Python agents

《Harness工程：从上下文管理到Agent系统构建》书籍配套代码

This is the official repository for our paper "Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning" published in ICRL 2026.

Reimagining Agent-based Modeling with Large Language Model Agents via Shachi

[ACM MM 2026] MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments

A harness framework for building domain-specific agents, the worked finance instance that beats every frontier model on public benchmarks, and the autonomous loop coordinator that drives 100-experiment optimization runs unattended.

Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligent file conversion (PDF/Office/images), and semantic search. Includes MCP server for seamless AI assistant integration.

Multi Agent for Business Automation is a multi-agent orchestration platform for business automation and decision support. It coordinates specialized AI agents—each with distinct roles, personalities, and tools—through LangGraph workflows, shared memory, and human-in-the-loop (HITL) approval gates.

Email gateway that opens a Claude Code session per inbound AgentMail message (cmux or Ghostty)

Your codex login → a full ChatGPT Plus/Pro account (every model, deep research, image gen, code exec) inside Claude Code, Codex & any MCP client. One-line install.

Vibe CSA (Code Security Audit)，是一款基于 AI Agent 架构的代码审计工具，采用多 Agent 并行执行架构，用“上帝视角”静态审计源代码，用“实战模拟”动态验证漏洞，保证了 Web 漏洞挖掘的全面性和准确性，输出稳定可靠的安全报告，并提供可落地整改建议。

A platform for running AI agents on realtime sport data and make predictions about game outcomes.

Run your Mac with your voice — gpt-realtime-2 + agent-desktop. Clone it and teach your agent any app.

🤖 零基础 AI 学习之路 | 30 天从小白到实战 | Python → 机器学习 → 深度学习 → Agent应用 → 项目实战 一个完整的 AI 入门教程，包含： 📚 30 天系统教程（费曼学习法·大白话讲解） 💻 9 个完整项目（图像分类·文本生成·目标检测·模型部署·AI客服·数据分析·智能投研·RAG·AutoGPT） 🎯 200+ 代码示例（可直接运行） 🆓 完全免费开源（MIT 许可证） 📖 配套教程：CSDN专栏 https://blog.csdn.net/m0_67081842 ⭐ 如果有帮助，欢迎 Star 支持！

Strands-based agents and harnesses for agentic benchmarks.

gradio mcp multi-agent research code-generation ai-assistant python web-search

transformers safetensors qwen2 text-generation code chat

transformers pytorch llama text-generation facebook meta

docker region:us

Telegram bot that answers questions over your PDFs using retrieval-augmented generation (LangChain + FAISS).

Red Hat Ecosystem Engineering - Agentic Collections

My personal agent skill repository, primarily focused on game development.

Official code for the paper "A New Role for Relevance: Guiding Corpus Interaction in Agentic Search"

The easiest way to manage semantic versioning and generate CHANGELOG.md automatically for AI-native projects.

[ICML 2026] Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks

这是一个专为 AI Agent（如基于大语言模型的编程助手）设计的 STM32 调试技能包（Skill）。它封装了常用的 STM32 固件编译、烧录、调试、寄存器查看以及变量实时监控功能，旨在让 AI 助手能够无缝、高效地协助开发者进行 STM32 嵌入式开发。

The Research Playground for the RLMSs and Coding Agents

Memory is a long-term memory module for AI agents, providing capabilities for memory extraction, storage, retrieval, and migration for agents running on the openJiuwen framework.

Automated optical design agent skill for Ansys Zemax OpticStudio via ZOS-API — AI-driven requirements parsing, lens modeling, staged optimization, and design reporting.

The elite design intelligence layer for AI agents, synthesized from 10+ legendary design books. It primes your AI with the collective strategic wisdom of master designers to generate high-intent UI/UX with zero "schtick."

Open-source framework for computer use agents: VeriGen verifiable task synthesis, online RL training (AgentRL), and OSWorld/ScienceBoard evaluation.

FTShare Agent Skills for financial data and investment research workflows｜金融数据 Skill 与投研业务 Skill 仓库。

Pixel-art virtual office for Hermes Agent — watch your agents work as animated pixel characters

Interactive CLI/domain learning agent for 5-12 day practical business execution.

Opensource benchmark evaluating web operators/agents performance

Local RAG as a simple CLI, for standalone use or as a gptme tool

Context-aware Open AI chatbot for Telegram using aiogram-3.

Explore Multiple Vector Databases and chat with documents on Multiple LLM models, private LLM models

An open-source agent toolkit that auto-syncs SDK versions, docs, and examples—built for seamless integration with LLMs, and AI agents ( MCP compatible).

Code for the paper "MARL-iDR: Multi-Agent Reinforcement Learning for Incentive-based Residential Demand Response"

A land use model based on Cellular Automata and Agent-based modelling.

Generate ATT&CK Navigator layer file from PowerShell Empire agent logs

A user-customized bot for your slack channels using LLMs, Tools and Documents

Designed for offline use, this RAG application template offers a starting point for building your own local RAG pipeline, independent of online APIs and cloud-based LLM services like OpenAI.

Teach ChatGPT the Alda music programming language, show it some superb code, and consult with it to compose a melody.

DaveLovable The Most Advanced Open-Source AI Web Development Platform Build React applications at lightning speed with AI-powered multi-agent orchestration

Performing a RAG (Retrieval Augmented Generation) assessment using voice-to-voice query resolution. Provide the file containing the queries, ask the questions, and receive the results via voice.

