Python agents

PyTorch Official Implementation of CoRL 2023 Paper: Neural Graph Control Barrier Functions Guided Distributed Collision-avoidance Multi-agent Control

Zero-dep agent workflows with structured approval gates and adversarial review.

Clawforce is the infrastructure for deploying persistent, proactive agent workforces that execute complex workflows, collaborate as teams, and deliver real outcomes — without constant human supervision.

Upload personal docs and Chat with your PDF files with this GPT4-powered app. Built with LangChain, Pinecone Vector Database, deployed on Streamlit

AI Chatbot with Streamlit, Langchain, and Mistral7b

Generate subtitles for all the videos in a folder with OpenAI's Whisper privately in your computer.

Source code for our EMNLP19 paper "Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework"

Fully-local Discord bot with chat, RAG memory, autonomous Discord posts, Bluesky integration, and image generation. Runs against LM Studio + Stable Diffusion OR Flux, with a FastAPI web control panel for live config and monitoring.

A collection of Discord programs to run autonomously

Airbnb Messaging Bot (TOBOT) - AI assistant for Airbnb Hosts

fine-tune Whipser model for Taiwanese speech recognition

OpenAI GPT 接入飞书机器人 无框架依赖

This project aims to combine the latest LLMs, Multi-Step Asynchronous Function Calling, Natural Language Processing, and Text-to-Speech.

One-line for your Flask / FastAPI to generate a frontend 📺

LLM-Blender: Ensembling framework that maximizes LLM performance via pairwise ranking. Employs PairRanker to rank candidates and GenFuser to merge outputs, generating superior responses by combining the diverse strengths of multiple open-source models.

Scientific Document Insight Q/A

A framework for building and testing custom autonomous agents.

AI agent skills for building, operating and troubleshooting Apache Kafka applications. Topic audit, consumer lag, schema review, security, connectors and DLQ

An AI legal workflow running on Claude Code. Four legal agents — each with their own jurisdiction, knowledge base, and MCP tools — collaborate to produce legal opinions with full audit trails.

AI Trading Agent with On-Chain Identity (ERC-8004) — 82.2% OOS Win Rate, Walk-Forward Validated, Kraken CLI Paper Trading

The Hierarchical Intrinsically Motivated Agent (HIMA) is an algorithm that is intended to exhibit an adaptive goal-directed behavior using neurophysiological models of the neocortex, basal ganglia, and thalamus.

MijiaPilot - 小米-米家生态 × MCP × CLI x AI Agent × HomeKit 全桥接家庭智能家居平台。

Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments (EMNLP'2024)

DiscordLangAgent: This is a Discord chatbot built with LangChain. It uses the 'Agents' feature in LangChain to create flexible conversation chains based on user input. The bot can interact with different language models and tools, and supports multiple API endpoints.

Crews Control is an abstraction layer on top of crewAI, designed to facilitate the creation and execution of AI-driven projects without writing code. By defining an execution.yaml file, users can orchestrate AI crews to accomplish complex tasks using predefined or custom tools.

Trade autonomously on Polymarket - PolyAgent. Polymarket Agent.

A simple example of how to implement vector based DDPG for MARL tasks using PyTorch and a ML-Agents environment.

A simple way to write multi agents systems

Code for "Coordinated Exploration via Intrinsic Rewards for Multi-Agent Reinforcement Learning"

This repository contains the code for the paper "A Novel Controller of Multi-Agent System Navigation and Obstacle Avoidance"

DocHarbor: portable multi-agent document retrieval and evidence workflow

Multi-Agent Deep Reinforcement Learning by using Asynchronous & Impala Proximal Policy Optimization in Pytorch with some explanation

（AAAI 2025）MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration

code for the accepted IEEE TITS paper: "Heuristic-based Multi-agent Deep Reinforcement Learning Approach for Coordinating Connected and Automated Vehicles at Non-signalized Intersection"

a peak-calling and differential analysis tool for replicated ChIP-Seq data

Agentic Graph RAG: Skeleton Indexing + VectorCypher + Agentic Router with Self-Correction

This project designs an Android remote control framework based on customized Accessibility Services and HTTP/HTTPS communication, enabling remote device manipulation within a local area network. Furthermore, an AutoGLM-based intelligent agent is integrated to provide a cross-platform Mac UI for high-level semantic control of mobile devices.

