Python agents

Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253

Hermes Agent made portable desktop for Windows — 100 tools, GUI, local models via LM Studio, TTS, Music, ComfyUI, workflows, tool maker. No install. No Docker. No admin rights.

本地化 AI 小说精修工作台🚀。内置 RAG 长时记忆🧠、三模态协作（作家/主编/助手）🖋️、卡片流式编辑器⚡。支持酒馆卡导入、全书自动化精修与扩写🎭。AI小说加料 小说精修 AI文本修改 小说扩写 小说总结

An LLM-based agent that will install the tools it needs.

🏆 gym-cooking: Code for "Too many cooks: Bayesian inference for coordinating multi-agent collaboration", Winner of the CogSci 2020 Computational Modeling Prize in High Cognition, and a NeurIPS 2020 CoopAI Workshop Best Paper.

MobileUse: an open-source mobile GUI agent for Android phone automation, AndroidWorld/AndroidLab evaluation, hierarchical reflection, and proactive exploration.

Open-source MCP server that lets an AI drive a live session of Altium Designer, and optionally KiCad or EasyEDA Pro, editing the open design in place while you watch. 300+ tools: schematic, PCB, library and project automation, design review, audits, rendering, auto-placement, panelization, autonomous design-plan executor. Apache-2.0.

🎬 Turn any topic into a finished Vox-style paper-collage explainer / motion graphics video — script, collage keyframes, animation, voice-over, music & captions, all automated. An agent skill for Claude Code, Codex & other coding agents.

Give your AI agent a phone number: order a private number in 200+ countries over the API, read the SMS verification code, hand the number back. The widest country coverage in the category, checkable with one API call.

AI-native SaaS framework that builds full-stack apps using autonomous AI agents

Gemini PDF Chatbot: A Streamlit-based application powered by the Gemini conversational AI model. Upload multiple PDF files, extract text, and engage in natural language conversations to receive detailed responses based on the document context. Enhance your interaction with PDF documents using this intuitive and intelligent chatbot.

BondAI is an open-source tool for developing AI Agent Systems. BondAI handles the implementation complexities including memory/context management, error handling, vector/semantic search and includes a powerful set of out of the box tools and integrations.

An AI-powered storytelling video generator that takes user input as a story prompt, generates a story using OpenAI's GPT-3, creates images using OpenAI's DALL-E, adds voiceover using ElevenLabs API, and combines the elements into a video.

Библиотека по разработке чат-ботов для мессенджера MAX

The definitive benchmark for AI agents on OpenClaw. 45 tasks across 4 tiers. Powered by MyClaw.ai

A desktop for AI agents

TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems

Red Teaming python-framework for testing chatbots and GenAI systems.

[ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use

Python library for building with LLMs. One interface across 11 providers (OpenAI, Anthropic, Gemini, DeepSeek, Ollama and more), automatic failover, Pydantic-validated structured output, embeddings with vector search, and an AI-powered router. pip install simplerllm

适用于 Claude Code / Agent 的论文写作 Skill (论文.SKILL)。涵盖论文内容、数据库ER图、整体流程图生成。针对本科论文进行aigc率降低、降重的优化，助力毕业设计高质量生成。

An agentic framework that helps developers build resilient agentic systems

Turn existing CAE files into structured text an agent can use — COMSOL, Abaqus, Fluent, HFSS, Icepak, FloTHERM — plus solver detection, script linting, and live solver sessions. Strong coverage for electronics thermal and advanced packaging.

Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.

为小红书 AI 工具实操内容生成稳定、干净、精致封面的 Claude / Codex Skill（脚本模式 + Agent 自主执行）

transformers gguf code codeqwen chat qwen

`xxg-portrait-rebuild-light` is an image-edit skill for existing portrait photos. It reconstructs the key light, fill, shadows, and background atmosphere with a director-led lighting workflow while restoring clean, healthy, low-contrast photographic skin microtexture.

Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents.

