Python agents

[TPAMI 2026] UniMM: A Unified Mixture Model Framework for Multi-Agent Simulation

[ACL'25] Repo for paper "M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation"

VS-Bench: Evaluating VLMs for Strategic Reasoning and Decision-Making in Multi-Agent Environments

ReAct agent with access to Python REPL to execute simple workflows. Uses OpenAI GPT-family as language model.

Curated rules, skills, and agents for Claude Code — clone into .claude/ and go

Create a domain specific (GRC) agent with the Claude Agent SDK

This is a base-react agent for AssetOpsBench

Kilo-Kit is a comprehensive, modular framework for building and managing AI agent systems at scale (kilo-code = thousands of lines, hundreds of files). It introduces a revolutionary Cognitive Flow Architecture (CFA) that treats AI interactions as continuous flows rather than discrete events.

Agent skills for long-running execution, high-recall code review, and measurable self-improvement loops.

Official codebase for the paper "WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction"

Bodhiorchard is the open-source, self-hosted alternative to Jira and Linear for AI-native software teams. Specialised agents draft every spec, forecast cycle times, and reason over your real repositories, commits, and pull requests — replacing story points, standups, and stale tickets so engineers can focus on building.

Let's Qitos! A torch-like agent-native framework for researchers.

Открытый бенчмарк LLM: какая нейросеть лучше пишет код 1С:Предприятие (BSL). Объективная оценка LLM по методике SMOP с реальным исполнением в 1С — Claude, GPT, Gemini, DeepSeek, YandexGPT, GigaChat.

Catch silent failures in AI agents before your users do

🏛️ Mnemosyne OS — A cognitive memory OS for AI agents. Magic Memory Palace (taxonomy × archive-no × tome cards × 3-channel summon), TMT distillation, knowledge graph, WIKI KB, Hermes-native. Self-hosted. / 认知型记忆操作系统 · AI 长期记忆宫殿 · 自托管

gradio region:us

gradio region:us

transformers safetensors qwen2 text-generation text-generation-inference unsloth

transformers safetensors glm text-generation chatglm conversational

transformers gguf llama legal text-generation en

transformers safetensors llama text-generation code granite

gradio region:us

transformers safetensors jais2 text-generation conversational ar

gguf text-generation base_model:Qwen/Qwen3-Coder-Next base_model:quantized:Qwen/Qwen3-Coder-Next license:apache-2.0 endpoints_compatible

gguf glm codegeex thudm text-generation zh

spec-builder + harness-bootstrap. Specs both you and the AI understand. An agent team tailored to your repo, derived from your contract and your code, not a kit that installs everything. Guardrails that block, not advise.

基于 RAG 与 Agent 的智能面试辅导系统，支持问答、模拟面试、工具调用和面试报告生成。

Archived first-generation Claude Code framework with agents, commands, rules, templates, and MCP integrations.

175+ pip-installable tool integrations for the ModuleX runtime — one pydantic manifest contract, entry-point discovery, async httpx tools

Schema-locked, drift-checked SEO automation as a Claude Code plugin — 49 skills, 29 slash commands, auditable agent workflows (GSC, DataForSEO, Screaming Frog, Scrapling)

AI-Powered Multi-Agent Crypto Investment Analysis Platform

This project leverages Large Language Models (LLMs) and a multi-agent framework to analyze stock prices, gather relevant news, and generate comprehensive financial investment reports for companies.

Voice agent using LiveKit (orchestration), Cartesia (STT + TTS), and OpenAI (LLM)

CryptoAgents is a sophisticated multi-agent LLM framework specifically designed for cryptocurrency trading. It leverages specialized AI agents working as a coordinated trading desk to analyze crypto markets, conduct research debates, execute trades, and manage risk in the 24/7 cryptocurrency ecosystem.

Source code for our paper: "Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents".

[EMNLP 2024] FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents

🍞 记得住、学得会、能进化的个人 AI 助手。持久分类记忆 · 闭环经验引擎 · 子代理并行 · 长任务不漂移 · 9 大平台 · 4 类 LLM · MCP 生态 · 桌面自动化，只有你需要的轻量。｜ The AI assistant that remembers, learns, and evolves. Persistent memory · Experience engine · Sub-agents · 9 platforms · 4 LLM providers · MCP tools.

An advanced multi-agent framework for automating complex bioinformatics workflows.

A modular simulation framework for controlling multiple drones in a PX4-based environment. It features ROS 2 integration, G-code trajectory planning, multi-agent communication, and a Dockerized setup for easy deployment and visualization.

