GitHub agents

An open toolkit for creating reusable skills that extend how your AI agent works.

The context intelligence layer for AI coding agents. Compressing noise, routing content to the right strategy, preserving session state across compactions, and surfacing the files that actually matter.

Promptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and large language models (LLMs).

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.

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

pytorch를 사용하여 텍스트 전처리부터 RAG, 에이전트, LLM 파인튜닝을 정리한 Deep Learning NLP 저장소입니다.

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

A memory system using mem0 for AI applications. Enables long-term memory for AI agents as a drop-in MCP server.

[EMNLP '25] A web app and Python API for multi-modal RAG framework to ground LLMs on high-fidelity materials informatics. An agentic materials scientist powered by @materialsproject, @langchain-ai, and @openai https://aclanthology.org/2025.emnlp-main.1280/

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

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 🤖

Inpact is an open-source AI-powered platform designed to connect content creators, brands, and agencies through data-driven insights. By leveraging Generative AI (GenAI), audience analytics, and engagement metrics, Inpact ensures highly relevant sponsorship opportunities for creators while maximizing ROI for brands investing in influencer marketing

The most comprehensive open-source product development system. 31 AI agents. 23 frameworks. Solo founder Day 0 → IPO.

PasLLM - LLM inference engine in Object Pascal (synced from my private work repository)

AI Prompt Library: Curated prompts with metadata automation, documentation, and dynamic CLI. Execute AI prompts in CI pipelines or local workflows. Customizable toolkit for building AI-powered processes and personal assistants.

AutoMind: Adaptive Knowledgeable Agent for Automated Data Science

Flow Nexus is the first competitive agentic platform built entirely on MCP. Deploy autonomous AI swarms, train neural networks, and compete in coding challenges while earning rUv credits. Transform agentic engineering mastery into lived experience through gamified cloud development where agents spawn agents and systems improve themselves

CLI tool for LLM agents to build and maintain personal knowledge bases

CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework

AI code attribution for git. Track which lines were written by AI vs humans.

Cyber-Zero: Training Cybersecurity Agents Without Runtime

The issue tracker your AI agents are missing. Think Linear or Jira, but for your Claude Code..

The GPT-RAG Orchestrator service is an agentic orchestration layer built on Microsoft Foundry Agent Service and the Microsoft Agent framework. It enables agent-based RAG workflows by coordinating multiple specialized agents to collaboratively generate accurate, context-aware responses for complex user queries.

Fully automatic AI research agent for Geoscientists, Remote Sensing researchers, and GIScientists. Features harness engineering, GeoBenchmark (OLS/GWR/MGWR), journal templates, and MCP servers.

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。

Curated collection of OpenClaw agent personalities — SOUL.md, AGENTS.md, IDENTITY.md configs

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

The exhaustive guide to mastering Claude for Product Managers. Build your AI-native PM OS from scratch — PRDs, research synthesis, stakeholder decks, and autonomous agents. 11 modules, 40+ hours, real deliverables.

Headless Ghidra MCP server — giving AI agents deep reverse-engineering capabilities.

MCP-powered Home Assistant conversation agent that solves entity context limitations through dynamic discovery instead of full entity dumps

De Chat a Sistema Cognitivo — 40-slide presentation on building AI agent systems with SDD orchestration, Engram persistent memory, and modular skills architecture. Gentleman Kanagawa Blur theme.

Official implementation of paper "ACON: Optimizing Context Compression for Long-horizon LLM Agents"

Official Agent Skills for the OpenData platform

[CVPR 2026 Highlight] WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning

Interactive terminals for AI agents, built for what you can't --yes away. SSH+MFA, GRUB/U-Boot, debconf installers, SOL/serial consoles, fsck, cryptsetup, pdb/gdb, apt, certbot, pwsh and even Vim in tmux-backed sessions. Agent-driven, human-assisted for secrets/MFA. Single-file Python. Agent Skill. CI with 700+ tests. BSD License.

Plug and play AI agents for any domain

Experimental agent swarm extension for Pi. Inspired by Claude agent teams.

Hermes Agent plugin for cron analytics and observability. The dashboard for agentic automations in Hermes.

Self-hostable, open-source alternative to Claude Managed Agents. Multi-LLM support (Anthropic, OpenAI, Ollama), enterprise governance (org/teams/RBAC)

AI股神Skill，改造了“麻省理工学院”开源的多agent股神框架，我用AI扒出了他们的核心源码，总结出了5个金融分析团队、8个核心agent提示词。用扣子封装成了一个人人可用的skill技能包。我们只要输入股票代码，AI就能模拟人类金融团队的运作模式，自动分析大a数据、并将舆情情报、板块涨跌、技术面、资金流动等多维度的可视化报告，自动推送到你的电脑上。用AI帮你彻底读懂市场行情！

Reusable GitHub Action that reviews Terraform PRs for security, cost, and style using a LangGraph multi-agent system, posting a single severity-ranked comment.

Uncensored AI coding agent in your terminal. Does the work, skips the sermon. 256K context, crypto-only billing, no card on file.

AI Agent开发全链路手册：开发，测试，基座

Model-driven development for coding agents. Plan changes in a shared responsibility model mapped to your code; your agent reads, modifies, and implements it through a built-in MCP server.

