Python agents

An open source chat bot architecture for voice/vision (and multimodal) assistants, local(CPU/GPU bound) and remote(I/O bound) to run.

Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"

This project is a **proof of concept** that aims to replicate the reasoning capabilities of OpenAI's newly released O1 model.

MyShelf is an experiment to create a GenAI utility to track reminders, memories, random adhoc information, shopping lists, and more.

Query LLMs and AI tools with voice commands

基于Qwen2+SFT+DPO的医疗问答系统，项目中使用了自定义的 SFTTrainer/DPOTrainer/TRPOTrainer用于训练，其次，项目还调用各种知识库工具（neo4j, milvus, LDA, 等）进行自动化训练数据生成。另外，使用 vllm 用于推理和部署训好的模型, 该模型会通过 vllm API 来接入一个基于 embedder + Reranker 的 RAG 系统。另外还参考 MDAgents 论文实现了一个多智能体会诊系统，同样也支持 vllm api 接入。

Example Environments for the Godot RL Agents library

Minimalistic server (written in C) and a python3 client to allow calling native functions on a remote host for automation purposes

AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while preserving semantic meaning with advanced compression strategies.

Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.

Dynatrace AI Observability OTel instrumentation examples

Collecting a variety of Agent-Ready tool modules

Use WeChat to route messages to Claude Code or Codex.

Building Software Agents On Bittensor

Build, deploy, and orchestrate event-driven agents natively on Apache Flink® and Apache Kafka®

Make AI work for Everyone - Monitoring and governing for your AI/ML

Context engine for large codebases, exposed through MCP. Gives AI coding agents precise repository context; benchmarked at frontier-agent quality with ~25x lower model cost and 45% fewer tokens with semantic search.

This depository introduces a multi-agent conversation framework which facilitates in depth conversation among LLMs for complex disease diagnosis.

A unified, self-hosted platform for testing and debugging regular expressions. OpenRegex uses isolated polyglot micro-workers to guarantee 100% native engine consistency, featuring ReDoS protection, real-time analysis, and an AI-powered assistant.

A collection of Restate examples for AI use cases: agents, A2A, MCP, ...

Agent Git: Agent Version Control, Open-Branching, and Reinforcement Learning MDP for Agentic AI. A Standalone Agentic AI Infrastructure Layer for LangGraph Ecosystems

You Can Learn Deep Research AI Agent Design & Launch In 25 Min | Kimi K2 0905, LangChain, OpenSource

Self-hosted AI agent system built on Claude Code. Multi-channel chat, persistent memory with semantic search, scheduled tasks, and a single-file dashboard.

Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, deterministic checks, built for CI.

AtlasClaw is an enterprise agent framework supporting mutliple users and multi system integration.

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.

Composable Agent Skills for Polymarket prediction market trading. Paper-trading-first, security-audited. Works with Claude Code, OpenClaw, NanoClaw, Codex, Cursor.

Code for Temporal Straightening for Latent Planning

A secure file system for your agents to execute code

一个让 AI Agent 订阅、转录、检索并深度理解全球播客的 Skill。

Local AI multi-agent orchestration desktop app (Tauri · LangGraph)

[ECCV 2026] Promsa: Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering

Open-source Agent Skills for planning, drafting, revising, and polishing SCI/SSCI papers—while preserving evidence, citations, and claim strength.

Production-grade agent skills and Custom GPT prompts for ChatGPT, Claude Code, and Codex. 140 skills, 28 agents, Agent Skills spec compliant.

A simple AI agent that turns prompts into articulated 3D objects.

针对闽台一带的宫庙建筑立面图像要素的科研助手Agent工具

Project-local Codex workspace kit with reusable skills, agents, hooks, plans, docs, and helper scripts for multi-repository development.

这是一个桌面小宠物 Agent，是我家暖宝

交接 Skill（Jiaojie）：跨窗口、跨模型、跨设备、跨语言的 AI 上下文交接工具。换窗口，不失忆；换模型，不重来。Open-source AI context handoff.

Donna — a starter Hermes Agent profile: opinionated persona, 73 curated skills, guided first-run orientation, optional Token Router. MIT.

Local-first, evidence-aware project memory for AI coding agents.

Hermes Agent conversation integration for Home Assistant

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters. It is a powerful platform that allows you to create, deploy, and manage continuous AI agents that automate complex workflows.

将参考图片离线描摹为纯 HTML + CSS 单文件插画的 Agent 插件，支持轮廓提取、局部渐变与输出审计。

Job Yang's AI Agent Skills: writing, video reading, and reusable agent workflows.

An agent skill with multiple gates to check and to remove any AI slop. Use it with codex/claude code or any of your favorite AI tools.

Dulus Ai — Agentic AI, Making Gemini web cappable of running bash commands in your terminal! [Gui, Web, Cli, Telegram, 2,000 MCP, 100K Skills . LiteLLM (100+ providers), local models via Ollama, /lang in 34 languages, Mesa Redonda, I create the first utility coin that can be used 100% as AI quota or Fuel, is called $Dulus

A skilll for agent to add a Civilization-style ceremonial quote when a substantial multi-step task is truly complete.

