Custom agents

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, TUI, iPhone, REST/SSE, and MCP.

The fully self-hostable, open composable platform for agent orchestration and human collaboration. With tools, security, memory, cost saving, and routing all built in.

Run LLMs, VLMs, ASR, TTS, diarization and more fully on-device with Apple's Core AI framework (iOS/macOS 27) — one line of Swift per model, 53 models pinned to immutable Hugging Face revisions, each gated against its source model before enrollment. Plugs into Apple's FoundationModels API: LanguageModelSession with tool calling + guided generation.

Open-source runtime action grounding framework for AI agents. Verify proposed actions against live systems of record before execution.

My Personal Blog (Robotics)

AI editing agent for Adobe Premiere Pro: silence removal, repeated-take dedup (LLM), and minimal Hinglish captions. UXP panel + local Node server.

Reasonix 便携工具箱：PortaKit for 0.5X（路径重定向）+ PortaKit for 1.X（NTFS Junction），U盘/同步盘即插即用。搭配 migration-assistant 实现 0.5X→1.X 无缝升级。 / Reasonix portable toolkit: PortaKit for 0.5X (path redirection) + PortaKit for 1.X (NTFS Junction), USB/sync disk plug-and-play. Pair with migration-assistant for seamless 0.5X→1.X upgrade.

A multi-agent KiCad PCB design workspace: 9 skills driving a Phase 0-5 pipeline from topology discussion to Gerber shipout. Noncommercial.

AI video auto-dubbing plugin for coding agents — translate & dub videos into multiple languages via the Perso Dubbing API. Works with Claude Code, Cursor, Codex & Antigravity.

📗Reusable docs, prompts, templates, and engineering practices for AI-agent coding, agent design, OpenSpec/SDD, context engineering, prompt engineering, and agent workflows.

Multiple agents, one source of truth: a Planner/Coder/Reviewer demo of how a shared Statewave subject prevents parallel-agent context collisions.

🔥 Quo Vadis, World Modeling? Towards Interactive World Proxies for Continually Improving Agents

Self-hosted personal AI assistant: chat, cost tracking, tasks, and agents.

Telegram channel and group reader MCP Server

Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.

Open-source AI workspace that turns an expert's context into structured talks, articles, and courses. LangGraph agent with versioned project memory (Knowledge Sphere), skills, and live activity streaming.

EduFlow 畅学 — AI-driven student self-learning platform. AI agents assist, students lead. Next.js + FastAPI + LangGraph.

Context Limiter & Output Vetter for context bloat. It is a highly specialized, structure-aware JSON built specifically to intercept and compress MCP responses before they annihilate your LLM's context window.

[AAAI 2026]RAG, Benchmark, robust RAG generation

Codex + Claude → DeepSeek or other llm 本地代理 | Agent Protocol Translation Proxy

A basic voice agent built with Node.js agents framework

A fully local, zero-API, zero-finetune multi-agent AI architecture that makes an 8B base model perform high level model reasoning, research, coding, and web analysis. By AI-assisted development. Open-source for everyone to extend.

Smart money tracker for Solana. Watches whale and VC wallets and alerts when they make significant moves.

The official documentation of Gaia. Learn how to run nodes, deploy nodes to domains, find framework integrations and learn how to build and run agents with decentralized inferencing.

Embedded PostgreSQL 18 server with true concurrent connections - zero config, auto-provision databases

Open-source AI agent. Lives in your terminal.

浏览器中的开源 AI 游戏分析实验室，结合结构化复盘演示与可游玩的沙盒模块，支持局势解读、策略建议与赛后分析。

an open-source tool for the multi-agent-based development and testing of local energy market applications

OpenMolt lets you build programmatic AI agents in Node.js that think, plan, and act using tools, integrations, and memory — directly from your codebase.

Multi-Agent LLM Evaluation Docs: https://maseval.readthedocs.io/

Complete observability platform for AI agents and MCP servers. Improve your AI deployment outcomes, identify inference inefficiencies, and gain insights into real agent usage patterns.

