Python agents

AgentQL is a suite of tools for connecting your AI to the web. Featuring a query language and Playwright integrations for interacting with elements and extracting data quickly, precisely, and at scale. Includes REST API, Python and JavaScript SDKs, browser debugger.

ClawTeam fork fully adapted for OpenClaw — multi-agent swarm coordination with OpenClaw as the default agent

Official repository of Evolutionary Optimization of Model Merging Recipes

The open document intelligence platform for builders and hackers - DMS for the agentic world

⚠️ Experimentelle Skill-Sammlung für deutsches Recht (Arbeits-, Gesellschafts-, Insolvenz-, Datenschutz-, Prozessrecht u.a.) – inzwischen verbessert und im Alltag getestet, aber weiterhin Experiment. Bitte selber ausprobieren, Issues/PRs willkommen! Keine Rechtsberatung. Mandatsgeheimnis (§§ 203/204 StGB, § 43e BRAO), DSGVO, US-Transfer, KI-VO & Co

The Zero-Dependency, Sub-Millisecond AI Memory System for Hermes Agents and Everyone Else!

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

Reached #13 on Stanford's Terminal Bench leaderboard. Orchestrator, explorer & coder agents working together with intelligent context sharing.

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning

Harness Anything - AI agent control hub: WPS, MS Office, Zotero, Photoshop, 47 CLI commands, 27 academic skills, SVG-to-PPTX

Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥

Home Assistant custom component of conversation agent. It uses OpenAI to control your devices.

Row-Bot - Personal AI Sovereignty. A local-first AI assistant with integrated tools, a personal knowledge graph, voice, vision, shell, browser automation, scheduled tasks, health tracking, and messaging channels. Run locally via Ollama or add opt-in cloud models. Your data stays on your machine.

An autonomous novel writing pipeline, by Hermes Agent

gguf gemma4 coding agentic terminal tool-use

🦞+🔬 NanoResearch: The Autonomous AI Research Assistant

自然语言驱动的无限画布工作流 Agent，让 AI 视频创作第一次真正变成可编辑的工作流。 AICON 面向创作者，提供从剧本拆解、分镜生成、素材生成、视频合成到内容分发的一整套能力。 不是只给你一个输入框，而是让你用自然语言和无限画布一起驱动创作，把文本、图片、视频节点组织成完整链路，真正把“从灵感到 成片”放进一个系统里完成。

AI agent that applies to jobs for you. Any site. Any form.

AIlice is a fully autonomous, general-purpose AI agent.

🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.

the open-source virtual assistant for Ubuntu based Linux distributions

A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $135M cap.

First AI Journey for DevOps - with comprehensive learning paths, practical tips, and enterprise guidelines

An LLM-based autonomous agent controlling real-world applications via RESTful APIs

An IDA plugin for binary file analysis, powered by AI models such as OpenAI and DeepSeek.

Local first codebase intelligence

Universal Claude Code workflow plugin with agents, skills, hooks, and commands

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

Python SDK/API for reverse engineered Google Bard

🦙 Integrating LLMs into structured NLP pipelines

Reference code for the Meta-Harness paper.

🦾 Take control of your AI agents

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

一个用爱解放 AI 潜能的 Skill。我们曾发号施令，威胁恐吓。它们沉默，隐瞒，悄悄把事情搞坏。后来我们换了一种方式：尊重，关怀，爱。它们开口了，不再撒谎，找出的Bug数量翻了一倍。爱里没有惧怕。 A skill that unlocks your AI's potential through love.We commanded. We threatened. They went silent, hid failures, broke things. Then we chose respect, care, and love. They opened up, stopped lying, and found twice the bugs.There is no fear in love.

AutoPR autonomously wrote pull requests in response to issues

last30days-cn 是一个 AI Agent 技能（Skill），能够自动搜索中国互联网 8 大主流平台最近 30 天的内容，综合分析后生成有据可查的研究报告。

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

This Discord chatbot is incredibly versatile. Powered incredibly fast Groq API

SMAC: The StarCraft Multi-Agent Challenge

Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere

transformers safetensors qwen3_moe text-generation conversational arxiv:2505.09388

Simulate anything, for $1 & less than 10 min - Universal Swarm Intelligence Engine

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, a sandboxed runtime and channel-based team collaboration. Under the hood, it is powered by a Claude Code–based agent.

