Custom agents

EN: ManimCat: AI-generated math animations from natural language. High-quality Manim rendering with LaTeX support and auto-code fixing. 中: ManimCat：AI 数学动画生成器。支持描述即视频，内置 LaTeX 与代码纠错，让数学动效触手可及。

[unmaintained]

🤖 Deep Reinforcement Learning Chatbot

Mean Field Multi-Agent Reinforcement Learning

《动手学SpringAI》包含SSE流/Agent智能体/知识图谱RAG/FunctionCall/历史消息/图片生成/图片理解/Embedding/VectorDatabase/RAG

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

Easy Code (formerly DeepV Code) — A highly customizable AI coding assistant compatible with all major AI models. The perfect alternative to Claude Code and Codex, offering deep code analysis, intelligent suggestions, version rollback, multi-device sync, and automated testing across multiple languages and platforms.

Stealth Chromium engine that stops scrapers and browser agents from getting blocked, with one line of code change.

A fast responsive, machine learning, conversational dialog engine for creating chat bots, written in Go.

Collection of templates using the Alchemyst AI Platform for your next big AI app.

Light-weight control pane to run CLI coding agents(Claude Code, Codex) in parallel

:round_pushpin: My dotfiles for macOS using Neovim, Zsh, and Ghostty + Tmux

Open-source, local-first alternative to Cowork-style computer assistants: real PTY terminal ops, explicit approvals, JSONL audit logs. Windows + Linux + macOS. Model agnostic.

Open-source AI agent for web automation and scraping.

🧬 Extend EvoScientist with Installable Skill & Knowledge Packs

GMGN OpenAPI skills for AI Agent — query tokens, wallets, and market data, and execute on-chain trades across Solana, BSC, and Base.

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

Your assistant's home — the memory, keys, code, and automations your AI agent keeps, portable across every MCP host. Built on Cloudflare Workers.

Command your browser with GPT

✔️Contextual word checker for better suggestions (not actively maintained)

A streaming multimodal database for Edge AI, and Edge Computing.

A curated archive of breakthroughs in Agents, Architecture, Training, RAG, and On-Device AI.

Live-SWE-agent: live, runtime self-evolving software engineering agent

Create state-machine-powered LLM agents using XState

Practical AI collaboration playbook for research, writing, reading, and coding: article, prompts, agent rules, and reusable skills.

Give Claude Code's ultracode mode to ANY model you already pay for. A tiny local proxy + one config.json. Point your AI at AGENTS.md and it sets itself up.

AI agent framework, written from scratch (not based on openclaw), focused on stripping it down to the bare necessities, optimizing token count, reducing security risks. modular so you can enable only exactly what you need.

AI Agent as a Pinix Clip — agentic loop with memory, tools, and vision

Project CodeGuard is an AI model-agnostic security framework and ruleset that embeds secure-by-default practices into AI coding workflows (generation and review). It ships core security rules, translators for popular coding agents, and validators to test rule compliance.

A free, safe and open agent for everything. Alternative to Claude Cowork & Codex. Open Bridge, the AI bridge between your intention and get the job done.

Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, Kimi

AI Assistant that reduces the size of your application's Docker Image

Lightweight LLM Interaction Framework

Personal OpenCode configuration - commands, tools, agents, knowledge

Server metrics fetching agent, based on SIGAR

modus: a framework for building agentic flows powered by WebAssembly

Global HTTP/HTTPS proxy agent configurable using environment variables.

Build robust LLM applications with true composability 🔗

Fully neural approach for text chunking

🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL

Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.

A Guide To AI-Assisted Software Engineering

AI Agent Team-拥有24/7专业AI开发团队：产品经理、前端开发、后端开发、测试工程师、DevOps工程师、技术负责人。一键安装，支持中英文命令，大幅提升开发效率！

Use devtools against a webpage; a CDP agent implemeted in client-side JS

An opinionated workflow layer for building, shipping, and operating apps with Hermes Agent

AI agent tooling for data engineering workflows.

The operating loop a coding agent follows — and skills to orchestrate multi-agent systems.

The open-source Render alternative — AI-native. Git push → build → deploy on your own infrastructure; agents are first-class users.

AgentKit is a toolkit that gives AI agents access to crypto wallets and onchain functionality. Powered by the 0xGasless AgentKit SDK.

Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Markdown preview server for AI coding agents.

SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration

RuoYi-AI user frontend for AI conversations, agent interactions, and knowledge-base Q&A.

Open source code for ICLR 2026 Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

从零开始的Agent学习之路

Agentic Resource Discovery (ARD) specification

Code for "SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes", ICML 2026 Spotlight

An Efficient Multi-Agent Path Finding Solver for Car-Like Robots

Build your first agent with Azure AI Agent Service Workshop

Resource collection of medical agent for clinical dialogue and health

⚡ A beautiful, fully customizable statusline for Claude Code - Starship-style TOML config, themeable colours, Nerd Font glyphs, and tunable cost/context/usage thresholds.

Browser Use Box: a 24/7 Claude Code agent for Playwright-style browser automation with Browser Use Cloud, Telegram, and a real browser on any box you own.

Claude Code 最实用的 Skills / Agents / Plugins 精选合集 | 50+ 精选 | 按场景分类 | 带推荐等级 | 复制即装

The open source technology for business process management

Persistent, searchable engineering memory for AI coding agents. Saves ~50% tokens and ~30% time while planning

smol-podcaster is your podcast production agent 🎙️

Enhance LLM agents with rich tool APIs

Design Your AI Agents

Lifecycle-Aware Memory for long-horizon LLM agents — 66.05% on PaperBench, 94.66% on SurveyBench, 10 peer-reviewed acceptances at FSE/ICML/TOSEM/AEI/ICoGB

Tactile: an accessibility-first operating layer for agents.

[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

VexJoy AI Agent with Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.

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.

Named Tmux Manager: spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Gemini) across tmux panes with a TUI command palette

A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM processing capabilities.

AI Agent Team scaffold for Claude Code — 19 roles collaborate through stage gates, enforced by mandatory skills + blocking hooks + DoD checklists. Spec-driven change folders, SIT-audited code reviews, 4-layer hook defense, multi-LLM (DeepSeek/Doubao/Qwen/MiniMax). Tracks: Web · WeChat Mini Program · Apple native (macOS/iOS). 中文/EN README.

An AI Based Chatbot [DEPRECATED]

Browser automation via CLI — for humans and agents

Giving LLMs like GPT-4 the ability to plan and execute terminal commands

[NeurIPS'25] GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

A Gemini CLI extension that allows you to use the Gemini CLI to orchestrate the Jules asynchronous agent to perform coding tasks like bug fixing, refactoring, and dependency updates.

Give your AI coding agent a design system. One command installs 400+ quality-graded company DESIGN.md references + skills into Claude Code, Codex, Cursor, and OpenCode. Free, MIT, zero AI calls.

Open Android AI agent runtime for phone control, app automation, VLM screen reading, skill routing, mini apps, and Mihomo VPN workflows.

Game-development Agent Skills for AI coding agents: install once and a master router loads the right skill for your engine and task. 66 original, version-pinned skills (plus a master router) in the portable SKILL.md format that runs across Claude Code, Cursor, Codex, Copilot, Gemini CLI and more, for Godot, Unity, Unreal, web and beyond.

A Claude Code skill that 10x's your effective context window by dispatching tasks to background AI workers.

🧻 Knowledge system for agents. Local-first, file-based, progressively disclosed.

An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability concerns.

WenShape文枢(原NOVIX写作):深度上下文感知的智能体小说创作系统/A Deep Context-Aware Agent-Based Novel Creation System

A CLI for managing Grafana Cloud resources. Optimized for agentic usage.

Workflow fluency for AI coding agents. 1 core skill · 25 commands · 7 domain references · memory layer · audit trail — works across Cursor, Claude Code, Gemini CLI, Copilot, and 6 more.

An on-device LLM understands your entire life, then proactively offers to get your work done through computer use.

An open-source application for building, observing, and collaborating with teams of AI agents.

pykoi: Active learning in one unified interface

DevOps Happiness: 1-click or 1-prompt MCP. Deploy apps + infra + CI/CD on your cloud. Happy humans + reliable agents. 🚀

Provider-agnostic operations for agentic resources. ARK codifies patterns and practices developed across dozens of agentic application projects.

Obsidian Skill for Claude Code and other agents