Custom agents

Skills for AI coding agents — Laravel, PHP, React, TypeScript, testing, security, and code quality.

Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Grok, GLM, Kimi, Cursor, Gemini, MinMax, OpenCode, Pi, or Command Code from any compatible tool.

Mnemosyne is a agentic memory and orchestration system designed to provide Claude Code with persistent semantic memory across sessions.

Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud, no Logseq API). Karpathy LLM-Wiki inspired.

Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-model training. arXiv 2605.08703.

Keep one source of truth for your AI coding-agent rules. Convert and sync between AGENTS.md, CLAUDE.md, .cursorrules, Copilot, Windsurf, Cline, Aider & Gemini — or scaffold a fresh AGENTS.md. Zero dependencies.

Orchestrate AI coding agents (Claude Code, Codex) as parallel subagents over tmux — a loop-engineering runtime with auto-continue, execute-then-review, and cross-session memory.

Listening all, Listening freedom!

The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. Industrial protocols (OPC-UA, Modbus) on the roadmap.

AI-powered multi-agent security auditor for Symfony applications, provider-agnostic via symfony/ai.

Planoda — the AI-native work platform that replaces Linear, ClickUp, Monday & Trello. Issues, boards, roadmaps & automations on one schema, with AI agents that propose and humans who approve. Try the live demo — no sign-up.

A portable AI-assisted Knowledge OS starter kit for Obsidian, Codex, Claude Code, and compatible AI coding agents.

Agent Skill that makes Claude a pixel artist — no Aseprite, no MCP, no diffusion. Every pixel is a decision.

Zorv AI — 安卓 Android 端开源 AI Agent 智能体助手。多模型对话、人格系统、记忆、语音全双工 TTS/STT、定时任务、可扩展工具链、飞书/QQ/微信接入。Kotlin + Jetpack Compose 开发。

Autonomous AI-agent orchestration engine for job discovery with decision traces, tool adapters, and production-grade run control.

GitX is a portable AI-agent skill for creating clean Git commits, tagged branches, and safe pushes across Codex, Claude Code, Cursor, and other skills-compatible agents.

Run GPT Responses inside the Claude Code harness with protocol-correct tools, agents, streaming, and compaction.

「EMNLP2026 Findings」AsyncTool is a benchmark for evaluating the asynchronous function-calling capability of LLM-based agents in multi-task tool-use scenarios.

Open-source GTM intelligence + automation for any sales call. Coaching, deal & account scoring, CRM auto-fill, and 30 post-call agents. Any recorder, any CRM.

An agentic workflow with a focus on reliability and developer experience

CrewOS 是一个关于企业 Agent 产品形态的公开实验。 我正在尝试回答一个问题： 当 AI 已经能够完成任务以后，它能否进一步接住长期、复杂、持续变化的真实业务？ 这里会持续记录产品原型、设计实验、思考过程以及失败的假设。 如果你也在研究类似问题，欢迎一起讨论。

A local-first desktop AI agent with a companion, real workspaces, tools, memory, Skills, MCP, and multi-provider routing.

Shared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.

Lemmary turns scans, PDFs, and office files into an organized library you can search, review, and research in plain language.

Hylo: Personal knowledge agent compatible with Obsidian.

Create and refine Blender product scenes in DSH: editable recipes, model imports, real previews, saved revisions and PNG/MP4 delivery.

Personal AIOps engineering project with durable workflows, scoped hybrid retrieval, reliable event delivery, and verified API/browser contracts.

An end-to-end evaluation framework for heterogeneous agents and plugins.

说一句，界面在画布上长出来 · https://wuch-ai.net

麦麦冷静期 mcd-chill — 基于麦当劳中国 MCP 的点餐前体检器，下单前 30 秒算清热量、复购与券浪费

把 Claude Code、Codex、Cursor 等 10 种 AI Agent 的本地会话汇到一处，统一搜索、阅读和管理（macOS，支持 Apple 芯片和 Intel 芯片）。

Локальный AI-копилот для интервью и встреч (Windows, BYOK): локальная ASR, оверлей, конфиденциальность

okx trading bot okx agent mcp cli cryptocurrency okx api automated trading typescript okx trading bot model context protocol cursor ai trading crypto spot futures okx trading bot npm pnpm okx mcp open source quant defi cex okx trading bot algorithmic trading crypto bot okx trading bot okx api mcp okx trading bot crypto mcp

A lightweight AI agent framework for vertical domain applications | 面向垂域应用的轻量级 AI Agent 框架

List of research papers of research papers investigating the user experience of AI-powered programming assistants (e.g., Copilot).

MCPcat is an analytics platform for MCP server owners 🐱.

Evaluation Framework for all your AI related Workflows

A complete voice AI starter app for LiveKit Agents with Node.js

AI Agent Nexus is an open-source platform for developing, testing, and hosting AI Agents, built with Streamlit and Gradio. It offers a user-friendly chat interface and focuses on teaching core concepts of building full-featured AI agents. The platform supports multipl AI Agent and assistant patters, and complements the book "AI Agents In Action."