Simple chatbot using Rasa.ai

久远：一个开发中的大模型语音助手，当前关注易用性，简单上手，支持对话选择性记忆和Model Context Protocol (MCP)服务。 KUON:A large language model-based voice assistant under development, currently focused on ease of use and simple onboarding. It supports selective memory in conversations and the Model Context Protocol (MCP) service.

This repository contains a web application designed to execute relatively compact, locally-operated Large Language Models (LLMs).

ChatGPT IRC bot

Anonymous chat bot telegram bahasa indonesia

Generate captions for videos using the power of OpenAI's Whisper API

A utility that leverages GPT-4o to rename image files based on their content

Personal collection of Claude skills - growing as I discover patterns and solve real-world problems

Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)

🎯 Your free LLM evaluation toolkit helps you assess the accuracy of facts, how well it understands context, its tone, and more. This helps you see how good your LLM applications are.

Lighter, cheaper and faster RAG toolkit (Graph RAG) supported by TargetPilot

Sample agents for Enterprise RAG Challenge 3: AI Agents in Action

A policy runtime for AI agents.

A full-stack EdTech system for generating, auditing, and managing outcome-aligned assessment questions using Bloom’s Taxonomy, featuring a FastAPI backend, PostgreSQL persistence, and a React-based dashboard.

Bring Claude's Skill system to any MCP-compatible AI agent through progressive disclosure. Universal, standards-based, and easy to use.

A powerful AI agent for browser-based interactions powered by Fireworks AI models. Navigate the web, extract content, analyze websites, and provide intelligent feedback based on what it sees. Features web navigation, content extraction, SEO analysis, and an interactive UI leveraging high-performance vision and language models.

Automate user story creation, in a format suitable for AI agents.

A short set of exercises that showcase the usage of autogen to create agents

PyTorch implementation of the paper: Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning.

MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection

Checkmk special agent for checking unifi controller

The game snake (for playing by yourself run snake_env.py). Deep Reinforcement Learning agent learns to play the game (run agent_1.py)..

NAIL is an agent that plays text-based interactive fiction games.

Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

Lumigo's Python Distributed Tracing and Performance Agent for AWS lambda

Generate CS2 signatures via Agent SKILLS with ida-pro-mcp

Agent for scheduling event generating processes and sending the results to Riemann

Code of the NeurIPS 2021 paper: Language and Visual Entity Relationship Graph for Agent Navigation

The resources for EMNLP-20 paper 'Profile Consistency Identification for Open-domain Dialogue Agents'

PGR is an experimental, stateless MCP code-search server for studying how ranking, latency, and output shaping affect agentic search.

OpenAI-compatible proxy for assistant-ui.com free LLM endpoint. Supports streaming, tool calling, vision, and 5 models.

AI-powered post-consume script for Paperless NGX that generates high-quality, language-aware document titles using OpenAI, Claude or local Ollama models.

This repository hosts a collection of custom web applications powered by OpenAI's GPT models (incl. o1, o3-mini, GPT-4.5, GPT-4o, and GPT-4o mini), Whisper model, and TTS model. These apps include an interactive chatbot ("Talk to GPT") for text or voice communication, and a coding assistant ("CodeMaxGPT") that supports various coding tasks.

HealthFlow: Automating electronic health record analysis via a strategically self-evolving multi-agent framework

Utilizing a LINE Bot integrated with LangChain in Python to assist with stock price inquiries.

Makes a improved prompts from a basic prompt

This repository provides a minimal, single-file implementation of SingLoRA (Single Matrix Low-Rank Adaptation) as described in the paper "SingLoRA: Low Rank Adaptation Using a Single Matrix" by Bensaïd et al.

[T-Cyber 2020] Cooperative Pursuit with Multi-pursuer and One Faster Free-moving Evader

Microsoft chatbot build using NLTK-Chatbot and django

Automate PR reviews with LLMs like OpenAI GPT and Google Gemini. Supports multilingual reviews, file exclusions, and custom model selection. Simple setup, smarter code reviews!

Multi-agent pipeline for automated SEC 10-K / 10-Q investment research

一个用于获取B站视频内容便于 Agent 解析的 SKILL

Code for sim-to-real transfer of a pretrained Vision-and-Language Navigation (VLN) agent to a robot using ROS.

PoC for a Havoc agent/handler setup with all C2 traffic routed through GitHub. No direct connections: all commands and responses are relayed through Issues and Comments for maximum stealth.

One prompt. Full delivery.

🔥 AI 投资复盘系统 | 温度计量化估值 | A股/港股/美股 | 从拍脑袋到有体系

Code repository for the NAACL 2025 paper "LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models"

AI Agent leveraging symbolic reasoning and other auxiliary tools to boost its capabilities on various logic and reasoning benchmarks. This project aims to develop a robust and flexible AI system that can tackle complex problems in areas such as decision-making, mathematics, and programming.

My version of an LLM Websearch Agent using a local SearXNG server because SearXNG is great.

Repository containing RL environment, model and trainer for GNN demo for ICRA 2022 paper "A Framework for Real-World Multi-Robot Systems\\Running Decentralized GNN-Based Policies"

livekit agent plugins

MongoDB Agents with Google ADK

MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning