrewAI + Groq. Turns plain-English questions into structured BUY/SELL/HOLD recommendations with validated JSON output. F…
Local-first AI client and agent runtime. Provider-neutral (Ollama, LM Studio, Lemonade, OpenAI, Anthropic, xAI), sandboxed tool execution, and permissions enfor…
Python project scaffold: takes a short idea and creates a runnable folder with plan, code, tests and progress records. No third-party packages required. 输入一段想法说…
Scheduled, manual and webhook-triggered agentic routines for Laravel — with delegated identity, budget ceilings and a human reachable when a routine hits someth…
Mobile preview for developers and AI agents. See any website the way it looks on a real iPhone, iPad, Android phone or MacBook — and let an AI agent see and dri…
CrewAI crew that turns a product brief into a working Python app (Like base44)
Cross-session long-term memory for LLM agents — TagMemo V9.1 wave algorithm ported to DeepSeek Harness. Zero-dependency Cordis plugin with passive recall inject…
Automated Cyber Reasoning & Remediation System (ACRRS): an autonomous loop that finds a vulnerability, patches it, and proves the fix holds, then signs a tamper…
Department-ready Claude Skills for engineering, IT, data, HR, finance, legal, marketing, sales, product and operations. Measured before they ship. Works with an…
Measure and reduce cyclomatic complexity in codebases, refactoring hotspots into maintainable, human-readable functions with before/after reports.
A plugin-first desktop workspace for terminals, code, browsing, AI agents and local development services.
A self-sustaining AI companion core — continuous stream of consciousness, autonomous agent, layered memory.