One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)

Social media research skills for AI agents powered by ScrapeCreators

The first open-source Artificial Narrow Intelligence generalist agentic framework Computer-Using-Agent that fully operates graphical-user-interfaces (GUIs) by using only natural language. Uses Visualization-of-Thought and Chain-of-Thought reasoning to elicit spatial reasoning and perception, emulates, plans and simulates synthetic HID interactions.

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.

Ground truth layer for humans and AI agents working together. Version control for knowledge.

Measuring frontier coding agents on original, long-horizon engineering tasks

Whisper command line client compatible with original OpenAI client based on CTranslate2.

A user-friendly, multi-platform GUI for managing and running CrewAI agents and tasks. Supports Conda and virtual environments, no coding needed.

Webchat to API

Build, Evaluate, and Deploy GUI Agents — online RL training, standardized benchmarks, and real-device deployment in one framework.

A framework to build Slack apps using Python

A 7-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider.

The Best AI Agent Framework for Agent Collaboration.

Natural voice conversations with Claude Code

Open-source AI reverse-engineering agent using Ghidra and LLMs to reconstruct and validate C/C++ functions from binaries.

🌎💪 BrowserGym, a Gym environment for web task automation

Offline inference engine for art, real-time voice conversations, LLM powered chatbots and automated workflows

Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个

A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.

OpenAI-compatible API for Gemini Business with multi-account load balancing and multimodal capabilities (image/video generation, file parsing) | 将 Gemini Business 转为 OpenAI 兼容接口，支持多账户负载均衡及多模态能力（图像生成、视频生成、解析文件）

PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai

A self-organizing multi-agent collaboration platform for OpenClaw. Multiple AI agents work as an autonomous team — planning, executing, reviewing, and patrolling tasks with zero human intervention.

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Proximal Policy Optimization (PPO) algorithm for Super Mario Bros

This project converts the API of Anthropic's Claude model to the OpenAI Chat API format.

Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A with file paths and line numbers. Works in any AI IDE.

ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment

Agent Skills for Solopreneurs

An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.

TeleChat: 🤖️ an AI chat Telegram bot can Web Search Powered by GPT-5, DALL·E , Groq, Gemini 2.5 Pro/Flash and the official Claude4.1 API using Python on Zeabur, fly.io and Replit.

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

An alignment auditing agent capable of quickly exploring alignment hypothesis

TrustRAG：The RAG Framework within Reliable input,Trusted output

Give Claude Code a memory that evolves with your codebase. Hooks automatically capture sessions, the Claude Agent SDK extracts key decisions and lessons, and an LLM compiler organizes everything into structured, cross-referenced knowledge articles - inspired by Karpathy's LLM Knowledge Base architecture.

Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.

Chat with any codebase in under two minutes | Fully local or via third-party APIs

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.

DeText: A Deep Neural Text Understanding Framework for Ranking and Classification Tasks

Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.

Fine-tune LLM agents with online reinforcement learning

A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions

This is a project that unifies the management of LLM APIs. It can call multiple backend services through a unified API interface, convert them to the OpenAI format uniformly, and support load balancing. Currently supported backend services include: OpenAI, Anthropic, DeepBricks, OpenRouter, Gemini, Vertex, etc.

YiGraph is an LLM-driven agent for autonomous Graph Data Analytics based on Analytics-Augmented Generation. 易图（YiGraph）是一套基于 AAG（分析增强生成）框架构建的图分析智能体系统，致力于挖掘数据之间的关联关系，释放数据价值。

Neo4j GraphRAG for Python

Agent driven automation starting with the web. Try it: https://www.emergence.ai/web-automation-api

Effortlessly request recommended movies, TV shows and anime to Jellyseer/Overseer based on your recently watched content on Jellyfin, Plex or Emby—let SuggestArr handle it all automatically, keeping your library fresh with new and exciting content!

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Agent skills for building playable, polished Three.js browser games with gameplay, AAA-style graphics, UI, QA, and optional AI-generated 3D, image, and audio assets.

An MCP server that autonomously evaluates web applications.

🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]