Custom agents

An open-source, ontology-based semantic context accelerator that enables AI agents to make more accurate, consistent, and explainable decisions.

DeepSeek 自带破甲 18+ 互动叙事：活人感 NPC（自主决策/拒绝迎合）、211个世界与上万素材、开局随心定制、世界自行运转、零漂移存档。

Agentic Web: Weaving the Next Web with AI Agents.

AI agent skills for UnifAPI MCP and public-data workflows

Deploy LangChain Agents and connect them to Telegram

A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page, designed for LLM RAG

AI Agent 面试知识库 100 题 | 涵盖 Agent 架构、RAG、工具使用、多 Agent、记忆、规划推理、提示工程、评估、安全对齐、生产部署、框架选型

Skills that teach Hermes Agent to write its own analytical prompts

You can now generate creatures directly within your project. Drop the open-source into your Agent, and start prompting what you want.

Control your Pi coding agent from your phone. Pair with a one-time QR code and chat with your local agent, even when you're away from your computer.

Awesome list of 女娲.skill — 用女娲蒸馏的人物思维框架合集 | Distilled human thinking frameworks for Agent Skills

Scaling in Games: Continued Pre-Training for Embodied Agents in Diverse Virtual Worlds. Weights on Hugging Face.

Shelley is a coding agent

Agentic Web: Weaving the Next Web with AI Agents.

Agentar-Scale-SQL is a novel framework that leverages scalable computation to significantly improve Text-to-SQL performance.

An agent skill focused entirely on Swift Testing, helping you write better tests, migrate from XCTest, improve test architecture, and adopt modern Swift testing patterns with confidence.

Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency

Flocks is an agentic SecOps platform.

Lean 4 theorem proving skill and workflow pack for AI coding agents

Always-on token-efficiency skill for coding agents (Claude Code, Codex, Cursor, Windsurf, Cline). ~31% lower bill on average, no loss of correctness.

AI-powered podcast & video generator.

[Deprecated & ingrated in docker-agent] Docker image for a Jenkins agent which can connect to Jenkins using TCP or Websocket protocols

Mega is an open-source implementation of Google Piper — a Git-compatible monorepo engine built for the AI Agent era.

Tool to find already running ssh-agent compatible agents

A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workflows. Now with Deep Research.

TalkCody - Code is cheap, show me your talk. 🚀 Free Open Source AI Coding Agent.

Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.

Hermes Agent 是目前开源社区最具潜力的 AI Agent 框架之一。它继承了 OpenClaw 的优秀基因，在架构设计、记忆系统、技能生态和自动化能力上实现全面升级。但 Hermes 的文档分散在多个仓库和平台，缺乏一本系统性的中文指南。 本书填补的正是这个空白。全书 16 册、30 万+ 字，覆盖从安装部署到高阶开发、从个人玩赚到企业服务、从单 Agent 操控到多 Agent 编排的完整知识图谱。

Android client for Hermes Agent - chat with your Hermes sessions from a phone or tablet over local Wi-Fi or a private Tailscale network.

Agent-led job application workflow with a local progress-tracking dashboard — works with any AI coding agent that can read files and follow instructions.AI Agent 驱动的求职投递工作流,配本地进度追踪看板——适配任何能读文件、听懂指令的编程 Agent。

Official AMD catalog of AI agent skills. Empower your AI agents with AMD's optimized SW stack.

Hermy HQ — a self-hostable mission-control dashboard template that pairs with your own local Hermes agent over a Postgres message bus. Send it to your Hermes and it onboards you step by step.

Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"

Making ANY Software Skill-Native -- Auto-generate production-ready AI Agent Skills for Claude Code, OpenClaw, Codex, and more.

Terminal-first, open-source AI agent manager for any CLI agent (agent agnostic), any OS (mac, windows, linux). The Open-Source Agentic Development Environment for running multiple coding agents in parallel. Run locally or self-host Remote Pane to manage agents from desktop or phone. Simplify multi-agent orchestration with the runpane CLI.

FOLOTOY AI Passport develop resources for Agent

Open-source AI design agent — alternative to Lovart AI, Runway Agent, Luma Labs Agent, Krea Agent, Pika Agent, Galileo AI, Magic Patterns. Autonomous multi-step creative for posters, social, brand kits, ad creatives, and video. Free, MIT-licensed, self-hosted.

Implementation of all RAG techniques in a simpler way（以简单的方式实现所有 RAG 技术）

Guardrails for secure and robust agent development

Claude Code for professionals who don't code — Skills, agents, and setup guides

Open tax skills for AI: 2,250 skills across 266 jurisdictions, every figure cited to the law. Works in ChatGPT, Claude, Cursor and any MCP client.

Local browser driver for trusted agents: control your existing Chromium browser through a small extension and local relay

WeSight Obsidian plugin for local agent runtimes.

Desktop workspace for Pi, OMP, and Prime Agent

Every file not opened. Every folder not explored. Tokens saved. A local repository map for coding agents: purposes, source, symbols, and dependencies. Native Rust CLI and MCP, isolated worktrees, and subagent hooks.

An open-source stack for generalist computer-use agents, combining code execution, GUI interaction, and cross-device control.

Standalone FFI library for calling C functions from lua. Compatible with the luajit FFI interface.

🚀🪐🌕🌑☄️🛸 Opensource equivalent of Google's Antigravity

xLLM 1.0, smart crawling, knowledge graph discovery.

OpenClaw 的官方企业微信插件，由企业微信团队开发和维护。它将你的 OpenClaw Agent 无缝对接到企业微信工作流，集成文档、智能表格、日历能力。

A curated list of agent-native services and infrastructure for AI agents: email, browsers, memory, sandboxes, payments, and MCP tools. Includes selection criteria and onboarding guides.