Comprehensive collection of 133+ specialized AI subagents for Claude Code covering the entire software development lifecycle

Governance-as-Code for AI agents. Declarative constraints with deterministic enforcement. Provisioning Identity, Tool-based rules, Brokering Credentials & Ensuring safe deployment

17 triggers × 44 algorithms × 3 AI experts — live crypto trading signals for Claude Code, Codex, Cursor & 30+ agents. Free during beta.

Learning something new about runtime security for agents

🐙 A curated set of Codex and OpenClaw skills for workflow automation, technical debugging, and agent-assisted development patterns.

A rich terminal dashboard for monitoring and controlling multiple AI coding agent sessions

Ready-to-use agent skills that clone the thinking of founders, philosophers, and scientists into your agent. Generated with K-Dense-AI/mimeo.

[COLM 2026]TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents

MCP Server that wraps mitmproxy and exposes it as a tool to any MCP client, allows your AI agents to inspect traffic, filter traffic, intercept & modify traffic, request reply, set global headers, and start/stop mitmproxy as needed.

Simple, flexible workflow orchestration for multi-agent AI apps, with YAML configuration, runtime safety, observability, and resume support.

Fast, lightweight, local-first Windows launcher to search apps, files, content, OCR text, clipboard history, browser history, Git activity, settings, commands, and AI agents from one shortcut.

The open source taint analysis tool for the AI era. The analyzer you can customize and self-host, built so AI agents drive your security analysis without burning tokens on every scan. AI-ready open source alternative to Semgrep Pro and CodeQL.

Official Webflow Agent Skills

Agent-friendly GPU profile-query CLI

Build your go-to-market engine with coding agents instead of a $2K/mo tool stack. Interactive onboarding, 10 educational chapters, GTM-OS skeleton, templates, and Python scripts.

Independent Claude Skills for the whole smart home: Home Assistant, ESPHome, Node-RED, custom integrations, dashboards, and fab-ready hardware design.

Elixir-native framework for building runtime AI agents

Pi's Heartbeat - Schedule recurring and one-shot main agent or background prompts with cron-like functionality

A curated list of practical resources for Agentic Engineering

A curated list of awesome Skills, resources, and tools for customizing coding agent workflows.

All-in-one Docker/Podman image: hermes-agent + hermes-webui + hermes-dashboard in a single container

31 natural-language prompts that prove one primary agent can stand up, drive, and tear down a whole fleet of AI coding agents and terminals inside cmux.

WRAITH — Weakness Reasoning & AI Threat Hunter | Multi-agent RL-driven penetration testing framework | DEF CON 2026

Self-hosted terminal browser multiplexer for persistent shells and coding agents on Windows, macOS, and Linux.

High-performance embedded off-heap storage engine for Java, built on memory-mapped files. Map/List/Set/Queue beyond the JVM heap, plus an AI memory layer with hybrid vector + BM25 search.

Agent 友好的文献管理方式

Sandbox for Agents

Single-file, zero-dependency task board: owner-vs-agent plates, a dependency map, tap-to-complete.

Give your AI assistant a phone — OpenClaw plugin for real phone calls via Twilio + OpenAI Realtime, with in-call tools, transcripts, and call screening

A browser runtime that lets AI agents control your real Chrome browser via MCP. Agents can explore websites, generate operation manuals, and reuse them to save tokens. AI操控你的真实浏览器。

AI-powered mobile automation agent — describe what you want in plain English, AppClaw reads the screen, reasons, and acts. LLM-agnostic, open-source, zero telemetry.

⚡ Open source, agentic alternative to Intercom & Zendesk

All-in-One Desktop Agent Skills Utility. Welcome to the Skill Zoo, where all your skills live!

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

GitHub intake + capability routing for Obsidian/Codex/Claude Code｜GitHub项目自动入库 + Agent能力冷库与调用路由

Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Open architecture.

Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, and AI-enriched metadata from research papers and books. Generate PRDs, workflows, topic clusters, and Claude Code skills from PDFs. No OCR required.

FTShare MCP tools for financial data, market data and AI Agent investment workflows｜金融数据 MCP 工具文档与接入说明。

Agent that read, write and edit documents.

Local-first, transparent threat hunting for the logs you already have: Zeek, Pi-hole, syslog, CloudTrail. Named technique behind every finding. No SIEM, no agent, no black box.

In-process Revit AI agent with dynamic C# code execution, multi-provider LLM support, and a guardrail system for safe BIM automation.

Interact with ChatGPT from your macOS Menu Bar

Template for building your own custom ChatGPT style doc search powered by Fresh, Deno, OpenAI, and Supabase.

Rust-first reimplementation of a local agent CLI inspired by Claude Code.

Standardized agent data feeds and automation instruction sets for the OpenClaw framework. 專為 OpenClaw 框架設計的標準化代理資料流與自動化指令集。

Botfuel SDK to build highly conversational chatbots

Tools for Vercel AI SDK

若爱 (IfAI) — AI Agent 编排助手 & 代码编辑器 | An AI Agent Orchestrator & Code Editor built with Tauri 2.0

Deep Agents 实战 — Course Website

Gradio based tool to run opensource LLM models directly from Huggingface

PDF based Chatbot using streamlit LangChain & OpenAI.