一个基于三层 Agent 架构的容器代码执行系统，专门用于在 Kali Linux Docker 容器中安全、自动地执行渗透测试工具。附赠配置好的hexstrike-ai docker

Just Another Telegram Ai Chat Bot Written In Python With Pyrogram.

openai/whisper + extra features

💡✨ Zotero, RAG, MCP, and deep research

The AI runtime that turns your framework functions into OpenAI compatible endpoints

ChatGPT Whatsapp Bot With Twilio

GPT-3 client for Windows and Unix with memories management that supports both text and speech in any language. Includes a free text2image

LLM Based NLP Library.

[ICLRW 2026 Best Short Paper Award] Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning

Find that one coding agent session you want to get back to!

Canopy - the open-source agent workspace runtime

A 股数据与量化 Skill，零配置开箱即用，完全免费。提供实时行情、历史 K 线、分钟线、技术指标与基础策略分析，内置多数据源自动切换；同时集成模拟舱 Skill，支持信号生成、模拟下单、持仓管理与交易结果反馈，适用于 Agent、策略研究与自动化交易系统

🌟PolyGPT: An Overview of Agent-Based System Architecture for Autonomous Business Operations

Langchain chat with memory and a GUI made in Streamlit

A Pythonic integration for LLMs.

The official server application for running agents within the Agentica framework from Symbolica

tinyAgent uniquely treats functions as first-class citizens, easily transforming them into powerful AI tools. Inspired by human organizational structures, it dynamically orchestrates specialized agents, balancing security and capability for complex tasks.

Memory Agent monorepo

🧠 Reverse-Engineered Python Client for ChatGPT Web Conversations

Welcome to GPTNicheFinder, a powerful niche research tool powered by Google Trends data and OpenAI's GPT model. This application provides a streamlined approach to identify profitable niche markets by leveraging data-driven insights and cutting-edge artificial intelligence.

Python program to make LLM agents play characters and talk to each other.

Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523). RODE is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft multi-agent benchmark.

The Unreal ML Agents Toolkit is an open-source project that enables Unreal Engine games and simulations to serve as environments for training intelligent agents using deep reinforcement learning. This project is a port of Unity ML-Agents, adapted to work within Unreal Engine.

SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents

This is a Python application that allows you to load a PDF and ask questions about it using natural language. The application uses a LLM to generate a response about your PDF. The LLM will not answer questions unrelated to the document.

Advanced MCP Server ROS 2 bridging AI agents straight into robotics

Development Plugin for Avalonia

AgentOpt automatically finds the best LLM model combination for each step of your agent — optimizing for accuracy, cost, and latency.

一个用于 AI 虚拟试衣的 Agent Skill。用户可以通过“上传服装图/模特图”或“文字描述”快速生成试穿效果图，并可继续生成多角度素材和展示视频。

Design Multi-Agent AI Systems Using MCP and A2A, by Packt Publishing

🇨🇳 claude-howto 完整中文翻译版 · 基于 luongnv89/claude-howto

An opinionated Claude Code Plugin Pack. Skills, Agents, Hooks, MCPs. Examples: Email draft preview assistance & humanisation. Agents for Codex and Gemini "outsourcing". Skills for Google Analytics & Google Tag Manager, Shopify and much more

Staged self-improvement engine for Hermes-style memory, skill, and fact updates with explicit review and apply/discard gates.

AI agent debugging, collaboration, and trace observability. Built for teams using CrewAI, OpenAI, and more.

The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.

A TRPG Agent with a UI for a better solo gaming experience.

Implementation of paper "Playful Agentic Robot Learning"

工业级数学建模竞赛 Agent · 支持国赛/五一赛/美赛 · 双模式（全自动 + 人工把关）· 6 维问题分流 · 5 人评审团 · 模型依赖 DAG · 一站式论文产出

The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.

Evolva 是面向工程场景的本地 Agent 控制台，把模型、工具、记忆、工作流、MCP、Trace、Eval 与 Guardrails 收敛到一个可审计的运行闭环中，让每一次 Agent 执行都可追踪、可验证、可复用、可进化。

This repo contains AI-powered software development patterns showing how to integrate agentic AI in different stages of software development lifecycle using Kiro, Amazon Q Business and Amazon Bedrock. This collection of patterns demonstrates practical approaches for leveraging AWS's generative AI capabilities across the software dev

Aurora: Unified Video Editing with a Tool-Using Agent

The core agent loop in a small Python codebase

PyTorch research stack for ML multi-factor trading: 213 factors, bias correction, portfolio optimization, and vectorized backtesting.

Jev-Mem: System-One Controlled Agentic Memory

ScienceIDE: Turning World’s Scientific Codebase into Agent Learnable Environments

An evaluation harness for medical/health AI agents — reproduce and cover multiple benchmarks under one scoring discipline

Client Code Examples, Use Cases and Benchmarks for Enterprise h2oGPTe RAG-Based GenAI Platform

Ship agents you can audit.

카카오톡 ChatGPT AI 챗봇 빌더

A new AI Game Paradigm in Autonomous world. it includes configurations for agents, functional buildings, and equipment, as well as the logic for agents daily behavior and interactions with buildings, equipments...etc.