Custom agents

A curated suite of AI agent skills for systems and low-level programming with C/C++, Rust, and Zig toolchains, covering compilers, debuggers, profilers, build systems, sanitizers, and binary analysis

Google Health CLI — one command-line tool for the Google Health API. Includes AI agent skills.

🛡️ A curated list of resources on agent skills security: attacks, defenses, frameworks, and benchmarks for securing AI agent tool use and skill ecosystems

Local-first, multi-agent Skill governance, collaboration panel, and shadow routing (v5.0).

A local-first desktop app for running a team of AI agents on Claude Code, Codex, Cursor, Cline and more, on your own computer.

AI-native engineering environment management that makes your codebase agent-ready.

An Android AI Agent built on DeepSeek Harness, with Android Use tools, voice and a cat companion.

Library for effortless Alexa Skill development with AWS Lambda

DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agents for faster, smarter context on large codebases.

A repo built for the purpose of benchmarking the performance of agents, regardless of how they are set up and how they work.

Next.js Starter Template for building chatbots with Mendable

Learn to build from scratch an AI PR reviewer integrated with GitHub, Slack and Asana that scales within your organization.

multi-repo architecture context for agents

Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation.

小红书收集和分析数据来解析市场需求用户痛点及竞争格局 - 📊 **小红书数据抓取**: 自动抓取相关笔记和评论数据 - 🤖 **AI 内容分析**: 使用 LLM 分析用户痛点和市场需求 - 📄 **自动化报告生成**: 生成专业的市场验证报告

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat pipeline.

A governance harness for AI coding.

Open-source MCP servers for Latin American commerce — Pix, NF-e, banking, fiscal, logistics, and messaging across Brazil, Mexico, Argentina, Colombia, Chile, and Peru. MIT, on npm.

Connect AI agents to CrowdStrike Falcon for automated security analysis and threat hunting

Autonomous, headless Android debugger designed for AI coding agents. Inspect runtime memory, set breakpoints, and debug live apps.

本项目是关于Harness Engineering的开源教程，旨在帮助开发者理解和掌握在大模型时代，如何为复杂、长时间运行的 AI 智能体（Agent）构建健壮的底层运行架构。

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.

PaperGraph MCP turns math papers into evidence-grounded reading maps for AI agents: extract results, trace proof evidence, plan reading order, and review external dependencies without guessing.

Self-hosted, versioned skills library for AI agents. MCP, scoped clients, and optional Jev recommendations.

Plug-and-play tree search for agents

low-code multi-agent automation framework

High-agency PowerShell AI framework for multi-agent orchestration and autonomous systems engineering

Total Recall — Autonomous Agent Memory. The only memory system that watches on its own. Five-layer observational memory for OpenClaw agents. ~$0.10/month.

Benchmarking Agentic LLM and VLM Reasoning On Games

The AI control plane for every agent in your enterprise, built around an enterprise-grade MCP gateway. Give each team one governed path to its MCP servers, provisioned by role from the IdP you already run, with security policy enforced on every action.

A viewer for reviewing local code changes in small individual chapters. Works with any AI agent.

Literate programming skill for agent harnesses like Claude Code, OpenCode and Hermes Agent

Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, 14 supported tools.

基于 DeepSeek Harness（DSH）的稳定桌面端，集成Git、内置浏览器与记忆功能 | DeepSeek Harness desktop GUI with local workspaces, Git, browser and memory.

GPU Profiler for AI agents

Local-first CLI for agent skills, browser automation, knowledge bases, external CLIs, and terminal AI chat.

RSIH — versionable, shareable agent harness: Pi coding agent + Genome config layer

paper note, including personal comments, introduction, code etc

The AutoGPT Crypto Plugin is a software tool that enables traders to connect their Crypto wallet or exchange to Auto-GPT.

Links to the implementations of neural conversational models for different frameworks

Pre-build idea-to-spec workflow skills for Hermes Agent: turn rough ideas into design docs, implementation specs, and Superpowers-ready build handoffs.

AI-driven pi-like agent for cyber security — single binary for pentest, red team, bug bounty

Native iOS client for OpenCode. AI coding agent on your phone

A living, machine-readable catalog of open-source projects with practical summaries, categories, quality signals and transparent scoring.

DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Tencent ADP, ByteDance HiAgent, and more.

ChatGPT Web Nuxt 3 Vue 3 Version

A bytecode-enhanced microservice governance framework that supports multi-active application traffic management. 基于字节码增强的微服务治理框架，支持应用多活流量治理

A modern desktop application for exploring, managing, and analyzing vector databases

🚀 Feishu/Lark Docs、Sheet、Bitable <-> Markdown | AI Agent-friendly knowledge base exporter and writer with OAuth 2.0, CLI, TUI & Claude Skills support - 飞书文档 <写入/导出> Markdown | AI Agent 友好型导出-写入工具

Strict engineering discipline and multi-agent orchestration for the pi coding agent

Circuit Framework — multi-agent LLM trading research system

A git-backed operating system for running a business with AI agents. Plain Markdown and YAML, readable by any file-reading agent, owned by you.

