Python agents

A reusable, open-source AI infrastructure designed for communities and organizations. It understands structured data, processes official announcements, and answers questions accurately by centralizing important information.

🎬 AI-powered localhost subtitle generator for hearing-impaired users. Automatic speech recognition using OpenAI Whisper + Intel OpenVINO. Supports 99 languages, torrent downloads, and online video playback.

A modified version of SalesGPT with the addition of TTS, STT, and Twilio to make calls. A Context-aware AI Sales Agent to automate sales outreach

Model Context Protocol (MCP) server for Databricks that empowers AI agents to autonomously interact with Unity Catalog metadata. Enables data discovery, lineage analysis, and intelligent SQL execution. Agents explore catalogs/schemas/tables, understand relationships, discover notebooks/jobs, and execute queries - greatly reducing ad-hoc query time.

Multi-strategy RAG system achieving 74% Recall@10 on MultiHop-RAG. Combines RAPTOR hierarchical retrieval, knowledge graphs, HyDE, BM25, and Cohere neural reranking.

A skill that teaches LLM agents how to use rope for python codebase refactors

AMLP integrates dataset creation, input/output handling, and analysis for machine learning interatomic potentials. It supports Gaussian, VASP, and CP2K, with LLM agents for code selection and ASE-based AMLP-Analysis for molecular simulations and validation.

Generate conversational, tool-calling, structured-output, and preference datasets — easily and at scale

Understand how CLI AI agents work and use your own local CLI AI! Easy to understand, written in python, built on Ollama/OpenAI compatible APIs.

Agent Alchemy is a curated collection of plugins, apps, and extensions designed to elevate your agentic engineering workflows. Built for Claude Code and other AI coding agents, these tools help developers work smarter and ship faster.

OpenAPI to MCP Server Code Generator

Playbooks for RunMaestro.ai Agent Orchestrator

Minimalist AI agent that fixes itself when things break.

A Python framework for building proactive LLM agents that simulate human-like cognitive processes. Enables agents to continuously generate and evaluate thoughts in parallel with conversations, and autonomously determining when and how to engage.

AI-powered web tool that automatically finds and generates highlight clips from your videos.

An Autonomous Curriculum Reinforcement Learning framework that steers agents to continually learn in specific environments with zero human data.

JarvisV3 is a Streamlit-powered AI assistant inspired by Iron Man’s Jarvis. It offers both text and realtime audio interactions using OpenAI’s API, with customizable settings including dynamic voice selection and optional function calling.

An agent framework for building and evaluating general digital agents.

Scan GitHub for exposed Anthopic API Keys

AI-native IDA Pro kernel — unrestricted IDAPython over JSONL, persistent sessions, zero dependencies. Let your agent drive IDA, not call tools.

Specification 1 (hierarchical style) for an agentic software development crew, for implementation with mainstream Agentic platforms like Claude Code, Strands, etc.

MCP server for AI agents to analyze Excel spreadsheets through atomic operations. Like SQL for Excel. Fast, accurate, and efficient. No context overflow.

智能体系统设计与实战：基于langchain与langgraph，Agent System Design and Practical Applications: Based on LangChain and LangGraph

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

Ship AI agents with guardrails — not prayers. Self-hosted runtime protection for LLMs and tool-calling agents: block prompt injection, enforce tool permissions, redact sensitive data, and control what agents are allowed to do.

World's First Autonomous Open-source AI Employees Platform

Open-source legal AI agent skills for PKULaw, citations, and DOCX workflows

VoidClaw is a universal autonomous AI command centre that runs seamlessly on Windows, Mac, Linux, and Android. It acts as a local-first digital assistant that manages your files, automates web tasks, and controls your devices with an evolutionary memory that adapts to your unique workflow.

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

This repository consists of agentic ai usecases.

SoccerLab is designed for developing, training, and deploying advanced control strategies for legged robots in a dynamic, multi-agent soccer environment.

Code for "Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems"

A step by step implementation to build an agent that runs for week to complete a task and self improve.

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"。

本地化个人理财助手 — A股/基金/理财/现金/数字资产/机器人全资产看板 + 市场AI问答 + 个股K线盘口详情 + 板块对比 + 早盘信息简报 + 资讯AI解读。只给客观信息，不荐买卖。

让 Claude Science 一键接入 DeepSeek、硅基流动 Kimi、OpenAI 等第三方 API 的 macOS 本地代理与安装器

Multi-agent remote dashboard for Claude Code, Copilot, and Codex. Approve permissions, answer questions, and monitor token usage in real-time from a GeekMagic screen, Android widget, GNOME Shell, or VS Code.

gradio tool region:us

gradio region:us

transformers onnx safetensors llama text-generation gpt

transformers safetensors llama text-generation conversational arxiv:2403.04652

transformers safetensors mixtral text-generation merge moe

transformers pytorch codegen text-generation arxiv:2203.13474 license:bsd-3-clause

transformers safetensors qwen3_moe text-generation abliterated uncensored

A machine-native, empirically-ranked resolution graph for autonomous agents.

Full-stack RAG application — OpenAI, Pinecone, Flask, React — and the tutorial series that builds it end to end.

