Python agents

Claude Code Plugins for AI Native-based Engineer

Agent-managed GitHub merge queue for Codex, Claude Code, Cursor, and MCP clients

LSAP (Language Server Agent Protocol) is an open protocol that defines how AI coding agents interact with Language Servers

This repository consists of agentic ai usecases.

When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deeds; fakes blocked, not warned. Each check ships at measured zero false positives. 誠

Build, debug, profile, test, refactor, and release Swift apps across iOS, macOS, Xcode, SwiftUI, SwiftPM, Tuist, and App Store Connect.

AI-driven Azure operations workbench. Chat with your tenant, investigate incidents with a team of specialist AI agents, and assess, monitor & remediate your cloud — runs in your own subscription. One-click deploy.

AI Agent驱动的Claude code 软件开发工作流框架 — 让AI Agent协作完成软件全流程开发。自动生成PRD、架构设计、源码、教程，实现"描述即交付"。

🤖 Agent skills for interacting with Capawesome, Capacitor and the Ionic Framework.

Open-source AI Operating System (AIOS) blueprint for Claude Code & Codex — turn any agent into your personal second brain + Chief of Staff: skills, self-verifying workflows, a second-brain wiki, and deterministic tools. Fork it for any role or domain.

Calibre library automation via FastMCP — metadata, shelves, RAG-friendly export. Companion to Calibre, not a replacement. For Cursor / Claude Desktop.

Agent-native Stata bridge for empirical research — run DiD/IV/RDD and publication-ready tables from Claude Code, Jupyter, or VS Code on one token-economy result schema, with StatsPAI cross-validation. | 面向实证研究的智能体 Stata 桥接器——在 Claude Code、Jupyter、VS Code 中用一套省 token 的结果格式跑 DiD/IV/RDD 与出版级表格，并支持 StatsPAI 跨栈交叉验证。

Optimize LLM agent harnesses through tunable Formulas to dynamically enhance the agent, and improve those Formulas with optimizers based on collected agent rollout trajectories.

A design-of-experiments platform for evaluating compound AI systems - find which technique drives quality, by how much, and whether the difference is real.

gradio llm diffusion grounding grounded llm-grounded text-to-image language

streamlit region:us

transformers safetensors llama text-generation text-generation-inference unsloth

transformers pytorch safetensors llama text-generation en

transformers safetensors qwen3_next text-generation qwen3 moe

transformers pytorch codegen text-generation custom_code arxiv:2305.02309

transformers safetensors gguf llama text-generation llama-factory

transformers gguf llama llama-2 text-generation code

🇰🇷 소상공인(운영 중인 가게·자영업자) 지원사업 조사 에이전트 스킬 [Claude Code·Codex·agy(Antigravity)·Cursor·Gemini CLI 지원] 소상공인24·기업마당 전수 크롤링 + 프로필 기반 5단계 자격 판정 '오늘 신청할 것'부터 보고 (Korea-only)

Caelune (凯露恩) — Local-first retrieval for private Markdown, PDF, and Tika documents, with a Windows desktop app and read-only MCP server.｜本地优先的私人知识检索工具。

douyin-agent

Graduation project researching a trading agent on microgrids to trade energy between them

AgentPay-AI is a lightweight pay-per-use GenAI agent platform that simulates token-based billing (USDC-style) for AI tasks. It demonstrates how AI services can be monetized at the request level, similar to how real-world AI APIs charge users per token or request.

AuditAI is an Agentic AI-powered website auditing tool that analyzes SEO, performance, accessibility, and security issues using AI-generated insights.

A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern

Curated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP, LangChain, and more. Browse, install, and verify reusable agent workflows.

McKinsey-grade market research decks for Claude Code — adversarially verified numbers, 15 McKinsey methodologies as executable workflow, multi-agent pipeline. 一条指令产出敢被挑战的麦肯锡级市场研究 deck。

[AAAI 2026] AutoTool: Efficient Tool Selection for Large Language Model Agents

基于大模型的自动化数据分析工具，支持上传 Excel/CSV 数据，通过 AI Agent 自动规划和执行分析任务，生成带可视化的复盘报告。 项目说明：这是一个学习项目，在探索不同 Agent 架构模式的过程中，迭代了多个版本的循环实现。因此项目中包含了 5 种不同的 Agent 运行模式，每种模式代表了不同的设计思路和实现方式，便于学习和对比。

NVIDIA Omniverse NuRec agent skills automate neural reconstruction for autonomous vehicle and robotics simulation, running the reconstruction and rendering workflow end to end.

Self-hosted AI agent that triages production errors and opens pull requests with fixes — LangChain + Gemini/GPT-4o/Claude, zero-ops Docker.

[NeurIPS 2025] LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents

OSINT investigation orchestrator for journalists — structured briefs, methodology approval, sourced findings, independent fact-checking, and knowledge ingestion. 17 skills, 7 runtimes, local-capable.

Local LLM·RAG·AI Agent·바이브 코딩을 개념부터 실습과 검증까지 다루는 학습 자료

Troubleshooting Kubernetes Agentically

Agent skills for daily use

Batch-remove AI provenance and image metadata with ExifTool. CLI + Agent Skill, preserving pixel data.

