Custom agents

Curated list of tools, frameworks, and resources for running, building, and deploying AI privately — on-prem, air-gapped, or self-hosted.

Dragonclaw: Maybe the best openclaw client. Built with Electron+SQLite, it doesn't touch OpenClaw's code but adds multi‑agent, high‑concurrency, DAG workflows. No prompt tuning needed (pre‑optimized). One‑click install with built‑in cloud service (replaceable).

The open-source suite of software for working with your agents

Model Context Protocol (MCP) server for reusable prompt templates, multi-step workflow chains, and quality gates. Compose agentic workflows with an operator syntax; export as native skills to Claude Code, Cursor, OpenCode, and Gemini CLI.

The first open source email gateway for AI agents — SPF/DKIM verified inbound, HMAC-signed delivery, webhook + WebSocket fan-out, CLI + SDKs + MCP

RAGGENIE: An open-source, low-code platform to build custom Retrieval-Augmented Generation (RAG) Copilets with your own data. Simplify AI development with ease!

A memory framework for Large Language Models and Agents.

A QA testing framework for your coding agent.

Local-first, hardware-bound key management and encrypted secrets for AI agents.

Build LLM agents that explain why, not just what. Attribution-driven agent requirements engineering framework. Based on the 4D-ARE Paper - https://arxiv.org/abs/2601.04556

Naptha is a framework and infrastructure for developing and running multi-agent systems at scale with heterogeneous models, architectures and data

Jarvis from the marvel universe

Multi-Agent Robotics Simulator

Graphite Agentic Framework by Binome Technologies

FTK Canvas Agent 是强大的多媒体处理自动化工具集，主打音视频处理与智能剪辑。集成多种先进 AI 技术，覆盖全流程，核心功能含 AI 剪辑、AI 特效、智能配音，自带横竖屏分类、场景切片等实用功能，支持零配置即用。其核心是连接 ComfyUI 实现 AI 服务，智能管理工作流，通过对话调用完成任务。

🚀 AIRouter - 智能AI路由器：为多个LLM提供商提供统一API接口，支持负载均衡、故障转移和智能路由 | Intelligent AI Router with unified API interface, load balancing, and smart routing for multiple LLM providers

A unified agent orchestration hub that lets you configure and manage multiple AI agents (native, ACP, AGUI, Claude Code) via YAML, and exposes them through standardized protocols (ACP/OpenCode Server).

The official implementation of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis".

Compendium of over 50 benchmarks for evaluating AI agents, categorized into Function Calling & Tool Use, General Assistant & Reasoning, Coding & Software Engineering, and Computer Interaction.

A general-purpose coding agent that runs inside an NVIDIA OpenShell sandbox, orchestrated by Deep Agents and powered by NVIDIA Nemotron. The agent writes and executes code in an isolated, policy-governed Linux environment.

Gym mode for agentic coding. OpenCode and Pi plugin that scaffolds exercises and reviews your work. Keep your edge.

Agent Skill for Baidu Netdisk (百度网盘) — upload, download, transfer, share, search files via natural language. Works with Claude Code, Cursor, Codex, Gemini CLI, OpenClaw.

A curated list of MCP servers for AI finance agents

【在线免费使用】 简单快速将SQL或DBML转换为美观的ER图（支持 Agent Skill）/ The best SQL to ER Diagram converter (Support Agent Skill).

AI-driven workbench for computational materials science — interactive 3D structure viewer, natural-language CatBot assistant, visual DAG workflow engine, HPC job submission. Tauri desktop app with SvelteKit frontend and FastAPI Python backend. Drives VASP, ORCA, CP2K, QE, GPAW, DFTB+, SIESTA, LAMMPS.

The Software Factory

Local-first AI learning workspace — ask, note, review and create around your own materials. Wiki KB, Agents, Skills, creation tools.AI 学习工作台，围绕你的资料完成问答、笔记、复习和创作输出。本地优先，多模型，Wiki 知识库，AI Agent，创作工具。

Poirot is a deep research agent kernel built for those who care about how agents are architected.

WAI Play - AI web game testing and quality evaluation platform

The Nexus SDK is a set of tools to help facilitate developers building with Nexus, the Agentic Workflow Engine, to build Talus agents or Talus tools

Magento Chatbot Integration with Telegram, Messenger, Whatsapp, WeChat, Skype and wit.ai.

Run and debug Alexa skills on the command-line. Create bots. Run them in Slack. Run them anywhere!

