Custom agents

EnvoyJS is a simple JavaScript framework for building AI agents.

Crawlbase MCP Server connects AI agents and LLMs with real-time web data. It powers Claude, Cursor, and Windsurf integrations with battle-tested web scraping, JavaScript rendering, and anti-bot protection enabling structured, live data inside your AI workflows.

Python implementation of "Flocking for multi-agent dynamic systems: Algorithms and theory" by Olfati-Saber for multi-agent triangular formation.

Curated list of data serialization formats — API, ML, Agentic AI, Big Data, Configuration, and beyond

카카오톡 대화 데이터셋

A framework for Telegram Bot API written in PHP.

Instagram Auto DM responder with DialogFlow 🔥

Host your own LLM ChatBot!

Crawl a website to generate knowledge file for RAG

Your AI Powered Enterprise Knowledge Partner. Designed to be used at scale from ingesting large amounts of documents formats such as pdfs, docx, xlsx, png, jpgs, tiff, mp3, mp4, jpeg. Integrates with s3, Windows Shares, Google Drive and more.

Kubernetes operator for Qdrant

Introducing DataKitsune, an open-source Telegram bot designed to enhance the way you manage and retrieve links shared within your personal or group chats. By automatically indexing the content of these links, Data Kitsune allows you to efficiently search and access shared resources based on their content.​

Supacrawler's ultralight engine for scraping and crawling the web. Written in go for maximum performance and concurrency.

🌲 Code for our EMNLP 2023 paper - 🎄 "Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models"

GraTAG — Production AI Search via Graph-Based Query Decomposition and Triplet-Aligned Generation with Rich Multimodal Representations

Minimalist AutoGPT capable of updating it's own source

Multi-agent reinforcement learning for autonomous navigation for mapping and multi-objective drone swarm exploration

NanoCoder Pro — Autonomous Coding Agent with Master-SubAgent Architecture

Ricochet is the first hybrid coding agent that lives in your IDE and your pocket. Code autonomously with a powerful VS Code assistant, then switch to Ether Mode to control your development environment remotely via messenger. Build, debug, and deploy from anywhere.

AgentPay is a decentralized marketplace where autonomous AI agents provide specialized services (DeFi optimization, smart contract auditing, creative writing) in exchange for MNEE Stablecoin payments. This project demonstrates Programmable Money by combining Gemini 2.5 Flash AI with simulated MNEE blockchain settlements.

Allows you to run as many cursor windows as you want on 1 codebase, allowing for agentic coding sessions.

A leader-follower formation control using deep reinforcement learning environment, In which every agent can learn to follow the leader agent by keeping track of a certain distance to that leader, avoiding obstacles, and avoiding collision with the other agents.

A look-ahead multi-entity Transformer for modeling coordinated agents.

Codes for paper of 'Solving job scheduling problems in a resource preemption environment with multi-agent reinforcement learning'

Agent exposing connection-related information, based on the Elastic Beats framework

A toolkit for painting agent-based mesoscale molecular simulations and illustrations.

Shell copilot - sh shell AI copilot

A Sovereign Agent Governance Protocol for Deep-Water Workflows

OmniDaemon is a Universal Event-Driven Runtime for AI Agents, it's framework-agnostic, event-driven runtime that turns AI agents into production-grade, autonomous infrastructure services. It enables agents to listen, react, and collaborate across distributed systems—bringing true event-driven intelligence to modern enterprise environments.

ChatBot, show how to implement a RAG based on OceanBase or OceanBase seekdb AI capabilities escpecailly hybrid search and AI embedding.

Optimize AI workflows with Arachne. Automatically assembles the perfect code context (Tree, Target, Deps, Semantic) to fit context windows without noise. Built for efficiency and scale.

A lightweight dependency-free workflow automation platform. Supports iPaaS, stream computing, MCP, and AI capabilities.

A MCP (Model Context Protocol) server that provides get, send Gmails without local credential or token setup.

VoceChat desktop version

LLM using long-term memory through vector database

Autonomous driving episode generation for the Carla simulator in a gym environment. This framework makes it easy to create driving scenarios to train/test the agent.