Local-first AI agent memory with a knowledge graph, ontology constraints, and traceable reasoning—all in one SQLite file.

Agent Skill for Chinese-first HyperFrames motion-video production from articles, products, websites, and README files.

End-to-end humanities writing assistant — an Agent Skill (open SKILL.md format). 11 modes from Socratic research-question sharpening through AI-use disclosure. Bilingual (EN/中文), discipline-aware (literature/history/philosophy/art/religion/linguistics + cross-disciplinary). Four-layer critique, calibratable devils advocate, voice preservation.

🖥️ Agent-project workbench for DeepSeek Harness — sidebar app drawer + dockable split workspace + a live control room watching every project.

BYD DiLink app (3.0/5.0/5.1, UI7): split screen 1/3+2/3, navigation on instrument cluster, Yandex Navigator on HUD, blind-spot cameras, Russian voice AI agent, real BMS consumption, trips/charges journal, automation, ABRP telemetry. EVs and DM-i/DM-o hybrids: Leopard 3 / Bao 3, Leopard 5, Sea Lion 07, Song, Song Pro DM-i, Atto 3.

Just a VLM Agent Can Play Robots

IDE, A native-feeling AI coding workspace that blends chat, planning, agent execution, and project navigation into a unified desktop experience.

Skill training with a corruption and reconstruction loop: train an agent's skill library, not its weights.

IDE, A native-feeling AI coding workspace that blends chat, planning, agent execution, and project navigation into a unified desktop experience.

My personal dotfiles: Zsh, Git, VSCode, Obsidian, Ghostty, cmux, etc.

Project/Worktree manager, deeply integrated with AI agents to increase productivity and multitask efficiently

A benchmark built to evaluate and improve agent capabilities for supporting legal work.

Free, open-source terminal SSH manager and SSH config editor in Rust for macOS and Linux that keeps ~/.ssh/config in sync with 16 cloud providers, monitors live SSH tunnels and manages Docker and Podman containers fleet-wide. Plus scp, Vault SSH certs and an MCP server for AI agents.

Swift Testing agent skill for Claude Code, Codex, and other AI tools.

The world’s #1 end-to-end job agent: semantic filters, ATS-optimized resumes, referrals from hiring managers — 100% hands-free.

[CVPR 2025] EgoLife: Towards Egocentric Life Assistant

A simple, fast and robust program-aware agentic inference system.

An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination.

An agent skills pack that turns an academic paper PDF into slides, a poster, a webpage, a Xiaohongshu post, or a WeChat article (paper2slides/poster/html/xhs/wechat)

Alpha Agentic Search — 分层记忆 RAG 检索问答系统

一个面向金融量化交易领域的 Agent Skills 技能维护仓库，主要聚焦A股量化交易。

【全链哨兵】全流程渗透测试 Agent 系统，支持 Web、小程序、安卓 APP、IOS app(测试中)。安全服务渗透测试辅助工具，禁止用于非法攻击。

William Strunk Jr.'s Elements of Style (1918) in markdown format for AI agents

AI agent skills for the Universal Registry - search, chat, and register 72,000+ agents across 14+ protocols. Works with Claude, Codex, Cursor, OpenClaw, and any AI assistant.

中文论文常用排版格式Skills，适用于课程论文、数模竞赛、毕业论文等场景，让llm agent写word论文或者将.md转.docx时可调用

Agent skills for the VisActor visualization ecosystem.

A wrapper around tensor2tensor to flexibly train, interact, and generate data for neural chatbots.

Kimi Agent SDK provides a programmatic interface to interact with the Kimi CLI

Powerline-style status bar extension for pi coding agent

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

The wallet your agents actually operate. x402 payments settled in USDG, tokenized-stock swaps, and DeFi yield — all on Robinhood Chain. Your agent gets wallet capabilities, never wallet ownership.

⬛ A native connected terminal for AI agent development. 为 AI Agent 开发而生的原生互联终端。

Diffs for function call stacks across git commits. 22 languages supported (AST-based, built using Tree-sitter). Great for agentic review.

BrainPilot: Automating Brain Discovery with Agentic Research

Usage Pulse: the live usage status bar for Claude Code. Session and weekly limits, your other AI subscriptions on their own rows, cost, context, agents, 10 themes, zero API calls.

A program synthesis agent that autonomously fixes its output by running tests!

Quantalogic ReAct Agent - Coding Agent Framework - Gives a ⭐️ if you like the project

MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.

An open, curated collection of Agent Skills for scientific research — clone it, use it, extend it!

Agentic Next.js Boilerplate

Clip any video into a narration recap with claude code skill｜用 claude code skill 把任何视频剪辑成中文解说视频，支持剪映导出

基于 DeepSeek Harness（DSH）的 SillyTavern 类文字游戏 Agent，支持候选项生成、对话式人物卡编辑、剧本模式与素材抽取。

Frametell: turn your ideas and material into vivid explainer videos with an AI director agent. Local-first, any model.

An easier way to use AI on your own computer. A free, open-source alternative to Claude and ChatGPT that runs open-weight models like Gemma and gpt-oss locally on Mac, Windows and Linux. Private, and works offline.

oar (Open Agent Runtime): programming interface for all agent harnesses

ZAPI by Adopt AI is an open-source Python library that helps you build tools for AI Agents by automatically capturing network traffic and API calls from web applications.

Aser is a lightweight, self-assembling AI Agent frame.

Building Agentic AI Systems, published by Packt