Custom agents

Craft your own AI agent: a real Agent Skill (SKILL.md) with a job, rules and a personality. Keep your team in one folder; your AI suggests who fits and asks first. Free, private, one file.

Product-Driven Development for coding agents

一套写给 agent 读的求职方法论。不是投递脚本，是每个决策点上的判断纪律。

AI 코딩 에이전트의 헛짓(과잉 검증·맥락 이탈·무한 루프·허위 완료)을 감지·경고·차단하는 하네스 / A harness that catches AI coding agents wasting time and money

The network layer for AI agents. Reach your customers' on-prem data, show what you build, keep it running — through one relay that your machines only ever dial out to. Plus tunnels and deploys.

Sandbox for Agents

Agent skill that turns any topic into one self-contained HTML study page: minimal, light focused, research-paper styled.

Native SSH client for macOS: Ghostty terminal, dual-pane SFTP, live server status, E2EE iCloud sync and an MCP server for agents.

Privacy-conscious native macOS and StickS3 companion for Codex and local coding agents

Actell (执言) is an experimental AI agent for iPhone that understands the screen and performs actions via CoreDevice, using on-device loopback or an ESP32 relay. An early-stage, vibe-coded prototype for exploration and idea sharing.

A Pi-native workspace for coding sessions on desktop. Run agent work. Keep control. Ship from anywhere.

①Trae/WorkBuddy/Zcode/Qoder/AutoClaw/Cline/商汤小浣熊/CatPaw等主流agent号池管家：统一签到、快捷切号、余额日历。② Skill技能库：本地扫描、智能去重、分类管理 Agent 技能，支持 WebDAV 远程同步，换机一键迁移。③ 用量记录同步：自动抓取 Trae/WorkBuddy/Qoder/Zcode/Codex/反重力等工具的 token 消耗与成本，加密存储、多端同步、结合计费规则自动算账，生成趋势图表与费用账单。④记忆中枢：可MCP链接进行记忆存储，配置模型可以进行蒸馏，多agent同步一套记忆，多设备同步记忆。

全球首个《杀戮尖塔2》iPhone 原生移植工具链 · 自备正版游戏(Steam)，让 AI Agent 读 AGENTS.md 一站式移植 · 与 MegaCrit 无关联

Physical Hermes - Give your Hermes Agent a body. This turns a cheap AliExpress AI robot toy into a voice device for Hermes Agent — running entirely on your own machine, using your own model, with no vendor cloud in the loop.

Memory layer for AI agents — SDKs, CLI and MCP server for Membase

Self-hosted IM ↔ local AI coding agent control plane with approvals, audit and isolation (Feishu/Lark + Claude Code)

TalaDB - An open-source embedded vector and document database for building local-first AI applications.

McDebate: agent debates, shared ordering and official checkout handoff over MCP

Otto: a personal operating system for the AI agents that work for you. Native macOS.

commerce-agent-bench

Requirement_Assistant_Agent

一款让agent可以像操作本地Windows文件一样操作wsl的mcp工具

A Roadmap to Becoming an AI Engineer, artificial intelligence (AI), sometimes called machine intelligence, is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans. Leading AI textbooks define the field as the study of "intelligent agents": any device that perceives its environment and takes actions that maximize its chance of successfully achieving its goals.

把口播博主的出镜动作拆成可复用的 Agent Skill，用于口播数字人生成

Finds the corrections you keep repeating to Claude Code and turns them into evidence-backed CLAUDE.md rules. Local CLI, no LLM by default, plus a public rule pack mined from claude-code issues

Evolved DSH plugin harnesses for five agent benchmarks, with versioned artifacts, evolution curves and Life-Harness comparisons

Rust-first reimplementation of a local agent CLI inspired by Claude Code.

A practical guide to building AI products end-to-end. You'll learn how to choose models based on product constraints, decide when fine-tuning is worth it, evaluate with real metrics, and build an agent that works in production. This project is in progress; chapters and code will land in stages.

Botfuel SDK to build highly conversational chatbots

Tools for Vercel AI SDK

Research works from Tencent AI Lab regarding self-evolving agents

Open Source Implementation of Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

A sequence2sequence chatbot implementation with TensorFlow.

A docker image for running AI agents in YOLO mode

Cartesia Line SDK for voice agents.

Collection of agent skills for AI assistants working with Dart and Flutter projects

Cortex: Advanced Memory System for AI Agents

Links to awesome OpenBB apps, widgets and AI agents

DAG-based Deterministic Context Compiler for AI Coding Agents

Get笔记 CLI — 让人类和 AI Agent 都能在终端操作 Get笔记

BCP-MAPF – branch-and-cut-and-price for multi-agent path finding

IntelliSense Designed for Coding Agent

an immersive browser dev environment with a seamless click-to-locate + agent edit loop.

A simple demonstration agent using the ReACT methodology for analyzing and executing tasks.

Parsing User-Agent on a mobile device, could detecting what os/browser/app.

A futures research and report review agent pipeline.

let coding agents use ncu skills analysis cuda program automatically!

