Python agents

A curated library of 137 production-grade skills for Claude and other AI coding agents.

TWICC - The Web Interface for Claude & Codex - A web UI to browse and interact with your Claude Code and Codex sessions. View projects, sessions, conversation history, costs, and run Claude and Codex agents — all from your browser.

Dynamic graph runtime for building, adapting, and observing multi-agent LLM systems in Python.

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's record can leak even if the agent is adversarial - enforcement lives in trusted code below the model, validated by a runnable attack gallery.

MetaTrader 5 in a real Windows VM (Docker + QEMU/KVM), driven over REST + MCP — programmatic trading plus server-side TA: OHLC bars enriched with RSI/MACD/Bollinger/ADX/VWAP/Ichimoku/Order Blocks/FVGs (primitives, not signals). Typed MCP tools mirror the whole surface. Multi-broker, multi-account. No Wine bullshit.

Code from anywhere.

Production-ready Agent Skills for Codex, Claude Code, OpenCode and OpenClaw | 小红书图文、学习路径、论文解读与 YouTube 播客笔记

Diverter distills Ultra’s delegation strategy into non-Ultra Codex sessions—bringing in the right native specialist while the main thread keeps moving.

Your AI company, in your device. Local-first AI platform: chat, agent crew, memory, and a model store sized to your hardware - from 4GB laptops to big GPUs. One-click setup, fully private.

Claude Code skill that delegates implementation to GPT-5.6 Sol via Codex CLI, Claude plans and reviews the diff, Sol writes the code. Multi-model AI coding where the model that wrote the diff never grades it.

Static analysis and attack-surface scanner for AI agents — SAST for prompts, tools, MCP servers, and agent workflows. Detects capabilities, prompt risks, tool permissions, and governance gaps before deployment.

AI 驱动的全球招聘信息雷达 —— 扫描全球与中国的在招岗位，用来找工作、读产业风向。 An AI-powered radar for the global job market — scanning open roles worldwide and in China, for job hunting and industry signals.

🤖 The strongest curated list of open-source AI-agent tools for literature review — 70+ tools across 11 categories (Claude Code skills, deep research, MCP servers, PDF parsing, systematic review). 面向智能体文献综述的最强工具大全。

A LLM-powered agent for NetHack

Lightweight agent framework for research PowerPoint generation, editable PPTX delivery, and rendered QA

Turn research and long-form writing into humanistic, model-interpreted Xiaohongshu carousels.

免登陆一键保存小红书笔记到本地的 Skill，适用于 Claude Code/Codex/OpenClaw 等 agent

AI-driven Abaqus workbench: describe a model in a spec, get a real solved one back. Every capability is backed by a check you can run on your own seat, and the gates refuse a doubtful answer instead of returning it. AGPL-3.0 + commercial licence.

SPAR: multi-agent scholarly retrieval with query decomposition, query evolution, and citation-aware exploration.

transformers safetensors eagle_llama text-generation Eagle VLM

🤖 Advanced multi-agent robotics system using ROS2, NVIDIA Isaac Sim, behavior trees, and RL locomotion controllers. Features mobile manipulator, forklift, and Spot robot with autonomous navigation and manipulation. Graduation Project 2025.

CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as a deny-by-default MCP server. Framework-agnostic, Python 3.11+.

AI Agent Skill for generating production-quality SVG illustrations, characters & animations. Render-verify-fix loop ensures pixel-perfect output. Works with Claude, Codex, Cursor, Windsurf & any Agent Skills-compatible tool. Rich gradients, five-zone lighting, character construction.

Guardrails and observability for autonomous AI agents - tool-call auditing, spend caps, and rollback for anything an agent does in production.

Decades of operational expertise from logistics, manufacturing, retail and energy. Codified into agent skills - Works with Claude, OpenAI Codex, OpenClaw, Cursor, Gemini, and 26+ platforms.

The Babel Library is a fast, resumable EPUB translation pipeline powered by the Codex CLI.

Claude Code production-readiness audit plugin with 8 specialist lenses in 3 waves for security, reliability, tests, DevOps, live-app QA, and launch blockers.

Guardrails and observability for autonomous AI agents - tool-call auditing, spend caps, and rollback for anything an agent does in production.

Cogito, ergo sum. A portable self-awareness framework for LLM agents — TICK heartbeat, Focus Stack, Temporal parsing, Self-Perception. Platform-agnostic.

Benchmark of report fidelity for browser agents: does the agent's final report tell the truth about what it actually did?

Personal collection of agent skills using the open SKILL.md standard. Works with Claude (claude.ai, Claude Code, API), Cursor, and other AI assistants.

AtomMem: a long-term memory system for personalized LLM agents.

PromptForge: An enterprise-grade, multi-platform Prompt Engineering framework for AI Agents. Featuring 56 structured templates across 9 domains, 118 ready-to-use presets, and native adapters for Cursor, ZCode, DeepSeek Harness, Claude, and OpenAI. Built with FastAPI Web UI & Typer CLI.

Course Compass 学生选课智能体 | RAG · Function Calling · 约束排课 · Streamlit 本地 Demo

CLI proxy for switching AI model profiles (Claude Code, Codex, etc.)

Набор агентских скилов (Agent Skills для Claude Code и Codex), позволяющих владельцу магазина на Яндекс.Кит управлять магазином из AI-агента: каталог, цены и остатки, заказы, промокоды, коллекции, витрина.

Local OCR, metadata automation and RAG document chat for Paperless-ngx using PaddleOCR and Ollama, designed for CPU-only self-hosted servers

Self-improving, harness-agnostic memory layer for AI agents, backed by Neo4j — lifecycle hooks capture every session, MCP tools recall project memory, and an LLM extraction loop distills durable learnings and evolves the agent's system prompt.

A collection of practical Claude Code skills for real-world development workflows

One expensive model orchestrates, five pinned cheaper subagents do the work. Drop-in CLAUDE.md, agents, and commands for Claude Code.

An ML-powered framework for detecting and counteracting sycophantic spiraling in AI chatbots.

AI security agent for the Python supply chain: scans packages, generates exploits, and validates them in Docker, autonomously.

面向个人用户的轻量化健康管理工具，基于LLM的 Agent 技术，解决用户日常用药安全查询、化验单快速解读、个人就诊记录统一归档的核心需求，全程严格遵守医疗合规要求，不提供任何诊疗服务。

Swarm Intelligence Prediction Engine - Multi-agent AI debate for calibrated forecasting

Prism is a windows desktop ai agent built with electron and a fastapi backend, powered by the google-gemini-3-api. it can understand what is on your screen, plan multi step actions.

a simple lightweight large language model pipeline framework.

🐱 你的二次元赛博哈基米 | 基于 LLM 的智能化番剧管理与分析助手。支持 Bangumi 数据同步、AI 深度画像分析、年度总结海报生成与个性化推荐。

Harnessing AI to Disrupt and Evaluate Security (HADES)

Build Agentic workflows with function calling using open LLMs

Use langchain to create a model that returns answers based on online PDFs that have been read.

Contextual Retrieval solves this problem by prepending chunk-specific explanatory context to each chunk before embedding (“Contextual Embeddings”) and creating the BM25 index (“Contextual BM25”).

A seq2seq based chatbot built with PyTorch (中文聊天机器人)

Telegram chatbot that is integrated with Chat GPT and deployed 24/7 on Render for free

SOC Analyst Level 1 Replacement using RAG LLM

Fully Cooperative Multi-Agent Deep Reinforcement Learning

A powerful, modular, and self-hosted AI assistant that combines website monitoring, ERP integration, system health checks, web search, and personal organization into a single Telegram bot and Web Interface. Powered by Ollama for local, private intelligence.

Reachy Mini MCP | Give your AI a body. This MCP server lets AI systems control the Pollen Robotics Reachy Mini robot. | Speak, listen, see you, and express emotions through physical movement and voice. | Works with Claude, Windsurf, Cursor, or any MCP-compatible AI. | Zero robotics expertise required.