We have developed a fully AI/ML-based itinerary recommendation system which when used by people coming to visit any place would allow them to better optimize their cost/time. We have 3 developed 3 inputs that are Scraping Twitter, UI Form, and FB Chatbot

FAQ's answering chatbot using open source chatbot framework Rasa Stack

Design and build a chatbot using data from the Cornell Movie Dialogues corpus, using Keras

用最简单的代码带你实现基于大模型的本地知识库问答系统

使用QQ聊天记录制作属于你自己的聊天机器人

A fullstack Rust + React chat app using open-source Llama language models

GPT-For-NLG-Tasks

🍥 Haskell向けLINE Messaging API SDK

Python3 wrapper/library that simplifies telegram bot development. It supports both sync and asyncio methods of programming. Dive in and start making awesome bots!

TypeScript framework for writing chatbot applications

Python 3 ChatBot / Botnet

A full-featured, hackable Next.js AI chatbot built using my chat UI components

support GeminiPro 、ChatGpt;Eywa comes from Pandora

Pytorch Implementation of "Sequential Dialogue Context Modeling for Spoken Language Understanding( https://arxiv.org/abs/1705.03455 )"

Cross-Platform App and Web Extension for Personalized Product Profiling

One stop shop - Local-first RAG stack with intelligent polyglot-code/docs, remote code execution, local llama enrichment, progressive disclosure tools, mcp server, sandboxed security.

This repository helps you evaluate your models on the FreshStack benchmark!

AI web agent to find answers to any question

Build powerful applications/modules with just one prompt using LLM agent tools like Cursor, Windsuft, GitHub Copilot, etc. This is the future of developer productivity.

Easy-to-follow Pytorch tutorial Notebook for Multi-Agent-Diverse-Generative-Adversarial-Networks

LTL Optimal Multi-Agent Planner (LOMAP)

Turn any MCP Client into a "multi-agent" system (via prompting)

This repository is your comprehensive guide to building, orchestrating, and deploying AI agents and workflows using the Microsoft Agent Framework. Whether you're creating simple chat agents or complex multi-agent workflows, this repository has everything you need to get started.

Neural parameter calibration for multi-agent models. Uses neural networks to estimate marginal densities on parameters and networks

Codes accompanying the paper "Influence-Based Multi-Agent Exploration" (ICLR 2020 spotlight)

Multi-Agent RL Environment for the Stratego Board Game (and variants)

one go multi-agent system like manus using any MCP you want with configuration // 一个go语言编写的类似manus的多智能体系统，可以通过配置连接任何你想使用的MCP组件

This is Claude Code Tool for Unity Shader.

Please Read Me First. This is a set of java file of my final version of electronic artifacts. This is a game to map my experience in Disney World, in Orlando during this spring break. However, because of my limited skills in computer science, I really have no idea how to simplify the process to run the game. Sorry for the inconvenience. In order to run the game, you may need to install JAVA. I hope the following links will help you.     http://www.oracle.com/technetwork/java/javase/downloads/index-jsp-138363.html#javasejdk
    http://www.cc.gatech.edu/~simpkins/teaching/gatech/cs1331/guides/install-java.html My main file is called Disney. You can call Disney in console to start the game. However, I failed to putting all the things inside Disney file. Therefore, you may also need to call AdventureLand, MainStreet, and FrontierLand to start other three games. I hope this will help you. Sorry again for the inconvenience. 1. the structure of my project My project only focused on my trip in Magic Kingdom, one part of Disney world in Orlando. It is a game which guides players to choose from six sub-games, which match six sections of the park, Main Street U.S.A, Tomorrowland, Adventureland, Frontierland, Fantasyland and Liberty Square. I chose one of the rides I took in each section which, from my perspective, shows what I found interesting in Disney world. I changed what I experienced in the park into a small computer game. I want to share my experience with others while they play my games. In the following part of self reflection, I explain the background, rules and other things about each game. For convenience of matching them, I use different color to mark different parts. I hope it will help readers a little bit when they are lost in my disordered reflections. 1. the hall of presidents - Liberty Square 2. Festivall parade - Fantasyland (I explain this one in the part of technology skill limitations) 3. Big Thunder Mountain Railroad - Frontierland

Basic ReAct agent implementation in Python from scratch

An infra-level React UI platform to create cohesion and consistency so teams and agents can build faster, together.

