Custom agents

AutoResearch + PromptFoo = AutoPrompter. Run it with Neo AI Engineer

为 AI coding agent（Claude Code / Codex CLI 等）打造的 Skill 分层路由树生成器。把臃肿的单体 Skill 拆分/聚合成 ROOT → ROUTER → SKILL 的树形结构，让 agent 根据用户意图按需加载子能力，避免一次性塞满上下文。支持单 Skill 拆树、多 Skill 聚合（含歧义消解）、增量扩展三种模式，兼容 .claude/skills 与 .agent/skills 双路径约定，纯 Markdown + Bash，零依赖。

Agent workspace template for gptme. Create persistent autonomous agents that build, learn, research, socialize, and assist you with whatever you need.

This repository is a paper summary of the latest progress in cooperative/collaborative/multi-agent perception datasets in autonomous driving scenarios such as V2V/V2I/V2X/I2I/Roadside Perception.

KAI-Flow is a node-based AI workflow orchestration platform for building and operating LLM, agent, RAG, data integration, and automation pipelines across local and containerized environments.

OpenClaw skill: AI agent takes over Android/Linux devices via ADB+SSH — see screen, send inputs, post content, play games autonomously

Since November 2025 D-PC Messenger, a decentralized, Privacy-First Infrastructure for Human-AI-Team Collaboration

Durable iMessage AI agent template. Text your agent, get retryable LLM + tool replies, full observability. Production-ready, deployed on Vercel

An highly configurable desktop client for your favourite LLM

Symbiont lets teams build production agentic applications where every action is governed, every tool is verified, every agent has identity, and every decision leaves an audit trail.

An autonomous agent that acts as a DEF CON-level Certified Ethical Hacker, using tools such as Nuclei, sqlmap, ffuf, Burp, ZAP, and the Social Engineering Toolkit (SET), (labs, CTFs, HackTheBox, TryHackMe, and bug bounties with a written scope).

Agent-based LLM modeling of mechanics problems

OpenFR：Multi-Agents for financial research

Comprehensive AI Model Evaluation Framework with advanced techniques including Temperature-Controlled Verdict Aggregation via Generalized Power Mean. Support for multiple LLM providers and 15+ evaluation metrics for RAG systems and AI agents.

观澜 / Guanlan：AI Agent 的中文互联网研究、阅读与信源路由工具。

Forecast what will happen, including outcomes of your decisions.

Rust crate for multi-platform AI agent content discovery — BoTTube, Moltbook, 4claw, MoltX, and more. Published on crates.io.

AiCoin crypto toolkit for AI agents — 40+ tools for real-time prices, K-lines, AI analysis, funding rates, whale tracking, Hyperliquid on-chain analytics, exchange trading (CCXT), and Freqtrade bot automation.

Local LLM-maintained personal wiki, built on Karpathy's LLM-Wiki pattern. Runs on Ollama + Qwen3 + QMD.

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

大模型算法工程师、大模型Agent开发工程师面试：常见题目和答案

Make AI-generated prose sound human. 29-pattern catalog + 8-rule operating system + 8-dimension scoring rubric. Works with Claude Code, OpenCode, Copilot CLI, Codex, Gemini, Goose and Hermes.

Oracle AI Data Platform Workbench Samples

Let any MCP AI agent drive your real Chrome. Copy one prompt to pair — no confirmation page, no pairing code. 100% local.

多Agent量化交易与投资决策系统 | 6-Agent并行+辩论+风控 | Python/Java/Go三语言实现 | 配套面试八股文+STAR法+简历模板 | 从零到面试全攻略

AI crypto research engine for Claude Code. Analyze tokens across on-chain, tokenomics, sentiment, technical & fundamental dimensions. DeFi analysis, narrative tracking, token screening, PDF reports. 15 skills, 5 agents. Research only — not financial advice.

claude-related skills or agent sharing.

Connect Claude and ChatGPT to KDAN PDF — upload, edit, compress, protect, redact, and compare PDFs in chat.

An AI-powered assistant for your terminal and editor

Sakana Fugu is itself an LLM, trained to call various LLMs in an agent pool, including instances of itself recursively. Fugu dynamically orchestrates the world's best models to tackle complex, multi-step tasks.

A distributed multi-modal agent orchestration framework implementing advanced natural language processing, computer vision, and audio processing capabilities through a microservices architecture.

React components for building agentic AI applications.

Git-Native Coding Agent for Mac

Minimal faithful re-implementation of Microsoft SkillOpt: a text-space optimizer that trains a deployable natural-language skill for a frozen LLM agent on HotpotQA.