[2026 IEEE RA-L] Multi-Agent Workflow with Chain of Thought Reasoning for Surgical Intelligence

Simple code sandbox supporting jupyter notebook style code execution. Used for agent training

Code for ICML25 paper "HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning"

Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control

Multi-agent harness for building and maintaining a personal wiki based on your data.

Rapidly build a multi-Agent management dashboard based on Claude Code, integrating daily work and remote IM collaboration. It includes Claude Code monitoring, channel configuration and message notifications, with a Codex GUI optimized for non-technical users.

AI-powered visual novel writing studio with multi-agent collaboration, node-based plotting, branches, and human-in-the-loop editing. Built with Tauri + ReactFlow. 开源长篇小说创作工具

A curated library of 137 production-grade skills for Claude and other AI coding agents.

🔧 LRA - AI Agent长任务超稳定执行框架 ⚡ 轻量 | pip一键安装｜突破上下文限制 📌 7种状态管理 | Long-Running AI Agent Framework • One-click pip install｜Break context barriers • 7-status management. 5.0全面支持CLAUDE/OPEN CLAW/OPEN CODE/CUSOR/TREA 等全部Agent编程工具，仅需运行 lra init命令，就会生成Agent.md/CLAUDE.md/lra.md. 你的agent会自动学会如何使用

TWICC - The Web Interface for Claude & Codex - A web UI to browse and interact with your Claude Code and Codex sessions. View projects, sessions, conversation history, costs, and run Claude and Codex agents — all from your browser.

The first MCP (Model Context Protocol) server for NetLogo, enabling AI assistants like Claude to create, run, and analyze agent-based models through natural conversation.

基于claude sdk的自动化小说撰写Agent，支持对话，高质量的小说写作与发表

Long-task-oriented video analysis skill for Claude Code (/vea) — resumable staged execution, automatic parallel scoring, OpenClaw orchestration, audiovisual analysis with agent handoff

Persistent memory for AI coding agents. Your agent learns your codebase the way a senior engineer would — what files go together, what you usually edit next. Works with Claude Code, Cursor, Cline, Continue. 100% local. (Side effect: 12-50× cheaper code questions.)

Free Gemini web interface proxy for OpenCode - Use your free Gemini subscription as an OpenAI-compatible API with full tool calling support

An edge agent framework built in pure Python

Agentic Framework for Synthesizing CodeQL Queries

Sage is a skills framework that makes AI agents think before they act, stay focused under complexity, and deliver outcomes you can trust. Built for product and engineering teams, open to any domain.

An autonomous, 100% local Agentic GraphRAG system for codebase intelligence. Paste any GitHub URL or local directory to chat with your code. Powered by LangGraph, NetworkX, and Ollama (qwen2.5-coder).

Dynamic graph runtime for building, adapting, and observing multi-agent LLM systems in Python.

Pick-a-Recipe: AI-powered recipe extraction from TikTok, YouTube & Instagram videos with automatic import to Tandoor/Mealie recipe managers.

Open, MIT-licensed food & nutrition science research skills for Claude Code, Codex, and MiniMax Agent — multi-agent literature/systematic review, journal-aware writing, peer review, and figures, plus author-guideline skills for 150+ journals. Initiated by the Food Science Group, University of Melbourne.

Production-ready Agent Skills for Codex, Claude Code, OpenCode and OpenClaw | 小红书图文、学习路径、论文解读与 YouTube 播客笔记

Collection of Hermes Agent profiles — persona-driven AI agent configurations for orchestration, coding, and research.

面向 AI Agent 的 HarmonyOS / ArkUI 设计与动效 Skill、规则库与评测基线 · Design & motion Skills, rule library and evaluation baseline for HarmonyOS / OpenHarmony / ArkUI

Clint is the AI Era Outreach System. It is a Python library and CLI (Command Line Interface) designed for production-grade lead discovery, evidence-based personalization, and safe outreach automation. It bridges the gap between raw data scraping and personalized human-like communication.

Production-ready multi-agent platform delivering orchestration, session governance and audit capabilities. Stack: Go/Python/Rust microservices, multi-type data storage, Next.js admin UI, automated CI/CD pipelines, AI code review triggered via PR comment mentions.

Six security outcomes an enterprise must achieve to run AI agents, and the controls that evidence them. A draft for public comment.