AI Assistant Delegation Framework - Keep your context clean by delegating API queries to specialized sub-agents 🐊

Agentic RAG with MCP Server

A platform designed to facilitate the development of advanced conversational agents using retrieval augmented generation (RAG).

Microsoft Agent Framework - learn how to adress agentic enterprise scenarios

replicantlife is a framework for generative agents that can be used in a simulation engine or standalone. Agents are powered with metacognition modules that allow that to learn and adjust their strategy over time.

CLI tool that lets you chat with your agent locally for faster feedback and debugging

Playwright Copilot is a Visual Studio Code extension that accelerates BDD (Behavior Driven Development) testing with AI-generated code suggestions.

Copilot AI translation plugin for Bob

This repository contains the code for the paper "Epidemic modelling with Generative Agents"

个人简历 2026 全栈完整版更新，支持自动化部署，后续持续学习和加入 AI 功能，欢迎交流学习。有帮助Star鼓励下吧，谢谢！

Personal dotfiles configuration.

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

CORMAS (COmmon pool Ressources and Multi-Agent Simulations)

Reset IDE data, Create backup and restore, manage multi-account easily, Work for VS-Code/fork based app.

AI code generation and improvement

A minecraft chat bot for anarchy servers (similar to mooomooo)

Local Video RAG Engine. A FastAPI microservice for video understanding: Scene Detection + Whisper ASR + Qwen3-VL. Optimized for Apple Silicon (MLX) & Windows/Linux (Llama.cpp).

Improve insights to make smarter decisions by tapping into real-time data with retrieval-augmented generation (RAG).

Interactive LLM Chatbot that constructs direct and transitive software dependencies as a knowledge graph and answers user's questions leveraging RAG and critic-agent approach

Dataflow-guided retrieval augmentation for repository-level code completion, ACL 2024 (main)

Enhancing Medical Question-Answering System through Advanced Information Retrieval Strategies

Code for Multi-Agent Common Knowledge Reinforcement Learning (NeurIPS 2019)

二阶多智能体系统固定时间一致性

The official repository for "CartoAgent: a multimodal large language model-powered multi-agent cartographic framework for map style transfer and evaluation".

[TPAMI] Interaction Pattern Disentangling for Multi-Agent Reinforcement Learning

Python implementation of Space-time A*, Prioritized Planning, & Conflict-based Search for Multi-agent Path Finding (MAPF)

[ICLR 2026] Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing

This is a MATLAB-based reinforcement learning framework that includes the Proximal Policy Optimization (PPO) algorithm and its multi-agent extension (MAPPO). It supports GPU acceleration and parallel computing, making it suitable for research and engineering applications in control systems.

Create configurable Claude Code agents as ComfyUI nodes. Assemble agentic workflows that can leverage all the existing possibilites of ComfyUI.

An open-source alternative to Claude Cowork, powered by Claude Agent SDK

Deploy Claude agents as production APIs — with sessions, streaming, sandboxing, and persistence handled for you.

Automated pipeline for generating, verifying, and preparing high-quality function calling datasets for model fine-tuning. Reduces manual annotation through multi-stage validation and conversion to training formats. Built for Azure ML with permissive license models (Phi3.5 MoE, Phi4 etc).

Backend for skillgraph - a skill based framework for building agents that work.

An example Nuxt 4 app using Mastra AI agent framework

An R package that provides an agent based modeling framework for epidemic models

A powerful Model Context Protocol (MCP) server that provides an access to serverless browser for AI agents and apps

A VSCode Language Model Chat Provider to use Amazon Bedrock in Copilot Chat