This is GitHub Copilot Agent Workshop

Claude Code skill for using Gemini CLI for large-context synthesis, English or zh-TW/CJK long-form drafting, and second-opinion review.

The Smart Marketing Assistant is an innovative project that leverages AI agents to automate tasks within an Instagram marketing workflow. This project aims to streamline and optimize various marketing activities, providing users with a powerful tool to enhance their social media strategies.

Multi-Agent Debugger: An AI-powered debugging system using CrewAI to orchestrate specialized agents that analyze logs, trace code, and uncover root causes across your stack — powered by LLM providers.

Lightweight RAG provenance middleware. Verifies every claim in an LLM response is grounded in a retrieved source - without an LLM call.

AI Coworker that lives in slack

Simple Python audio transcriber using OpenAI's Whisper speech recognition model

TutorAI is a RAG system capable of assisting with learning academic subjects and using the curriculum and citing it. The project revolves around building an application that ingests a textbook in most formats and facilitates efficient learning of the course material.

[CVPR 2025] Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval

Trustworthy question-answering AI plugin for chatbots in the social sector with advanced content performance analysis.

Convert Files / Folders / GitHub Repos Into AI / LLM-ready Files

An AI agent framework which uses hawkinsdb as long term memory

AI-powered book-writing system that converts ideas into full manuscripts in hours with multi-agent collaboration, real-time streaming, and built-in cost control. Tech Stack: FastAPI · PostgreSQL · Redis · Next.js 14 · Tailwind/shadcn · CrewAI · LiteLLM · GPT-5 / Claude / Gemini · Docker · Kubernetes · Prometheus + Grafana · GitHub Actions CI/CD

AI agent skills for Claude Code — video analysis, X/Twitter scanning, Gmail triage, and tweet reading

Repository for CrewAI MCP demo codebase

A prototype of an autonomous agent for garbage collection.

Official repository of the paper "FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning"

GenoTools: Advanced Genotype Data Analysis A robust suite for processing genotype data, offering genotype calling (.idat to PLINK), comprehensive sample/variant QC, and ancestry estimation. Ideal for computational biology and genetics research.

A local predictive experience layer where AI agents turn repeated work into inspectable model cards

Hands-on AI agentic patterns workshop material for building real AI and web apps.

[ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"

An AI chat bot based on volcengine's webRTC protocol.

CLI tool for intelligent Obsidian vault interaction using RAG. Query your notes with natural language and convert URLs to markdown files with AI-powered content extraction.

DevOps-OS is an open-source DevOps automation platform that scaffolds production-ready CI/CD pipelines, Kubernetes configurations, and SRE observability configs — in seconds, from a single CLI command or an AI chat prompt.

Waifu_AI_Vtuber is a AI virtual YouTuber chatbot powered by OpenAI GPT-3.5, interacting in real-time with YouTube live chat and converting responses into Japanese audio using VoiceVox. Create multilingual subtitles and customize character prompts.

An implementation of an Autonomous Vehicle Agent in CARLA simulator, using TF-Agents

Working code repository for the paper "SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction"

built on top of OpenAI Agents SDK

😈 OSINT AI - CHAT << Leak Finder >>

[ACL'26 Main Conference] Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning

The aim of this repository is to simulate a forklift model and to train a Deep Reinforcement Learning agent to control the forklift to achieve various tasks such as autonomous navigation to a pallet placed nearby.

Uses an AI agent (powered by Google Gemini via the Agno framework) to intelligently propose and execute a plan for organizing files within a specified directory on your computer.

🎮 VibeC64 - AI-Powered Commodore 64 Game Creator (BETA)

Orchestrate agents with a peer network of state machines. Supports checkpoint/restore, persistence, and more. BYO cli, or agent, or use flatagents with API. Batteries included.