Fully stealth chromium for AI agents.

AI agent to automatically check grammar and spelling on documentation files

The agent benchmark that scores the full stack — harness, config, and model — not just the LLM. Trace-based scoring, reliability metrics, configuration diagnostics.

Multi Agent Path Finding Algorithms

RVM — The Virtual Machine Built for the Agentic Age, in Rust.

Apollo ~ Deep Research Meta Agent

Deep active inference agents using Monte-Carlo methods

agent-based reactive programming library for typescript

Code and links for over 25,000 trained Atari agents

Search Self-Play: Pushing the Frontier of Agent Capability without Supervision

A curated list of frontend Agent Skills installable via npx skills add

LiveMCPBench is a benchmark for evaluating the ability of agents to navigate and utilize a large-scale MCP toolset. It provides a comprehensive set of tasks that challenge agents to effectively use various tools in daily scenarios.

Fetch papers as agent-ready markdown — DOI/URL/title in, structured full text out. CLI · MCP · Skill.

An example of a chatbot built with Microsoft Bot Framework and featuring e-commerce capabilities via Moltin, Azure Search, Recommendations API, and LUIS

A set of re-usable AI agent for document processing

Open Agent Computer Interface

An example chatbot application built on the Letta API, which makes each chatbot a stateful agent (agent with memory) under the hood.

Run & debug workflows for AI agents running Dockerized tools in VSCode

A lightweight, highly extensible ai code agent, built in Rust.

【软件创新大赛国三】🧩 An open-source multi-agent framework for intelligent health management, powered by the Linkage ecosystem.

phpipam scan agent

Tell the story on Auto. Your agent writes the code.

Local CLI tool for coding agents to search up-to-date developer documentation. Supports GitHub repos and public websites.

获取各种系统监控数据于一体的Agent 交流QQ群：204322929 获取最新版直接执行update即可

ai trading agent using interactive brokers api

A text-grid web renderer for AI agents — see the web without screenshots

Simulation of reward tokens in a DAO ⚡️Employs multi-agent simulations and discrete-time Markov random fields.

GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation

This project uses Deep Reinforcement Learning (DRL) to develop and evaluate stock trading strategies. By implementing agents like PPO, A2C, DDPG, SAC, and TD3 in a realistic trading environment with transaction costs, it aims to optimize trading decisions based on return, volatility, and Sharpe ratio.

Official code for the paper: InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (previously: Do Role-Playing Chatbots Capture the Character Personalities? Assessing Personality Traits for Role-Playing Chatbots)

Eunomia is the open-source authorization layer for AI Agents

GitHub tools and agents for the Vercel AI SDK, wrap GitHub's API as AI SDK tools ready to plug into any agent

希望用代码为 waifus 绘心。

Self-hostable RAG platform - document ingestion, embedding, and vector search behind a simple REST API

Agent Skills to empower developers building AI applications with Weaviate.

A toolset repository for AI agents

Our survey's paper list on Agentic AI, continuously updated with the latest research.

Universal AI Agent Orchestrator - Run any AI coding agent (Claude Code, Amp, OpenCode, Codex, Droid, Gemini) repeatedly until all tasks are complete

Agent Tool Protocol

📚 Benchmark your browser agent on ~2.5k READ and ACTION based tasks

Toolchain built around the Megatron-LM for Distributed Training

This repo contain all my AI agentic workflow in n8n

AirSim-based UAV Foundation Model Learning: Covering Agents, VLN, World Models, etc.

AI skills that turns coding agents into UiPath experts.

Deterministic and Agentic patterns for installing and maintaining successful production applications

Build agentic-MCP servers by composing existing MCP tools.

✨ Build dashboards with end-to-end version control. 🔋 CLI w/ batteries included, no infra required. Develop on your laptop for instant results, deploy changes safely (with automated checks), and keep every report trustworthy for stakeholders, analysts and agents 🤖

learn-claude-code js version 且只保留中文

A collection of skills for AI agents

An advanced LangGraph series exploring real-world agent workflows, dynamic tools, parallel execution, long-term memory, and human-in-the-loop designs. Includes hands-on Python notebooks for building scalable, production-ready AI agent architectures.

A plugin for your agentic framework that optimizes code using the GEPA algorithm (Genetic-Pareto LLM-driven search).

SonarQube Plugin for AI Agents

Open standard for coding event sounds. CESP v1.0 — any agentic IDE can implement.

AutoMind: Adaptive Knowledgeable Agent for Automated Data Science

High-performance vector search for Browser, Node, and Edge

🖥️ Run a Team of AI Agents. In Your Terminal.

An open-source benchmark for evaluating AI agents' ability to find backdoors hidden in compiled binaries.

AI-powered test automation tool which allows developers to run mobile automated tests

An SMS-based AI Agent that keeps you informed of stock price changes and the factors influencing them.