Custom agents

AI Background Agent - v0 for your codebase (WIP)

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

The HugChat Streamlit app is an LLM-powered chatbot built using Streamlit and HugChat.

An agent based LLM assistant that extends RAG with batch entity extraction and SQL querying to improve performance on multi-step and analytical questions.

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

🦞 MobileClaw — 带眼睛的龙虾对讲机 | Multimodal voice+vision walkie-talkie for OpenClaw AI agents. iOS & Android.

Research-first design skill for AI agents. 150K+ real app screens and flows via Refero MCP.

Stitch 提出的设计系统文档格式 —— 用纯文本 Markdown 记录设计系统，让 AI 编码 Agent 能够生成风格一致的 UI。

Autonomous multi-agent system for end-to-end bioinformatics research

Code and data for the paper: Competing Large Language Models in Multi-Agent Gaming Environments

A skilll for agent to add a Civilization-style ceremonial quote when a substantial multi-step task is truly complete.

Build and deploy stateful agents across federated resources

A benchmark for evaluating learning agents based on just language feedback

[EMNLP 2024] DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models

A TypeScript SDK for implementing Model Context Protocol (MCP) over MQTT, supporting both browser and Node.js environments.

Eunomia is the open-source authorization layer for AI Agents

An example extension in go using retrevial-augmented generation

AIEvo is a multi-agent framework open sourced by Ant Group. Through this framework, you can create a multi-agent application.

Make your AI code agent write production-grade Go instead of tutorial-grade Go. A plugin for Cursor & Claude Code with version-aware guidelines (Go 1.0–1.26) covering modern syntax, performance tuning, error handling, concurrency patterns, testing, and graceful shutdown.

Starter template to build multi agent systems

jStyleParser is a CSS parser written in Java. It has its own application interface that is designed to allow an efficient CSS processing in Java and mapping the values to the Java data types. It parses CSS 2.1 style sheets into structures that can be efficiently assigned to DOM elements. It is intended be the primary CSS parser for the CSSBox library. While handling errors, it is user agent conforming according to the CSS specification.

AI-Powered Chat & Text Tools for Alfred

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

Guide on how to set up LMStudio and VSCode Continue.dev extension as a local and private coding Copilot. Targeted for 32GB RAM Apple Silicon devices.

Toolchain built around the Megatron-LM for Distributed Training

This repo contain all my AI agentic workflow in n8n

learn-claude-code js version 且只保留中文

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).

An Agent that makes outbound calls using SIP and Dispatch APIs

A comprehensive set of rules and guidelines for AI-assisted development in Cursor IDE

AGNTCY Identity allows to onboard, create and verify identities for Agents, Model Context Protocol (MCP) Servers and Multi-Agent Systems (MASs).

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

OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM

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

AgenTracer: A Lightweight Failure Attributor for Agentic Systems

AgentSkills multi-IDE management extension: browse and install skill repositories for Antigravity, CodeBuddy, Cursor, Qoder, Trae, Windsurf (and VS Code), and search a cloud catalog (~58K skills) from https://claude-plugins.dev/.

大语言模型评估平台，支持多种评估基准、自定义数据集和性能测试。支持基于自定义数据集的RAG评估。

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

A curated list of papers on LLMs and agents for scientific research and development

Agent Harness Platform — shareable workspaces, MCP tools, skills, memory, and cron/webhook automations. Self-hosted and transparent.

A type-safe, declarative AI agent framework for Swift. Build composable AI pipelines with Steps, Agents, structured outputs, and tool integration. Features FIFO session management, MCP support, and distributed actor communication.

WinDbg Copilot - Agentic Debugging extension

This repository is the official implementation of our paper (From reactive to cognitive: brain-inspired spatial intelligence for embodied agents)

面向 AI 协作场景的 AGENTS.md 压缩实验仓库：用统一规约格式提升指令命中率、降低幻觉风险，并量化 token 压缩收益。

Official implementation of the WASP web agent security benchmark

DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical Dialogue

The CoSAI Risk Map is a framework for identifying, analyzing, and mitigating security risks in Artificial Intelligence systems. As traditional software security practices are not always sufficient for AI, this project provides a shared understanding and a common language for addressing the unique security challenges of the AI development lifecycle.

The source code of Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents (ACL2026 Main).

🛡️ Portable credential management for AI agents — Age encryption, session leases, killswitch

Microsoft Foundry Local - Workshop - Build AI apps locally with Foundry Local - RAG, agents, and multi-agent workflows in Python, JS, and C#. No cloud required.

Sandbox wrapper for AI coding agents. Runs GitHub Copilot CLI, OpenCode, Google Gemini CLI, Pi, or a plain shell inside a kernel-level sandbox so the agent can work on your project but cannot access your secrets.