Blender addon for the DCC Model Context Protocol (MCP) ecosystem — embeds a Streamable HTTP MCP server directly inside Blender

LongCat-Flash-Chat safetensors text-generation transformers conversational custom_code

Agentic Theorem Prover for Rocq for Program Verification

A local-first permission firewall and approval layer for AI agent tool calls.

An open-source Coding Harness Platform for long-horizon, multi-agent software delivery.

Slack Starter Agent - a minimal AI-powered Slack agent using the Claude SDK, OpenAI SDK, and Pydantic AI.

Self-hosted, OpenAI-compatible speech server: faster-whisper STT and Piper/Kokoro TTS. A local voice backend for Open WebUI, CLIs, and custom agents.

A personal AI operating system built on OpenClaw/Claude Code, MCP servers, and structured markdown. Feedback RL, voice cloning, Screenpipe integration.

Claude Code skill for planning, executing, and measuring digital marketing campaigns. Includes UTM tracking, content strategy, email sequences, social media tactics, brand voice guidelines, and analytics frameworks.

MCP server exposing financial data using Yahoo Finance via yahooquery. Provides stock insights, historical prices, earnings, recommendations, and ownership info. Built for Zentickr AI tools and compatible with research agents or financial copilots.

Lightweight agent framework for research PowerPoint generation, editable PPTX delivery, and rendered QA

Agentic memory infra for AI agents

Based on Hermes Agent's `llm-wiki` skill and Andrej Karpathy's LLM Wiki pattern; extended with multimodal ingestion and provenance hardening.

企业级多智能体AI管理系统 | 企业级智慧管理解决方案 | 基于MCP架构的财务分析、成本预测、知识管理、效能评估一体化平台|- 多智能体系统 (Multi-agent System) - MCP协议 (Model Context Protocol) - - AI决策支持系统 - 企业级AI应用 - Python + FastAPI + Streamlit

AI proposal-writing & deal-closing engine for Claude Code. Research a prospect, price the engagement (3-tier + ROI), define scope, pre-handle objections & generate client-ready PDF proposals. 14 skills, 5 parallel agents. Auto-builds from your GEO/SEO/reputation audit reports.

A compact high-signal benchmark for evaluating frontier agents

An OpenClaw-based agent framework designed for college students.

LitReview Skill is an installable agent skill for end-to-end literature review generation. It helps agents conduct literature reviews with a well-designed and widely used review framework so the search process is broad, iterative, and less likely to miss relevant articles.

ValuSee 是面向消费者的 AI 购物决策与省钱平台，支持商品截图与浏览器扩展采集、SKU 同款及规格识别、跨平台真实到手价核算、评论证据与购买风险分析，并结合预算、已有设备和偏好生成个性化建议；持续提供历史价格、降价监控、保价、退货、保修及买后管理。

Autonomous AI research: an LLM agent searches for the best algorithm to fit the Mandelbrot set.

[ACL 2025] Official respository for EvoPatient: LLMs Can Simulate Standardized Patients via Agent Coevolution

🎬 Autonomous AI agent that transforms long-form videos into viral short-form content across YouTube Shorts, TikTok, and Instagram Reels using advanced AI analysis and automation.

MAS-Orchestra: train, inspect, and vibe-code multi-agent systems with RL-learned orchestration and MASBench

The most advanced multi-agent cinematic production system for Grok 4.5 Build + Grok 4.3 cinematic dual stack · Grok Build ≥ 0.2.93

A股 AI 金融智能决策中台 · 129 个 MCP 工具 · eltdx 通达信协议 + akshare + 同花顺 + 东财 + 本地数据 · SmartRouter 多源降级路由 · 免费零鉴权

Agentic DFIR

Runtime security for AI agents. In-process, zero dependencies, Apache 2.0.

This project is a fully automated AI blogging platform built with LangGraph and Groq’s LLM. It generates and publishes technical blog posts automatically to a modern, responsive website. The system dynamically renders Markdown content without requiring complex build setups.

LLM evals for Hermes agents. Benchmark to find the best models for Hermes

The creation pipeline for Claude Code products — research, create, validate, publish. 13 types, 20 quality patterns, zero coding required.

Red-Team - AI Agent to Phish Employees based on Social Intelligence.

Official code of Attention-MoA: Enhancing Mixture-of-Agents via Inter-Agent Semantic Attention and Deep Residual Synthesis

Campus Docs Assistant – Built to solve a common challenge in universities, this AI-powered chatbot uses LLMs, intelligent agents and RAG to make academic documents and institutional information easier to access and understand.