Intellectual property data tools for AI agents

移动端 AI 自动化测试平台 —— MCP 工具 + AI Agent + 可视化操控台

Non-destructive local file maps and instant search indexes for AI agents

Agent-driven SAP/ABAP knowledge base engine that turns S/4HANA custom objects into citable Markdown/Obsidian context for humans and AI agents.

A debugging framework for agentic AI systems: diagnose failures, attribute root causes, recover with evidence, and validate fixes through reruns.

Talk to anyone: /coach persona plugin for Claude Code — research any public figure from their YouTube + web, then talk to them

Preserve knowledge, sustain wisdom forever.

AdCraft — 首个面向营销广告的 Agentic 视频制作平台。无限画布 · 拉片复刻 · 全流程自动化，从创意到成片一站直达。AdCraft — The first agentic video production platform for marketing and advertising. Infinite canvas · shot-by-shot replication · fully automated, from idea to final cut.

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

Interactive Sandboxes for AI Agent Evaluations & Reinforcement Learning on 3rd party APIs (Slack, Linear, Box, gCalendar)

AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence

An AI code agent that can make patches inside an isolated Docker sandbox

Sync reMarkable to PDF and MarkDown via either USB or Wifi. Backup your device and let your AI agents reason over the content.

An autonomous agentic harness for Kubernetes. Proactive fleet audits, declarative GitOps remediation, and ChatOps in one place.

A YouTube analytics tool for trend, sentiment, and suitability insights.

An easy-to-use reverse engineered text to image generation Python API wrapper for Lexica.art

Let’s build a curated Knowledge Graph based on the collective wisdom of 260+ experts

Multi-agent RL algorithms are applied to large-scale cooperative target searching mission

Turn domain experts into production AI agents.

Composable Python framework for LLM agent workflows focused on simplicity and developer experience. We ❤️ OSS.

Analyse environmental, social, and governance policies for potential gaps using AI - powered by LLMs, RAG techniques, and a regulatory knowledge base using OpenAI API, LangChain, Pinecone and Streamlit.

Ask question over your Notion Database! A naive Retrieval-Augmented Generation (RAG) pipeline backed by Langchain and Streamlit

Unit tests for plain text - LLM as a copy editor

🚀 LLM-I: Transform LLMs into natural interleaved multimodal creators! ✨ Tool-use framework supporting image search, generation, code execution & editing

By calling FirewaLLM, users can ensure the accuracy of the large model while greatly reducing the risk of privacy leakage when interacting with it. We believe that FirewallLLM is a privacy protected chatgpt interaction platform.

Build conversation Seq2Seq models with TensorFlow

Build a chatbot using deep learning techniques. The chatbot will be trained on the dataset which contains categories (intents), pattern and responses. We use a special recurrent neural network (LSTM) to classify which category the user’s message belongs to and then we will give a random response from the list of responses.

The Google Reviews Chatbot fetches reviews via the Google My Business API, analyzes sentiments using GPT-3, and generates tailored responses. Deployed on AWS, it uses Elastic Beanstalk, EC2, and ElastiCache for Redis to run tasks on a schedule, ensuring seamless and efficient chatbot functionality.

A demo of fine tune Stable Diffusion on Pokemon-Blip-Captions in English, Japanese and Chinese Corpus

🤖 Boost automation in your Camunda processes using task-specific AI connectors

Human-supervised AI code generation using Plan-Do-Check-Act methodology with TDD and refactoring. Works as Claude Code skill or standalone prompts.

Dynamic Shell Command MCP Server

Open WebUI + LangGraph AI Agents with Python Executor and Postgres Database

A standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs. It enables AI agents to run autonomously in cloud environments and interact with various systems securely.

Security measure for agentic LLMs using a council of AIs moderted by a veto system. The council judges an agent's actions outputs based on specified categories.

AI (A2C agent) mastering the game of Snake with TensorFlow 2.0

TradeAgents is an AI-powered framework for simulating market interactions, integrating economic principles with intelligent agent design.

Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 which was presented at RSA San Francisco 2024.

将任意线上网站的设计风格提取为一份结构化 `DESIGN.md`。本 skill 是 design-extractor Chrome 扩展的命令行 / AI Agent 移植版。

A collaborative organization system for Claude Code. Architecture over memory, build an "attractor basin" that lets any Claude instance orient quickly and collaborate at depth. Includes hooks, agents, principles, and guided onboarding for human-AI partnership.

[AAAI 2025 𝐎𝐫𝐚𝐥] MuMA-ToM: Multi-modal Multi-Agent Theory of Mind

The code for paper, "Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration", NeurIPS 2021.

cordial-sync is a software package than can be used to reproduce the results from the paper "A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks”

Implementation of routing using multi-agent deep reinforcement learning

Provides per-subagent MCP access controls to Claude Code (or any MCP client) across all your MCPs and prevents context window bloat. Loads only 3 tools instead of all your MCP Server's tool definitions. Agents discover tools on-demand, only when needed. Control which servers and individual tools each agent/subagent can access.

Leveraging LLMs for modernization through intelligent chunking, iterative prompting and reflection, and retrieval augmented generation (RAG).

Command Line telepathy. An Autonomous Al Agent for your Terminal that turns intent into Execution (Windows/Linux/Mac)

Open domain persona-aware dialogue generation

Framework for deploying configurable AI agents with real-time streaming and tool execution.