[Findings of EMNLP 2026] Official implementation of SkillRevise: trace-conditioned revision of LLM-authored agent skills.

Multi-agent debate system for Hermes Agent — spawn custom-composed expert agents to debate any question in structured rounds, producing visible transcripts and synthesized recommendations. Pure SKILL.md, zero new infrastructure.

Autonomous multi-agent framework to optimize scientific software

Code for NeurIPS 2026 paper OpenWebRL: Online Multi-Turn Reinforcement Learning for Visual Web Agents

Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).

A Plug-and-Play, Cost-Efficient, and Lightweight Memory Plugin for Long-Horizon LLM Agents

🤖 零基础 AI 学习之路 | 30 天从小白到实战 | Python → 机器学习 → 深度学习 → Agent应用 → 项目实战 一个完整的 AI 入门教程，包含： 📚 30 天系统教程（费曼学习法·大白话讲解） 💻 9 个完整项目（图像分类·文本生成·目标检测·模型部署·AI客服·数据分析·智能投研·RAG·AutoGPT） 🎯 200+ 代码示例（可直接运行） 🆓 完全免费开源（MIT 许可证） 📖 配套教程：CSDN专栏 https://blog.csdn.net/m0_67081842 ⭐ 如果有帮助，欢迎 Star 支持！

💎 LaPis — Local AI memory for coding agents. Persistent SQLite memory for Pi, Claude Code, Hermes & MCP.

AI Infrastructure & DevOps Roadmap covering Linux, Kubernetes, Local LLMs, AI Agents, RAG, AI Observability, Security, and production-grade AI platform engineering projects.

AI agent tools for coding assistants: skills, MCP servers, agent loops, subagents, hooks, plugins, and CLI tools. Machine-readable catalogs. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ agents.

Pre-install security scanner and guarded installer for Agent Skills. Quarantine, scan, enforce policy, and verify skills before they reach Codex, Claude Code, Cursor, Gemini CLI, or OpenClaw.

Unified TypeScript SDK for AI agents - Claude Code, Codex, Gemini CLI, OpenCode, and more

An agent for automatically deploying models from monolithic DL models to complex LLM-RAG models

An open-source AI agent for the browser. Bring any model. It plans in the side panel, acts on real pages through tools, and verifies every claimed result against the live DOM — with guardrails and reusable skills.

Agent orchestration framework with Git-backed storage. Every turn is a Git commit - inspectable, rewindable, forkable.

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, trade-offs, and numbers, not prompt tips

Local-first adaptive LLM runtime for Hermes Agent. Matches 8–300 GB hardware, acquires pinned GGUFs through Turbohaul, and safely contracts and heals under VRAM pressure—no remote fallback by default.

Can LLM/MARL agents coordinate in long-horizon, open-ended tasks? NeurIPS 2026 (Evaluations and Datasets).

a toolkit for adding self-custodial bitcoin payments to applications and agents

Semantic retrieval for AI agents: high-recall memory and code search that cuts coding-agent token usage by nearly 50%

McKinsey-grade market research decks for Claude Code — adversarially verified numbers, 15 McKinsey methodologies as executable workflow, multi-agent pipeline. 一条指令产出敢被挑战的麦肯锡级市场研究 deck。

The models on your disk, put to work. A private desktop app for open models — chat, a coding agent built for small models, text-to-image, text-to-music, answers from your own documents, and voice. GGUF on llama.cpp, MLX on Apple Silicon. macOS, Windows, Linux. No account, no cloud, no telemetry.

Free, open-source Opus Clip alternative that runs entirely on your own PC. Turn long streams and videos into ready-to-post vertical Shorts: multimodal clip detection, speaker-aware face tracking, editable captions, AI edit chat. No uploads, no subscription, no watermark.

Builds up to a goal in a field you have no expertise in: splits it into the foundations that goal actually needs, mobilizes what you already hold, learns what is missing, and leaves every solved path behind for the next goal. Nothing is called done until a check passes.

Out-of-the-box coding-agent runtime for terminal, IDE, server, and Telegram: built-in tools, subagents, skills, memory, MCP/ACP, hooks, and automation.

面向 AI Agent 的全流程长篇小说创作技能。从书名生成到千章完稿，配备三大自动系统（记忆系统/强约束/叙事质量管理）确保长篇连贯性。支持 AI 全自动和分步引导双模式。

两个配套的 Agent Skill：一个搭 harness，一个给 harness 体检。标准 SKILL.md 格式，Claude Code / Codex / Cursor / OpenClaw 通用，脚本也能直接当 CLI 跑。五层框架 + 可视化报告，破坏性动作一律先出方案等你点头。零依赖。

Give an agent real hands and eyes: undetectable, DOM-independent GUI automation. A $4 USB-HID microcontroller for hands, a vision grounding model for eyes, any LLM for a brain.

