Python agents

🐟 闲鱼 OpenClaw/Botpress 频道插件 | Xianyu (Goofish) AI Agent Channel Plugin — 智能客服自动回复、自动发货，Bridge 模式一键接入

AI agent that turns your rough ideas into perfect image generation prompts. 7-component formula, 70+ creative techniques, 9 domain modes.

Welcome to the central repository for the **Antigravity** ecosystem. This project houses a collection of AI Agents, Task Skills, and Coding Rules designed to enhance autonomous coding workflows.

Cross-agent session translator (Claude Code <-> Codex CLI)

Quantitative trading skill for Indian equity markets with Zerodha integration. Generate trading bots, fetch live index data, and manage risk with Claude Code.

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

Live2D、AI Agent 与 GPT-SoVITS：桌面 AI 数字角色

🐧 Unify-Agent: An end-to-end unified multimodal agent for faithful, knowledge-grounded image generation.

Code for MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems

A Model Context Protocol (MCP) server that exposes PyMOL as a typed tool surface to your agent (Claude Code/Desktop, Codex, or any MCP-compatible client)

CAD CLI and MCP server for AI agents

Standardized tool schemas and SDKs that expose Sciverse Open Platform retrieval capabilities to LLM agents.

Source code for the Build Your Own Coding Agent book

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

⚡ CLI toolkit for Google Flow — Nano Banana Pro images, Omni Flash videos, MCP v2 & OpenAI API.

Run a documented subset of verl-style OPD on one consumer GPU—typed config, Parquet prompts, and PEFT scale-out artifacts.

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

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

Ship agents you can audit.

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.

Agent Connect Protocol SDK

VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking

An open-source platform for orchestrating AI agents — secure, simple, and built for everyone. Multi-agent, real-time task board, web control panel, skills system, browser automation, multi-provider, scheduler, and more. One command to start. Everything from the browser. No coding required.

Langchain chat with memory and a GUI made in Streamlit

Build a 100% local Retrieval Augmented Generation (RAG) system with Python, LangChain, Ollama and ChromaDB!

The open source chat powered by LLMs with RAG. Kollektiv makes it easy to sync your custom data sources and get accurate, contextual replies.

🤖️ 聊天机器人——夫子的「自然语言理解」模块

A simple matrix bot that supports image generation and chatting using ChatGPT

Some words that LLM regularly uses

Query LLMs and AI tools with voice commands

Pirate trainer (Deep Learning, Autonomous Agents, 3D, Unity, Hyperopt, Keras)

AI Coding 落地架构的参考项目，支持所有主流支持 Skills 的 Agent/AI Coding IDE。

A local macOS HTTP API gateway that exposes Apple apps (Reminders, Messages, etc.) to AI agents

UGC reel production engine for AI coding agents. Create scroll-stopping short-form videos at scale.

Python agent for Opbeat.

Training an Agent to make automated trading decisions in a simulated stochastic market environment using Reinforcement Learning or Deep Q-Learning

Meta-prompt: a simple self-improving language agent

Server-side video workflows for agents: ingest, understand, search, edit, stream.

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.

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。

Browse, search, and revisit your AI coding sessions.

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.

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.

YGK-a: Your Genius, Knowledgeable assistant, An advanced ChatGPT client from your shell.

Dynatrace AI Observability OTel instrumentation examples

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.

Collecting a variety of Agent-Ready tool modules

Building Software Agents On Bittensor

An algorithm-focused interface for common llm training, continual learning, and reinforcement learning techniques

Structured, temporal memory for AI agents.

Development Plugin for Avalonia

Ultra lightweight API server to convert files (.pdf, .docx, .xlsx) into formatted markdown.

Open-source AI customer support platform — AI chatbot with human handoff, Shopify & Slack integrations, visual workflow builder. Self-hosted alternative to Intercom & Zendesk. Apache-2.0.

Observability for AI agents. See what your agent did, why it cost that much, and what to fix.

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.

Search-Then-Verify natural language querying over time series databases (ICML 2026). Includes NLQTSBench.

streamlit region:us

transformers safetensors internlm2 text-generation conversational custom_code

transformers safetensors gemma4 image-text-to-text bf16 multimodal

transformers safetensors qwen2 text-generation code qwen

transformers safetensors stablelm text-generation causal-lm conversational

Official code for "MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management"

An easy-to-use harness for agentic projects.

Create speech-to-speech voice agents that deliver personalized self-service experiences and natural-sounding voices, seamlessly integrated with telephony systems.

Developer recipes for Meta Model API — agentic workflows, multi-agent orchestration patterns, and use case examples with cost comparisons. Colab notebooks + standalone Python files.

MemoHarness: Agent Harnesses That Learn from Experience

ScrapeGPT is a RAG-based Telegram bot designed to scrape and analyze websites, then answer questions based on the scraped content. The bot utilizes Retrieval Augmented Generation and webscraping to return natural language answers to the user's queries.

Using Langchain and OpenAI to analyse resume

linkedin-jobs-RAG

Guardrails to support any-agent

A simple stochastic OpenAI environment for training RL agents

A Python crawler tool that can automatically simulate browser operations to crawl all users' tweet content and save all static resources (videos, pictures) locally without calling the Twitter API. Use the selenium library.

🍎SciDER: Scientific Data-centric End-to-end Researcher🍹

🧠 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.

Welcome to AI Agents Handbook — your all-in-one guide for building AI agents, from basics to advanced techniques. Explore code, tutorials, and resources for beginners to experts!

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

Chinese version implementation of Generative Agents: Interactive Simulacra of Human Behavior

Secure, locally-run Retrieval-Augmented Generation system for document-based question-answering, utilizing Llama 3, Mistral, and Gemini models with a user-friendly Streamlit interface.

[CVPR 2025] RAP: Retrieval-Augmented Personalization

[NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.

[NAACL 2025 Demo Track] GenSim: A General Social Simulation Platform with Large Language Model based Agents

Agentic GitHub Guardrails - Replace static protection rules with context-aware enforcement.

基于 Apache Airflow 的微信智能应用编排框架，通过可视化工作流驱动 AI 与数据自动化任务。支持 智能客服（多轮对话/知识库）、AI 图文/短视频生成、智能提醒等应用，灵活扩展多模态交互与大模型能力。

A Straightforward, Step-by-Step Implementation of a Video Diffusion Model

An MCP (Model Context Protocol) server that turns all pybag Windows debugger functions into native MCP tools. It lets MCP-compatible clients (Claude Desktop, Claude Code, Cowork, OpenAI Codex CLI, Cursor, and custom agents) control user-mode processes, kernel sessions, and crash dump analysis via structured JSON calls.

A quickstart tool for AmpliconArchitect. Enables all steps (alignment, CNV calling, seed interval detection) prior to running AmpliconArchitect, and invokes AmpliconClassifier

Lightweight markdown-based workflow for collaborating with AI coding assistants using spec-driven development methodology

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.

[NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents

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

Connect agent policies for distributed ML applications

Multi-Agent Mesh · Connect · Orchestrate · Scale

Production-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol, persistent memory, web dashboard, RBAC.

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