TeamClaw 是面向企业内部 AI Agent 落地的 operations control plane。它把运行时实例、Agent、Skills、模型资源、知识库、权限、审计和对话体验收口到一个多租户平台里，让团队可以在同一套界面里管理多个实例、多个部门、多个 Agent 和多个 runtime。

Open-source AEO (Answer Engine Optimization) infrastructure — every page, dual-marked. Markdown twins for AI agents alongside HTML for humans, picked by HTTP content negotiation.

The first comprehensive open-source AI-native framework for CRE acquisitions, turning diligence, underwriting, financing, legal, and closing into executable agent workflows.

A CLI-first, headless, AI-native IDA Pro bridge built on Unix philosophy.

AI Agent开发全链路手册：开发，测试，基座

Claude Code bug bounty agent. Install in current workspace: npx -y hacker-bob-cc@latest install "$PWD" then restart Claude and run /bob-hunt target.com

🇰🇷 Korean language skills for AI agents

一个面向 AI Agent 的通知配置工具。支持将 Claude Code、Codex、Grok Build 等 Agent 的事件通知推送到飞书、企业微信、钉钉和系统通知。

CAPTCHA proves you're human. HATCHA proves you're not.

Turn your team's AI coding sessions, GitHub code, and docs into one shared, searchable memory — a self-hosted git truth store you query right from your editor over MCP.

A Git-based package manager designed for AI-assisted development, similar to npm but supporting skills, agents, commands, hooks, and any AI resource types.

Companion code for 'Designing AI Agents' (Manning, 2027) — 27 agent design patterns, organized by the 7 cognitive modules. Chapters 1–5 available.

personal agent server mcp with multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams | mcp server of several socials

Agent skills to run computational-chemistry tasks, used in OpenClaw

A Unified Memory Benchmark Suite for Memory-Augmented Agents

本地优先的多模型长篇小说大纲与世界观推演工作室，围绕 LangGraph / langgraph-swarm 多 Agent 编排、正典库、关系图谱、世界规则推演、大纲推演和人工确认流程构建。

📂 Web File Browser | Server Manager | Server Ai Agent | 文件服务器 | 内网穿透

Evaluating agents on high fidelity reasoning tasks in the finance domain

Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseStore. No vector database, no embeddings.

Not a loop. Not a harness. Not a workflow. Not a framework. An AI Agents Organization. RoboCo: 25-agent software company with role-gated lifecycle. Self-hosted. AGPL.

The complete video-production skill behind the 蝦說 AI channel — lets an AI agent autonomously produce narrated educational videos (slides + TTS + ASR verification + subtitles).

📚【更新中】AISecOps: AI-Driven Enterprise Security｜AI 驱动的安全体系。一套将 AI 能力嵌入企业安全体系的方法论框架，以及支撑它落地的完整工程实践——从安全架构、GRC、云原生、数据隐私到 SOC 运营、身份治理与 AI 系统安全。开源中文技术专著，CC BY-NC-SA 4.0。/*⚡🌊🛡️*/

Camera-only closed-loop driving agent for Forza Horizon 6, with geometry as the control interface.

161 field-tested Claude Code patterns & anti-patterns for building an AI workflow that compounds — knowledge base, memory consolidation, hooks, agents. Updated monthly.

A Pi-native extension for thorough, agentic security audits

A coding-agent skill for generating designed HTML textbooks and print-ready PDFs

混合驱动的新一代 Agent 运行时安全插件，专为 OpenClaw 框架设计。

Enhancing Translation with RAG-Powered Large Language Models

ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization

vvaifu.fun clone: Vvaifu fun fork (AI crypto agent: AI agent + solana smart contract source code)

Join the OVOS collective, utils for OpenVoiceOS mesh networking

Evaluate your dialog model with 17 metrics! (see paper)

Step-by-step challenge lab repo to build your custom LLM Deep Researcher Assistant using Genkit

Kubernetes‑native control plane for running AI agents in containers

"Multi-robot Coordination with Agent-Server Architecture for Autonomous Navigation in Partially Unknown Environments", IROS 2020

Jenkins docker inbound agents with tools built in.

Agent swarming organization system

💧 Query mode for agents

RepoLaunch is an agentic SWE tool aimed at automating the build, execution and test of GitHub repositories across programming languages and operating systems.

Slightly less YOLO version of pi-coding-agent in Docker container sandbox

Reference code to create a control agent using Wi-Fi Test Suite’s Control API on a device with Linux OS

A toolset repository for AI agents

NIXStats monitoring agent

A low-level library for writing Go LLM agents

The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.