A simple IM framework based on Satori Protocol. 基于 Satori 跨平台协议的 IM 框架

Unofficial. Splunk MCP server. Implemented in Python and TypeScript/JS. Runs searches, queries Splunk, and outputs data as JSON, CSV, or Markdown for agentic LLM workflows. Includes guardrails for input SPL validation and output sanitization. SSE/stdio transport support. Deployment options: Stdio, local HTTP (SSE), or Docker.

This Guidance demonstrates how to effectively orchestrate multiple specialized AI agents to solve complex customer support challenges through different coordination mechanisms on AWS.

Visual, demo-ready multi-agent orchestration patterns powered by Foundry Local and Microsoft Agent Framework. Six runnable demos with live D3.js graph animations, real-time message tracing, and event replay

[ICLR2026] The official repository for the CodeGym project: "Generalizable End-to-End Tool-Use RL with Synthetic CodeGym"

AI-powered legal chatbot that leverages Retrieval-Augmented Generation (RAG) with DeepSeek R1 for advanced legal reasoning and document analysis. It provides a sophisticated legal assistant that can process and analyze complex legal documents, retrieve relevant information using advanced vector search, and generate nuanced legal analysis.

An agentic system for autonomously generating explainable and reproducible time-series anomaly detection rules using LLMs.

赋予openclaw持久的灵魂：多层次的人格、心跳驱动的日常生活以及不断发展的关系记忆，从而实现栩栩如生的陪伴。openclaw skill that gives agents a persistent soul: layered persona, heartbeat-driven daily life, and evolving relationship memory for lifelike digital companionship.

Advanced-RAG-LangGraph is a Streamlit-based web application that implements an advanced Retrieval-Augmented Generation (RAG) pipeline using LangGraph, ChromaDB, and Tavily to enable interactive document-based Q&A with enhanced retrieval and error-handling capabilities.

AI Helpers — collections of Skills, Hooks, Agents (compatible with Claude Code, Cursor and other tools) and Gemini Gems

[ICLR2026] DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking

Agent skill for fast, cheap market research using LLM synthetic surveys + Semantic Similarity Rating (SSR). No API keys needed.

Local-first hybrid semantic code search tool. Indexes codebases into PostgreSQL with pgvector embeddings via Ollama, combines vector similarity + keyword search with RRF fusion. Supports 30+ languages. Features CLI, MCP server, WEB dashboard and interactive REPL.

Agentic Memory for Claude Code

An AI-powered agent utilizing LLMs (e.g., Claude) with Function Calling to automate tasks in Blender. Enhances workflow efficiency by integrating intelligent command execution and automation. 🚀

🚀 Experimental AI demos showcasing Amazon Bedrock, open-source LLMs & creative possibilities. AI Agents, RAG systems, streaming agents & more!

[CVPR 2026] Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation

A research framework for evaluating proactive AI assistants through active user simulation

Framework for building continuous-loop autonomous AI agents.

Robinhood portfolio advisor skill for Hermes Agent, OpenClaw, Claude Code, Codex, and other MCP-compatible AI agents

Terminal-native AI assistant built specifically for Termux and Android development.

将自然语言描述的 COMSOL 建模需求自动转换为完整 .mph 模型文件的智能 Agent，支持几何、物理场、网格、研究与求解的完整仿真流程。

A FastAPI-powered workflow orchestration system that integrates LangGraph to design, run, and manage AI Agents workflows

Agent2 is a self-hosted, browser-based autonomous AI agent powered by aaravprogrammers that combines a coding assistant, real terminal access, security testing tools, persistent memory, and a workspace system into a single unified interface.

PDBe MCP Servers integrate Protein Data Bank Europe resources with LLMs via Model Context Protocol. Provides seamless access to protein structure data through API tools and graph database schema assistance for intelligent Cypher query generation, bridging structural biology and AI research.

Official code for "Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate" (arXiv:2605.01347).