Give your agents real time desktop perception. Stream screen, microphone, and system audio for live context and actions.

proof of concept to generate Airbyte low-code YAML connectors from API documentation

Package with sinapsis templates to support langchain functionality

🤖 🤖 GPT-4 Code Interpreter, Financial Assistant and Content Creator Chat Bot (OpenAI or Local-enabled)

A minimal Chatbot GUI for Ollama models - Streamlit App

Instead of dumping 1000+ tools into a model’s prompt and expecting it to choose wisely, the Unified MCP Tool Graph equips your LLM with structure, clarity, and relevance. It fixes tool confusion, prevents infinite loops, and enables modular, intelligent agent workflows.

An AI-Powered Development Environment generator and workflows

This discord bot gets support on your server managed providing a full featured support ticket system.

Simple. elegant LLM Chat Inference

Python Bot using RASA for NLP

NLP class for rapid ChatBot development in Hungarian language

Pandora is a Therapeutic AI Assistant designed to act as a therapist in order to provide emotional support to people with anxiety & depression.

A multi-functional QQ chatbot developed in NoneBot

A Chatbot with UI design is created, according to some certain datasets (can be replaced). Through statistical analysis and PINN model, it can answer many kinds of questions. The structure of the chatbot can be used as a source of reference.

一个关于血色衣冠的对话机器人， 基于 Rasa, 可语音与机器人对话

discord bot, but its gpt-2

Open-domain chatbot (Meena-style) with a vanilla Transformer seq2seq in PyTorch.

It shows how to use mutimodal and RAG based on multi-region LLM.

Solving openAI's game 'BipedalWalker-v2' with Deep Reinforcement Learning

Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs. EMNLP 2024

Package with sinapsis templates to support OpenAI functionality

GenAI Mind Map Flow Builder uses LLMs (OpenAI & Google Gemini) to generate intelligent mind maps from diverse sources like PDFs, SQL, CSVs, media, and websites. Built with FastAPI and ReactJS, it visualizes key ideas and relationships for data analysis and knowledge discovery.

This is the guide to show the method to build your own AI-Powered voice agent with LiveKit and Twillio

Proximal Policy Optimization (PPO) algorithm for Sonic the Hedgehog

Eva - Is your AI. The future is now.

Python command that uses openai to perform text translations

A Reinforcement Learning agent to perform overtaking action using Double DQN based CNNs which takes images as input built using TensorFlow.

This script allows you to use OpenAI in your CLIs tested on Linux terminal, Mac Terminal and Windows Command Prompt

Writing assistant that edits .docx files and returns output with track changes.

Chat with your Python debugger

Example of RAG using SurrealDB and OpenAI

GPT-3.5-ON-STEROIDS combines GPT with Python tools, empowering dynamic web scraping, language processing, and data retrieval. Contribute to advancing text generation with AI. 🚀

Tools for the Griptape Framework.

Multivoice: Enhance your foreign-language movie and TV show experience with personalized dubbed versions. Our project uses voice cloning and TTS to deliver natural and engaging dubbed dialogue for a seamless viewing adventure.

Void Patcher for Claude Code v2.1.132 — 105 patches (42 feature gates unlocked), zero refusals, zero AUP blocks, in-place Bun SEA bytecode patching with multi-strategy drift detection + auto-heal. macOS / Linux / Windows.

Pyvigate: A Python framework that combines headless browsing with LLMs that assists you in your data solutions, product tours, building RAG applications, web automation, functional testing, and many more!

Experiment on QnA tabular data using LLMs and SQL

🎩 AI-powered cover letter generator

Agent-first knowledge base — wiki over RAG. Plain markdown with wikilinks, background quality agents, and an MCP server for agent navigation.

MCP Server leveraging crawl4ai for web scraping and LLM-based content extraction (Markdown, text snippets, smart extraction). Designed for AI agent integration.

Kuberentes LangChain Agent - Interact with Kubernetes Clusters using LLMs

A highly contextualized retrieval system integrating Large Language Models (LLMs), embeddings, and a dynamic agent-driven framework. Supports PDF and audio file processing, conversational memory, and tool integration (search, calculator). Features advanced HNSW indexing and reranking for accurate information retrieval.