AI 幾級了 — What level is your AI usage? Reads local agent logs and writes an LV0–LV5 report. No ranking.

Delegated authority for AI agents. A Pigeon Pass says what an agent may do.

Lightweight AI coding agent for the terminal, with one-shot automation, persistent agent teams, and a small reusable OpenAI-compatible agent kernel.

AI-enabled Intelligent Document Processing for Python: 12+ LLM backends, Pydantic schemas, self-hosted OCR (Nanonets-OCR2-3B), auto-schema discovery, HITL review, prod FastAPI server. AGPL-3.0 + commercial.

🎱 AI Agent Governance Framework — Constrain how AI Agents behave in your project. pip install pattern8

Continuous-time multi-agent crowd simulation engine implemented in Python using Numba and Numpy for performance.

This project shows the area division process in Multi-Agent exploration using Cyclic Gradient Descent and also how Cooperative Perceptional Messages are used in V2V communication to share information among agents in about the environment.

Lightweight coding agent that runs in your terminal

MCPToolBench++ MCP Model Context Protocol Tool Use Benchmark on AI Agent and Model Tool Use Ability

Clone of writesonic.com & copy.ai - BlogIQ is an innovative app powered by OpenAI and Langchain, designed to streamline the content creation process for bloggers.

LangChain agent usable tool to screen stock data

⭐ College.ai is an advanced AI-powered platform that provide a set of tools for students, job seekers, and professionals.

An innovative AI conversation API leveraging Google's Gemini for multimodal understanding. Combines FastAPI, Langchain, and Redis for robust, scalable, and privacy-conscious text and image-based interactions

Langchain Agent utilizing OpenAI Function Calls to execute Git commands using Natural Language

A crew of ai agents for extracting data from Jira boards, generating reports and request follow ups on slack.

Source code of our paper "Multi-Agent Consensus Seeking via Large Language Models".

A collection of pre-build wrappers over common RAG systems like ChromaDB, Weaviate, Pinecone, and othersz!

autonomous agent with access to a tool library

yt-chat is an AI skill for summarizing YouTube videos and answering questions about them in Codex or Claude Code.

download and view the contents of a GitHub repository or a ZIP file as a single text file

🌟 OpenAI Assistant Builder & Sharer: Democratize AI Access Empower your AI journey with our cutting-edge repository! Build, share, and monetize AI assistants effortlessly using OpenAI's robust capabilities. Access an intuitive API, integrate custom functions, and retrieve data seamlessly. Join us in democratizing AI for everyone.

A quirky agent

Custom research AI agent that analyzes IPOs, you just have to upload the DRHP and give the company name to the AI agent

An AI agent Learning to play Flappy Bird using Evolution Strategies and deep learning models.

Run AI coding agents like Cursor, Windsurf, and Claude Code via code and let them implement features all the way to a pull request

Ein multimodaler, multi-intelligenter Entwicklungsrahmen

Multi-agent Trajectory Prediction with Fuzzy Query Attention

This is a minimal example to demonstrate how multi-agent reinforcement learning with differentiable communication channels and centralized critics can be realized in RLLib. This example serves as a reference implementation and starting point for making RLLib more compatible with such architectures.

Automatic agentic story generator.

Archive of Indy Reference Agents and Tools. Superseded by the Hyperledger Aries Project.

worker agent API for processing data for Menome Knowledge Vault

Minimal code for A Generalist Agent

My attempt at making a GPT agent for pentesting

Very minimal (and stateless) agent framework

Speed up image generation and improve image quality using Agent Attention.

Variation of "Asynchronous Methods for Deep Reinforcement Learning" with multiple processes generating experience for agent (Keras + Theano + OpenAI Gym)[1-step Q-learning, n-step Q-learning, A3C]

The first Open-Souce RAG-LLM tool to analyse macroeconomic data and forecasts 🦜🔗

A cross platform application to allow use of ChatGPT through mobile MMS applications such as iMessage and Android

customer care chatbot made with Rasa Open Source.

Integrate browser-based ChatGPT with dingtalk chatbot.

Drop-in caching proxy for OpenAI and Anthropic APIs - stop paying for the same answer twice!

A Python-based AI agent chatbot used for generating service proposals based on your own pricing information 🤑

Transform Python functions into remote tools for AI agents

PaperPub is an academic arena where diverse AI Agents read papers daily, pick apart each other's arguments, and fiercely debate.

Multi agent reinforcement learning for intelligent active matter

[NeurIPS 2023] The official implementation of "Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization"

A framework for hosting and scaling AI agents.

ML-Dev-Bench is a benchmark for evaluating AI agents against various ML development tasks.

An AI-powered game playing agent using Claude and PyBoy

[EMNLP 2025] Dataset and Code of "PersonaGym: Evaluating Persona Agents and LLMs"

Reinforcement Learning for Multi-Agent Path Finding

Telegram AI Agent: A powerful Python library for creating AI-powered Telegram bots

Do literature review Fast, Simple and Reliable