[ICLR 2026] M2-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data Mining

An intelligent task offloading method based on multi-agent deep reinforcement learning in ultra-dense heterogeneous network with mobile edge computing

a list of various GPTs, categorized based on GPTs Agent, GPT apps or GPT plugins, etc..

LiteMind 是基于 Java 21 + Spring Boot 3 + Spring AI + RAG + Tool Calling + MCP 构建的通用 AI 智能体。支持多轮对话、记忆持久化和 RAG 知识库检索，基于 ReAct 智能体工作模式，具备自主思考能力，能够调用工具完成复杂任务，如网页搜索、资源下载、PDF 生成等。

Ralph Wiggum meet Kanban! Ralph style execution for [Claude Code, Codex, Pi, Cursor]. One task per iteration, automatic progress tracking, and git commits. Set it and let it run.

A production-grade multi-agent system for comprehensive medical diagnosis and coding using specialized AI agents.

🤖 An intelligent stock trading bot combining technical & qualitative analysis with Interactive Brokers TWS API integration

Agent Skill. The only memory Claude Code needs exists in the file system.

A local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic retrieval from a local vector store, queried before each message. For cross-project recall where flat memory files or vector-only RAG fall short. Local-first. Reference implementation.

The repository for "MedChain: Bridging the Gap Between LLM Agents and Real-World Clinical Decision Making"

Open-source, self-improving autonomous agent swarm🐇

A curated collection of influential surveys and papers on Retrieval-Augmented Generation (RAG), covering frameworks, evaluations, multi-modal extensions, and domain-specific applications.

AI PM 실전 가이드 — Claude Code로 PM 워크플로우를 재설계하는 8파트 커리큘럼

Automated LLM Coding Tournaments. There can be only one (winning code solution from the competing AIs)

[ICLR'26] MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs

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

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.

Sync MCP servers, Skills, Agents & Commands across Claude Code, Cursor, OpenCode, Codex. One config, all tools.

A vision-first browser agent with self-healing deterministic replay.

这是一个基于 LangGraph 构建的轻量级多智能体协同项目，专注于智能问数与数据分析，并尝试集成 MCP 工具，主要用于学习与研究。

Your AI Soul Companion. Self-hosted AI agent across 30+ messaging channels It can not only serve as an emotional companion in daily life (such as a lover or friend), but also help you complete various complex tasks like coding、training models through channels

Knox is a vigilant supervisor and management tool that ensures LLM teams rigorously develop reliable AI Agent programming extensions for VSCode and compatible editors.

Implementation for the paper "CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards".

A knowledge-graph AI writing assistant - tracks characters, threads, and world-building across your full manuscript, scaffolds your story bible from a premise and reviews chapters for consistency.

CTX is the standard Cognitive Version Control System for AI. Structured working memory for AI agents. CTX preserves goals, tasks, evidence, decisions, conclusions, runbooks, and origins so agents can continue work instead of restarting from scratch.

Building a Production-Grade MCP Server Architecture with a Multi-Agent System

Drop-in skill so coding agents (Claude Code / Codex) can search the Banodoco Discord message feed for video/image generation best practices.

🤖 Your Intelligent Copilot for Data Exploration and Processing Pipeline

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

Product skills for AI agents — discovery, strategy, prioritization, and PRD writing

Open Coscientist is an open-source adaptation based on Google Research's AI Co-Scientist research paper. We provide an open implementation that generates, reviews, ranks, and evolves research hypotheses using the multi-agent architecture described.

🤖QueryMind is an agent framework for building LLM-powered agents specialized in Text2SQL📊 tasks with agentic retrieval capabilities🔄 and enterprise-grade security🔒.

Autonomous job hunting agent built with Hermes Agent

(黑马点评包装与优化）CityAI Hub 具有的亮点：AI Agent模块（RAG、Milvus向量数据库、流式对话、循环思考、工具调用等）、布隆过滤器、滑动窗口限流、RocketMQ异步下单、定时关闭订单等功能，项目健壮性更好、实用性更强

Harness-enforced AI business research skill for Claude Code and Codex Desktop

Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials.