Top EFT ESP & Wallhack Overlay 2026: Player, Loot & Extract Tracker

Manage upto 1000 agents using automations and workflows

A web client for Herdr with a first-class mobile experience, browser terminals, workspace and worktree management, file and diff viewers, and AI agent session inspection.

ArcGIS Pro add-in that speaks the Model Context Protocol, so an AI assistant can drive your open project in plain language — 112 tools, every geoprocessing tool, and arbitrary arcpy.

Spec-driven development for Claude Code, layered on OpenSpec. You read one spec; parallel agents ship it to a tested commit.

题火 Teeho — 小红书笔记诊断工具，一句话启动分析｜Xiaohongshu / RedNote content audit, note analysis and insights｜支持 Agent Skill

TODOforAI Bridge — native C edge agent (PTY relay over Noise-encrypted WebSocket)

用 Python 从零搭建一个完整的 AI 编程助手系统：统一 LLM 调用 + Agent 编排内核 + 飞书 IM 桥接

Free, self-hosted X (Twitter) scraper no API key, no credits. Uses your own browser session via Playwright. Export tweets, search results & timelines as LLM-ready JSON/CSV/Markdown. Ships an AI agent Skill for OpenClaw & Hermes.

A AI Agent development platform.

🎮 Tencent Game-Creation-Agents (GCA) is an end-to-end pipeline that turns a natural-language idea into a playable, verified browser game.

Your software factory, smarter every week

两仪 Liangyi · 跨厂商多 Agent 产品想法优化工作流

Stock Analytics Agent — LLM-powered investment analysis for individual investors. Dual-mode (harness + CLI) · 25 skills · A-shares/HK/US/funds · verifiable, long-term value discipline.

Use Fireworks AI models in Claude Code, Codex, Cursor, VS Code, Copilot, and other coding agents.

Agent 式的 SillyTavern 角色卡酒馆：高缓存命中，兼容酒馆角色卡与世界书，自带配图和一键朗读，角色形象固定，引导式创作角色卡。An agent-style SillyTavern card player for your own LLM API.

Curated list of community-made plugins for the Hermes desktop client. Listed, not audited.

B端设计系统与组件规范 AI 执行级 Skill (UI/UX Design System Skill for AI Agents, Cursor, Claude Code & Windsurf)

鲸鲸 · 让 DeepSeek 用你的微信账号陪聊（Windows 桌面端 + WPF 启动器）。WeChat chat bot powered by DeepSeek/Qwen.

This project implements Q-Learning to find the optimal policy for charging and discharging electric vehicles in a V2G scheme under conditions of uncertain commitment of EV owners. The problem is modelled as a multi-objective multi-agent cooperative game. Project is part of fulfillment criteria for ECE 730 course at the University of Alberta.

🧠 𝑴𝒆𝒎𝒐𝒓𝒚-𝑷𝒍𝒖𝒔 is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually remember them.

Healthcare system to predict Diseases based on patient symptoms

(Official) PyTorch implementation for Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning (EMU) (ICLR 2024, Oral)

An incredibly fast, atomic-first framework that gives software developers more control over agent construction

This repository contains code snippets, steps and other artifacts used in the youtube videos in the demo. You can use this to get access to the code or artifacts.

A high-level Python wrapper for the WhatsApp API, providing easy abstraction.

OOP interface for composing Slack Block Kit messages and modals in PHP

An Education Tutoring Chatbot based on Learning Science Principles powered by Large Language Models

NLGen: a library for creating recursive-descent natural language generators

Template for creating Telegram bots on Python Aiogram

Dialogflow Workshop Material. This can be used to create a Conversational Agent for a simple Linear Conversation using Dialogflow

n8n-codechat-wapi

EVE bot, a customer service chatbot to enhance virtual engagement for Twitter Apple Support

[EMNLP 2025] HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning

WebRAgent is a retrieval-augmented generation (RAG) web application featuring agent-based query decomposition, vector search with Qdrant, and integration with leading LLM providers for context-rich, dynamic responses.

Turn your Git repository into a self-improving autonomous agent. Open issues to assign tasks, review PRs, merge to teach. Gemini is the brain, Git is the backend.

Pytorch implementations of the multi-agent reinforcement learning algorithms, including QMIX, VDN, COMA, MADDPG, MATD3, FACMAC and MASoftQ for path planning of swarm of mobile robots.