Enhancing Translation with RAG-Powered Large Language Models

Code and prompts for AI-augmented obsidian usecases

Desktop agent framework for creating AI agents that can see and control your computer through voice and text commands

An AI agent framework built to get your agents into an application as fast as possible. Deploy on MagmaDeploy.com or self-host

Chef cookbook for Datadog Agent & Integrations

3D RL Volleyball environment built on Unity ML-Agents

A benchmark for evaluating learning agents based on just language feedback

An example extension in go using retrevial-augmented generation

Promptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and large language models (LLMs).

Portable multi-agent AI developer setup for Claude Code + Ollama. Role-based local LLM orchestration via Bash — plan, code, review, commit. Zero Dependency. Works with any language stack.

Headless AI agent for deterministic reverse engineering.

This repository is used to collect papers and code in the field of AI.

A curated, DevOps-focused list of Model Context Protocol (MCP) servers—covering source control, IaC, Kubernetes, CI/CD, cloud, observability, security, and collaboration—with a bias toward maintained, production-ready integrations.

Agentic RAG platform purpose-built for small language models (SLM). Robust PDF/SQL search

Modular Agentic AI Architecture - NousResearch x Teleport (Flashbots)

eBPF-powered silent observer for containerized runtimes, built for malware analysis sandboxes and Agentic AI monitoring.

A mini AI agent CLI, similar to Claude Code and Gemini CLI

simple multi-agent pathfinding (MAPF) visualizer for research usage

DART-GUI: Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation

COR paper: A Deep Multi-Agent Reinforcement Learning Approach to Solve Dynamic Job Shop Scheduling Problem

AgenTracer: A Lightweight Failure Attributor for Agentic Systems

A lightweight MCP server bridging AI agents to Google's Gemini AI via official CLI

FreeThinker is an AI agent that uses free-of-charge API open source LLMs in order to automatize tasks. That meaning that you don't required pay-per-token API keys to run it.

AI-driven vibe based Minecraft building via MCP. Describe a build, watch your agent construct it in Minecraft.

Enable AI agents to create and execute their own tools in Rust autonomously. Available as web API and MCP services

Code repo for "LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners"

A collection of different implementations of the same agent to show differences in frameworks.

为Godot引擎编辑器开发的Ai Agent插件

A very customizable version of a Conversation Agent for Home Assistant

Use Notion AI with your local files, shell, and fallback local agents.

Collaborative and secure AI agents platform that empowers software quality

甲木常用的 Agent Skills 集合，包含日常工作流中积累的高效技能扩展。 / A curated collection of Agent Skills for daily productivity workflows.

This is the official implementation for AgentSPEX: An Agent SPecification and EXecution Language

Use Poe to power your favorite coding agents (Claude Code, Codex, OpenCode, etc). No need for multiple subscriptions.

Github action to evaluate AI agent applications using model as the judge, content safety and mathematical metrics.

Agent Ops for your second brain - a 3D IDE for Obsidian built on Three.js. Visualize your vault as a code city, dispatch AI coding agents (Claude Code, Codex, Antigravity), post research quests, and watch your agent fleet work in real time.

ClawMax is OpenClaw to the Max! 🚀 A web orchestration layer for OpenClaw agents, teams, workflows, and templates.

给 AI 一篇文章，自动生成一款可以玩的 RPG Maker MZ 游戏

This repository is all you need to understand how to build Gen AI products or AI agents

Open-source SQL workbench powered by DuckDB. Query local files, BigQuery, and Snowflake right in your browser. Drop-in UI for duckdb -ui. AI SQL assistant included.

A comprehensive toolkit for deploying production-ready Generative AI infrastructure on Amazon EKS. Includes pre-configured components for: 🚀 AI Gateway (LiteLLM) 🤖 LLM Serving (vLLM, SGLang, Ollama) 📊 Vector Databases, 🔍 Embedding Models (TEI) 📈 Observability (Langfuse, Phoenix) etc. Fast-track your GenAI deployment with Kubernetes

Observability for AI agents. See what your agent did, why it cost that much, and what to fix.

Code intelligence CLI — function-level dependency graph across 34 languages, 34-tool MCP server for AI agents, complexity metrics, architecture boundary enforcement, CI quality gates, git diff impact with co-change analysis, hybrid semantic search. Fully local, zero API keys required.

The open-source alternative to Factory.ai's Agent Readiness.

A unified pi-coding-agent extension combining hash-anchored file editing with structural code maps

Find · Leverage · Optimize · Win — an evidence-led SEO playbook for the AI-search era. 72 docs · 42 AI prompts · 27 diagrams · 15 sourced 2026 stats. CC BY 4.0.

MatClaw: an open materials-science agent that turns natural-language tasks into reproducible simulation workflows.

Let AI agents control Windows applications. Click buttons, type text, toggle settings — all by name, not coordinates. Uses the Windows UI Automation API to find UI elements reliably, regardless of DPI, theme, resolution, or window position.

'Personal AGI' that thinks on its own. Autonomous cognitive cycle, earned autonomy, 60+ tools. It decides what to do without being told.

Practical guide to running LLMs locally on Apple Silicon, with a focus on architecture, memory scaling, and agent workflows.

Multi-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor, and any MCP client.