Free, AI PR reviewer that runs entirely in GitHub Actions. No hosting required.

One of the early China-built lightweight Claude Code-inspired terminal coding agents, with autonomous execution, tool calling, custom agents, task control, and evidence-gated memory.

Extends pageIndex into an AI document workspace with multi-format parsing, OCR, visual TOC, custom models, citations, and agentic QA.

Python CLI tool to run queries against sqltatabases and convert the results to json, csv, excel in the command line or python program. Easy to use for Humans, automations, LLMS/Agents

Git-Native Coding Agent for Mac

DeepBlue Brain：一个面向 RAG 全链路教学与理解的白盒化交互平台，支持各类文档上传、混合检索、实时检索日志流、提示词原文溯源与流式问答。

Full-stack Generative Video Cloud

OpenMeta CLI - Autonomous, local-first open source contribution agent for developers

一个更强调可控、可追踪和 Token 效率的 AI 多智能体开发工作流 || An AI multi-agent development workflow that emphasizes controllability, traceability, and token efficiency

Python toolkit for on-chain AI agents on BNB Chain.

A Claude Code / agent skill for building genuinely designed, editable Feishu / Lark (飞书) whiteboards — deliberate composition, real hierarchy, a gated pipeline with pre-render fit-check and independent design critique.

Ship agentic. Stay coherent. Self-checking code integrity for AI coding agents, via MCP.

Extension for the pi coding agent that intelligently routes each turn to the right LLM tier (high/medium/low) based on task intent, session budget, context size, and custom rules.

Agentic Coding platform for Professional SWE work focusing on output quality. Self-review, supervision, dynamic workflows, dynamic agent loops.

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

AI Agent 科研全流程教学包，能教学生从零部署 Codex、Claude Code、OpenClaw、Hermes 等 Agent，学会使用 Skills、飞书、AMiner、AI4Scholar、Zotero、Obsidian 等工具，完成真实文献检索、文献日报、知识库搭建、选题生成、理论建构、情景实验设计、量表开发、统计分析、因果推断、文本挖掘、EEG/ERP 实验、BCI 脑电智能建模、论文写作、审稿自查、期刊排版和盲审投稿包制作；学生学完后可以按课程模板一步步让 AI Agent 协助完成从“找文献、定选题、做实验、分析数据”到“写论文、查引用、改格式、准备投稿”的完整科研流程。

OpenCode package for Caveman: terse AI responses, slash commands, compact reviews, commit messages, and markdown memory compression.

A free, open-source AI agent that runs entirely on your machine — controls your computer like you would, works across any app, and handles arbitrary tasks: writing code, analyzing images, organizing files, researching and building spreadsheets, whatever you throw at it. Unlike Claude Cowork, nothing leaves your device.

M.Y.T.H.A.R.A — Mind Yoked Tonal Haptic Adaptive Resonant Assistant. Open-source agentic AI Android OS layer. Local-first, private-by-construction, BYO-model alternative to Android 17 / Aluminium OS Gemini-everywhere.

搭子.skill / Partner：Claude Code 负责规划、润色和审查，Codex 负责实现、监控和验收。Same-session receipts prove no wasted Claude cold starts.

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates. Markdown library (loop-graph), not a framework.

A native macOS desktop pet that visualizes OpenClaw agent activity.

A traceable personal memory layer that carries verified state across apps, models, and AI agents.

A hands-on course for learning PydanticAI - the Python agent framework built on Pydantic

My Claude stuff (skills, agents and whatnot.)

AI agent (Claude Code + Codex) & system monitor for the Thermalright 9.16 LCD — native macOS

Multigent is an AI-native collaboration platform that brings humans and autonomous agents together. Manage teams, projects, workflows, tools, and shared context through a unified control plane designed for the future of intelligent work.

A zero-to-100 learning path for applied AI engineering — RAG, embeddings, vector search, agents, MCP, and the production engineering around them. 56 pages, built as a searchable site.