Open Source AI Tracing Framework built on Opentelemetry for AI Applications and Frameworks

[ICLR'26] Stronger-MAS: A RL Framework for multi LLM agent system; [arxiv] MetaAgent-X: End-to-End Reinforcement Learning Automatic Multi-Agent Systems

Realistic examples of building evals and optimizing agents with Harbor

OpenClaw 深度研究 Obsidian 知识库 | 351 篇笔记 · 3250+ 双链 · 100 张配图 · 9 大主题 | AI Agent 最全中文知识图谱

ZhiJuTong (ZJT) is an AI-powered, open-source platform specifically designed for creating professional short dramas. It automates the entire production pipeline, from script and storyboard creation to final video synthesis

transformers safetensors gemma text-generation license:gemma text-generation-inference

本地优先的全栈 AI 创作工作站：AI对话 · AI漫画 · 漫剧创作 · 写作台 · 知识学习五大模块；vLLM / llama.cpp / Transformers 多引擎本地推理，显存智能调度、舱壁隔离自愈、仅供学习使用，欢迎交流指正。

Tiny toolkit for air-gapped LLMs on consumer-grade hardware

A multi-step reasoning pipeline powered by the Datarus-R1-14B-Preview model

A practical agent skill pack for DevOps work in Claude Code and Codex.

Multi-Agent Adversarial Inverse Reinforcement Learning, ICML 2019.

MrlX: A Multi-Agent Reinforcement Learning Framework

Low-code/no-code python library that transforms plain English instructions into fully configured multi-agent AI teams

[NeurIPS 2025 & ICLR 2025 Financial AI Best Paper Award] A multi-agent framework that leverages LLMs to simulate socio-economic systems

Hardware testing for the software world. Real or virtual, local or remote, human, automated or agentic.

AI-assisted Lean project automation with DAG blueprints, proof orchestration, and multi-agent coding/proving workflows.

数据分析智能体 (Data Analysis Agent)：基于LLM的智能数据分析智能体

LambChat — Enterprise Agent Infra for governed AI agents. Skills + MCP powered, Loop Agent ready, multi-tenant by design.

A New End-to-end Framework for Evaluating Voice Agents

Agent Skill that analyzes your repo and generates the AI-ready configuration coding agents need — AGENTS.md, copilot-instructions, CI, issue templates, and more. Works in Claude Code, GitHub Copilot, Codex, and Cursor.

Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy

Enterprise-grade fast-response Agent framework.

transformers safetensors text-generation chat cogvlm2 conversational

Pydantic extension for annotating autocorrecting fields.

Self-hosted AI agent orchestration service controlled via Telegram, Discord, or Slack.

World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociation) + a Cannes Lions evaluation engine, powered by a library of 571 legendary award-winning cases.

aimy-skill 是一个轻量级、可嵌入 AI Agent 的渗透测试辅助技能，专为授权环境下的自动化信息收集和基础漏洞探测设计。它可以被 AI 助手（如 AutoGPT、LangChain 应用）调用，也可以独立命令行运行。

A local, multi-agent workspace designed like a messenger-style app. You can add custom teammates and chat with them individually, or create group chats and choose exactly which teammates to include. The whole experience feels like a familiar messaging app—but with much more powerful multi-agent collaboration capabilities.

OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.

This software contains an agent based on LangGraph & LangChain for solving general requests in the Whatsapp channel of this medical clinic

Efficient Large-Scale Fleet Management via Multi-Agent Deep Reinforcement Learning

Persistent memory for AI coding agents

PowerMCP is an open-source collection of MCP servers for power system software like PowerWorld, PSSE and OpenDSS. These tools enable LLMs to directly interact with power system applications, facilitating intelligent coordination, simulation, and control in the energy domain.

[KDD 2026] MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation

transformers safetensors qwen2 text-generation chat conversational

static trackio open-reproductions icml2026 agent-collab region:us

Open measurement infrastructure for AI agents. Our audit of 124 usage tools found 45+ verified billing bugs — 19 fixes landed upstream. Conformance fixtures for token accounting: PASS / FAIL / UNPROVABLE in CI.

Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses

Official code for NeurIPS2025 "Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers"

GPT-4 level function calling models for real-world tool using use cases

PocketGroq is a powerful Python library that simplifies integration with the Groq API, offering advanced features for natural language processing, web scraping, and autonomous agent capabilities. Key Features Seamless integration with Groq API for text generation and completion Chain of Thought (CoT) reasoning for complex problem-solving and more.

Team fight tactics AI

Custom TTS component for Home Assistant. Utilizes the OpenAI speech engine or any compatible endpoint to deliver high-quality speech. Optionally offers chime and audio normalization features.

This is the official companion repository for the book The Complete LangGraph Blueprint: Build 50+ AI Agents for Business Success. The repository provides source code, practical examples, and resources to help you build dynamic AI agents using LangGraph, a cutting-edge graph-based framework for artificial intelligence workflows.

Security operations toolkit for AI coding agents. Give Claude Code 25+ skills to catch vulnerabilities, scan containers, detect secrets, and enforce policies automatically.

Agent-native PowerPoint manipulation — one CLI lets AI agents inspect, edit, create, and verify .pptx files through atomic JSON patches. Packaged as an Agent Skill.

AI Trading Agent for Everyone

A background agent system for automating end-to-end software engineering tasks, direct from your github repos.

Chat application with multi-agents system supports multi-models and MCP

OpenAI-Compatible Proxy Middleware for the Wyoming Protocol

A unified interface for various AI model providers

[EMNLP '26] Dependency-Aware Structural Retrieval for Massive Agent Skills

Demonstrate once, execute anywhere — secure remote skills for AI agents.

transformers safetensors llama text-generation conversational arxiv:2403.04652

A workspace and framework to build domain-specific systems for agentic knowledge work.

Deep research agents using MiniMax M2.1 interleaved thinking

PDF解析（文字，章节，表格，图片，参考），基于大模型(ChatGLM2-6B, RWKV)+langchain+streamlit的PDF问答，摘要，信息抽取

Official Implementation of Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization

Level-based Foraging (LBF): A multi-agent environment for RL

An implementation of a computer use agent (CUA) using LangGraph

這是一個專為影片字幕處理設計的 AI Agent Skills 集合，提供從音訊轉字幕、優化字幕、設計字卡到生成社群媒體摘要的完整工作流程。

CogniDB is a Python-powered Natural Language to SQL interface that enables users to query databases like MySQL, PostgreSQL, MongoDB, and AWS RDS using plain English. It parses questions, understands schema, generates safe SQL, and returns results, empowering non-technical users to gain database insights without writing SQL.

Edge-cloud Multi-Agent execution framework for embodied intelligence, connecting AI agents to real devices with verifiable actuation and entropy-bounded recovery.

Speculative programmatic tool calling (sPTC) for harnesses like RLM, CodeAct, etc.

Open-source, license-free MCP server for RTL waveform debug: reads FST waveforms (VCD/FSDB auto-convert) plus a SystemVerilog netlist, with 34 tools covering driver analysis, value/X tracing, pass-fail waveform diff, a browser wave viewer the agent drives, and pre-simulation static analysis.

Official code for paper "Learning to Use Tools via Cooperative and Interactive Agents"

The Google Ads MCP Server is an implementation of the Model Context Protocol (MCP) that enables Large Language Models (LLMs), such as Gemini, to interact directly with the Google Ads API.

Seamlessly integrate with OpenAI's ChatGPT plugins via API (or client), offering the same powerful functionality as the ChatGPT api + plugins!

Generate images by Stable-Diffusion-webui Based on Python | 使用Python的基于 SD-webui 的画图机器人（支持中文、Novelai和Naifu）

DaVinci - The ChatGPT AI Virtual Assistant

Practical setup guides and helpers to connect Burp Suite MCP Server to multiple AI backends (Codex, Gemini, Ollama, ...).

OpenAI's Structured Outputs with Logprobs