A naive webui for ChatGLM

Goal-Oriented Chatbot trained with Deep Reinforcement Learning

This is the code for "Unity AI" by Siraj Raval on Youtube

Complex Function Calling Benchmark.

A self-evolving multi-agent financial assistant powered by OpenClaw

Stateful runtime management for LLM agents—inject, manipulate, and retrieve Python objects across turns.

Magentic-Marketplace: Simulate Agentic Markets and See How They Evolve

MCP prompt template server: hot-reload, thinking frameworks, quality gates

BioAgents: An AI scientist framework for autonomous deep research in biological sciences. Multi-agent system combining literature analysis agents with data scientist agents to enable deep research automation through user feedback integration and iterative scientific discovery. Inspired by advances in Edison Kosmos, Sakana AI, K-Dense and others.

Multi-Agent AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程

Production-grade memory layer for AI agents with durable multi-tenant memory, semantic recall, async distillation, and SDK/Gateway integration.

Bitbucket CLI with gh-like ergonomics

中文互联网内容的个人 AI 稍后读 + 知识库 · Read-later + AI knowledge base for the Chinese internet

The middle manager for your agents

AI semantic search for Zotero, with a built-in MCP server for AI agents (Claude Code, Codex). Find papers by meaning. 100% local and private.

Personal LINE bot to automate various tasks. Home automation, expense tracking, transaction monitoring

WayFlow is a powerful, intuitive Python library for building sophisticated AI-powered assistants. It is a reference runtime for Agent Spec, with native support for all Agent Spec Agents and Flows.

A protocol that recasts the primary research object from narrative document to machine-executable knowledge package — so AI agents can navigate, reproduce, and extend published research without re-discovering every dead end.

BizClaw là nền tảng AI Agent kiến trúc trait-driven chạy trên điện thoại android . Hỗ trợ nhiều LLM provider, kênh giao tiếp, và công cụ thông qua kiến trúc thống nhất, hoán đổi được.

Context Encoding for Semantic Segmentation MegaDepth: Learning Single-View Depth Prediction from Internet Photos LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume On the Robustness of Semantic Segmentation Models to Adversarial Attacks SPLATNet: Sparse Lattice Networks for Point Cloud Processing Left-Right Comparative Recurrent Model for Stereo Matching Enhancing the Spatial Resolution of Stereo Images using a Parallax Prior Unsupervised CCA Discovering Point Lights with Intensity Distance Fields CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation Learning a Discriminative Feature Network for Semantic Segmentation Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation Unsupervised Deep Generative Adversarial Hashing Network Monocular Relative Depth Perception with Web Stereo Data Supervision Single Image Reflection Separation with Perceptual Losses Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains EPINET: A Fully-Convolutional Neural Network for Light Field Depth Estimation by Using Epipolar Geometry FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds Decorrelated Batch Normalization Unsupervised Learning of Depth and Egomotion from Monocular Video Using 3D Geometric Constraints PU-Net: Point Cloud Upsampling Network Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer Tell Me Where To Look: Guided Attention Inference Network Residual Dense Network for Image Super-Resolution Reflection Removal for Large-Scale 3D Point Clouds PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image Fully Convolutional Adaptation Networks for Semantic Segmentation CRRN: Multi-Scale Guided Concurrent Reflection Removal Network DenseASPP: Densely Connected Networks for Semantic Segmentation

What if AI agents could form teams as fluidly as humans? Spawn specialists in milliseconds, share discoveries in real-time, review each other's work, and remember everything across sessions. Watch it all unfold in a live mission control UI. Open source.

C++ Agent toolkit - Pre-built binaries, visit: https://github.com/mtconnect/cppagent/releases Docker images available at https://hub.docker.com/repositories/mtconnect

Official implementation of MASS: Multi-Agent Simulation Scaling for Portfolio Construction

一个基于思维导图的智能思考辅助系统

Build an agentic RAG app from scratch by collaborating with Claude Code. 8-module course covering hybrid search, reranking, text-to-SQL, subagents, and more. React + FastAPI + Supabase.

iOS development ClaudeCode plugin for mindful token and context usage. Contains modular MCPs that group various Xcode/IDB tools based on your current workflow.

[ICML'26] Scaling Long-Horizon LLM Agent via Context-Folding

Exposes internet search tools for use by LLM-backed Assist in Home Assistant

Watchtower is a simple AI-powered penetration testing automation CLI tool that leverages LLMs and LangGraph to orchestrate agentic workflows that you can use to test your websites locally. Generate useful pentest reports for your websites.

OpenShell is the safe, private runtime for autonomous AI agents.

Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.

Production-grade RAG API built in Rust. Hybrid search with HNSW dense vectors and BM25 sparse matching, cross-encoder reranking, layout-aware document extraction via Docling, and 94.5% accuracy on Open RAG Bench. Powered by Cerebras, Groq, Milvus, and Jina AI.

Invoke functions with a spoofed return address. For 32-bit Windows binaries. Supports __fastcall, __thiscall, __stdcall and __cdecl calling conventions. Written in C++17.

ChatData 🔍 📖 brings RAG to real applications with FREE✨ knowledge bases. Now enjoy your chat with 6 million wikipedia pages and 2 million arxiv papers.

🏄‍♂️ Next.js 16 web UI for OpenCode - real-time chat with streaming, SSE sync, and React Server Components

AI enabled insights from emails, calendars, contacts, files, Slack, databases, web... Fast, private and local. Launching soon!

🧠 The Copilot that lives in your shell. Type in your thoughts, press ^Z and let the AI do it's magic ✨

An opinionated, Agentic Engineering toolbox powered by LLM Agents to solve problems autonomously.

LLM based AI Agent to automate Data Analysis for dbt projects with remote MCP server

AI Agents are missing the UI! We're here to change it. Build Business AI Agents for your company: business workflows, API's, bookings, e-commerce, social commerce, b2b, CPQ, intake forms, NPS tests, made-to-order use cases

AnythingLLM Embed widget submodule for the main AnythingLLM application

A Runtime Framework for Agent Deployment and Tool Sandbox. AgentScope Runtime Java Implementation.

MobileUse: an open-source mobile GUI agent for Android phone automation, AndroidWorld/AndroidLab evaluation, hierarchical reflection, and proactive exploration.

The open-source company brain. Run your entire company with AI agents, skills, and a self-improving context.

Canvas LMS MCP server — 80+ tools and 5 agent skills for students & educators. Works with Claude, Cursor, Codex, and 40+ agents.

Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.

Pure instruction-pack skill wrapping Ai2's Asta MCP server (Semantic Scholar). Intent-to-tool routing, safe defaults, multi-agent.

The MCP server for interacting with Blockchain, Swaps, Strategic Planning and more.

Renders any URL via headless Chrome, tiles screenshots into OCR slices, and streams structured Markdown + provenance back to AI agents and pipelines

A multi-agent AI research system designed to know what it knows (and doesn't know) when conducting research and creating content.

The older sister of Claude Code - useful for learning harness engineering

GenAI & LLM usecases and applications

A solution guidance for Generative BI using Amazon Bedrock, Amazon OpenSearch with RAG

Input text from speech in any Linux window, the lean, fast and accurate way, using whisper.cpp OFFLINE. Speak with local LLMs via llama.cpp.

Generate vector embeddings in NodeJS

Your own AI-powered virtual world. 一个属于你的 AI 虚拟世界 。AI companionship.AI陪伴。AI Socializing.AI社交。

LLM agents for working with the SRA and associated bioinformatics databases.

One folder. Every session knows where you left off. — An open-source methodology for AI-assisted projects.

Connect your local Claude Code agent with Slack

Build a Claude Code–like CLI coding agent from scratch.

AI mentor agent for vibecoders on Claude Code — conversation analysis, mentoring, growth reports

Agent Skills 终极集合地，一站式装载，“让每一寸上下文都发挥到极致”🚀 The Ultimate Collection of 400+ High-Quality Agent Skills for Claude AI — Creative, Technical & Enterprise Workflows

Run AI coding agents (OpenCode, Claude Code, Gemini CLI) on Android

IAGA Sentinel sits next to your AI agents and answers the one question the agent itself cannot.

AgentPet 是一款基于 Electron + React + TypeScript 架构开发的开源本地桌面 AI 助理。它常驻于您的桌面，不仅提供基于 Pixi.js 的 Live2D 虚拟体陪伴与语音互动，更能集成微信飞书等代理进行 24H 消息回复、动态调用 MCP 服务、四层记忆沉淀机制；所有聊天数据均保存在本地 SQLite，保障您的数据隐私。

system prompt of claude fable 5

免费接入 GPT4 , DALL-E3 API , 还提供 Google&Bing 搜索 , BiliBili搜索 等众多插件

Prompt packs that make any AI agent a LaTeX expert — fix errors, polish writing, format for venues, read papers, recover source