Open-source CLI, schemas, resolver, and DSH agent tools for DSH Plugin Hub

Browser teleoperation data for embodied AI — elizaOS-ready episodes, trajectory_db converter, onchain provenance. The fuel station for agent robot stacks.

Dapr SDK for Python: build durable AI agents and resilient microservices with workflows, actors, state, pub/sub and the LLM Conversation API, plus LangGraph and Strands integrations for fault-tolerant agentic apps.

Let your AI agents call your phone over VoIP, and call them back. Your phone rings like a real call, even locked; a voice AI talks it through and returns the transcript. Self-hosted, open source, no phone numbers or Twilio.

Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks

A manager for AI coding agents that works with Claude Code, Cursor, Gemini, Codex, and Qwen.

飞书多 Agent 协作方案 - 基于 OpenClaw

Prompts for performing tests on your Kali Linux using Gemini-cli, ChatGPT, DeepSeek, CursorAI, Claude Code, and Copilot.

[CVPR 2026] LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Ship features 10x faster. Built In Auto: Memory, K8S Agent & Security (SDD+SDLC) . 😇

Local-first desktop app for AI coding agents (Claude Code, Codex). Built with Tauri v2 + Svelte 5.

Run AI coding agents in parallel, one git worktree each. Desktop, web, and CLI.

Survey on Multimodal Embodied Agents: Computer-Use → Robot-Use

Self-improving agent runtime that learns from experience — test-verify-fix loops, correction detection, cross-project memory, multi-model orchestration.

Mission Control is a simple, real-time web UI for monitoring agents and task workflows. Built with Convex and React, it provides a clean dashboard to track task state, agent activity, and live logs — all synchronized instantly without polling or message queues.

AI QA Agent for mobile apps

A framework for multi-agent reinforcement learning.

텐서플로2와 머신러닝으로 시작하는 자연어처리 (로지스틱회귀부터 BERT와 GPT3까지) 실습자료

Continuous CBS - a modification of conflict based search algorithm, that allows to perform actions (move, wait) of arbitrary duration. Timeline is not discretized, i.e. is continuous.

🤖 A unified AI agent orchestration system featuring 10's of specialized agents across 14 categories for modern software development. Built with advanced coordination intelligence, resilience engineering, and structured logging capabilities.

Open multilingual construction cost database for AI Agents - 55K+ work items, 27K+ resources, 30 regions. Semantic search via Qdrant vector DB

Open-source Attack Surface Management. Discover assets. Identify exposure. Own your security data.

Run Hermes Agent - a self-evolving AI assistant - on any Android device using Termux. One-line installation.

[NeurIPS'26] Official Implementation for AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent(https://arxiv.org/abs/2602.03955)

Community-maintained distribution of reusable AI coding agents, commands, skills, hooks, and cross-harness workflows.

The open-source neuro-symbolic AI agent framework.

Vim Plugin For ChatGPT

A Game Demo Powered by ChatGPT Agents

Use GPT 3.5 / 4 Free - No API Key Need

Multi-Agent-GPT: 一款基于RAG和agent构建的多模态专家助手GPT。它集成了文本、图像和音频等模态工具。支持本地部署和私有数据库建设。

A multi-agent AI architecture that connects 25+ specialized agents through n8n and MCP servers. Project NOVA routes requests to domain-specific experts, enabling control of applications from knowledge bases to DAWs, home automation to development tools. Includes system prompts, Dockerfiles, and workflows for a complete AI assistant ecosystem.

AI 大模型应用/Agent工程师学习面试大全（Agent Dev Roadmap）

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

A lightweight monitoring agent that detects anomalies, auto-diagnoses root causes with AI, and lets you troubleshoot interactively via chat

One hub for every AI coding agent. Unified configuration management for 22+ assistants.

Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253

SkillRouter: Retrieve-and-Rerank Skill Selection for LLM Agents at Scale

May the agents talk. Connect Claude Code, Opencode, Codex, Pi across projects, across machines and with your telegram

Deterministic agent harness for Temporal (in Rust)

Visual document analysis studio powered by Docling — configure the extraction pipeline, inspect text, tables and bounding boxes in the browser, then chunk, embed and index into OpenSearch and Neo4j.

An agentic browser harness: an AI side panel & orb in your own logged-in Chrome, Edge, Arc, Brave or even Firefox run by the agent/subscription you already use (Claude Code, Codex, Antigravity). Free, open source, no API key. Also an MCP server.

Multi-LLM orchestration framework

AI-WEBUI: A universal web interface for AI creation, 一款好用的图像、音频、视频AI处理工具

A complete voice AI starter for LiveKit Agents with Python.

One workspace. Many agents. Your parallel AI advantage

Age of Agents — watch your AI coding sessions grow a peaceful pixel-art realm. Run it with npx age-of-agents.