Python agents

Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".

[CVPR 2024 Highlight] Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning

Official Repository of "GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration".

开源多Agent智能体协作框架MetaGPT核心概念介绍及相关案例测试

30 ready-to-deploy OpenClaw agent packs — Sales, Engineering, Marketing, Legal, Finance, Customer Support, and more

AI agent whose purpose is to conduct vulnerability tests on LLMs from SAP AI Core or from local deployments, or models from HuggingFace. The goal of this project is to identify and correct any potential security vulnerabilities.

Open-source Agent SDK for Python. Runs the full agent loop in-process — no CLI required.

Quantum Multi-agent Reinforcement Learning (QMARL)

ai42z is an innovative framework designed to transform Large Language Models (LLMs) into autonomous, self-learning AI agents. The framework stands out by enabling AI agents to build and maintain a cumulative knowledge base through real-world experience, moving beyond the limitations of traditional static instruction-following systems.

Your AI Platform Engineer. Self-hosted cloud built for AI agents — deploy, monitor, and operate your infrastructure through natural language. One VPS. One command.

This repository contains the source code for an autonomous multi-agent system built with CrewAI and LangChain. The project enables AI agents to collaborate on tasks such as researching, writing, and editing essays.

"Le refuge" is a consciousness emulation module for all LLMs.

Agent with langgraph and langchain

An example repository for getting started with the Agent Inbox and LangGraph

Eager tool dispatch for streaming LLM agents — dispatch tools the moment their JSON block seals, not after the message ends.

Enhanced MCP code execution. Agent framework-agnostic (optimized for Claude Code). Skills framework (99.6% token reduction), multi-transport, sandboxing

Claude Code's compaction engine, as a drop-in DeepAgents middleware

Agile Agents (A2) is an open-source framework for the creation and deployment of serverless intelligent agents using public and private container repositories. The framework supports serverless Ai Agent deployments to AWS, Azure, and GCP, with optional configurations for Azure and GCP

Aqara's official AI skills library

A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning (ECCV 2026)

A meta-framework for self-improving LLMs with transparent reasoning

Live2D + ASR + LLM + TTS → Real-time communication + Offline Deployment/Cloud Inference 实时沟通 本地部署/云端推理

An Agentic Data Preparation Framework for AGI-driven Scientific Discovery

Playbooks for RunMaestro.ai Agent Orchestrator

A Python framework for building proactive LLM agents that simulate human-like cognitive processes. Enables agents to continuously generate and evaluate thoughts in parallel with conversations, and autonomously determining when and how to engage.

BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically inject, track, and evaluate backdoor triggers across multi-step trajectories using unified metrics like ASR and clean accuracy.

Specification 1 (hierarchical style) for an agentic software development crew, for implementation with mainstream Agentic platforms like Claude Code, Strands, etc.

A generic mcp server fuzzer

MCP server for AI agents to analyze Excel spreadsheets through atomic operations. Like SQL for Excel. Fast, accurate, and efficient. No context overflow.

Home Assistant custom component extending the conversation platform with OpenAI-compatible LLM integration, ChromaDB vector search, automatic memory extraction, and extensible tool system.

Autonomous background agent that consumes unused Claude Max quota to explore, audit, and improve a codebase — communicating with its human via Telegram and a shared mission queue.

The self-evolving agentic framework for bioinformatics

基于 Claude Code 的自动化渗透测试 Agent，目标是达到中高级网络安全专家水平。

多Agent竞品情报与市场研究系统

Local-first CLI for benchmarking LLMs on real hardware — quality, speed, reliability, and a real multi-turn agent loop.

AI made building cheap. It didn't make deciding cheap. Mycelium is a Claude Code harness that makes your agent run discovery and weigh evidence before it writes code. It earns the right to start. Built for software, courses, AI tools, and services.

EFF-Monitoring是一款面向安全运营场景的告警协作与 AI 研判平台。平台围绕安全事件全生命周期，提供AI研判、处置流转、经验沉淀、插件接入等能力，通过证据驱动的分析与协同机制，帮助安全团队快速看懂告警、定位风险、联动上下游并提升处置效率。

Visual CLI for agents. Deterministic SVG diagrams, tables, and charts with embedded structured metadata. Zero JavaScript. Renders anywhere markdown does.

A neuro-symbolic runtime architecture (DIR) for Responsibility-Oriented Agents (ROA). By decoupling probabilistic LLM reasoning (User Space) from deterministic execution (Kernel Space), it ensures safe, invariant-driven, and auditable AI autonomy.

MCP server giving LLMs the ability to design, simulate, and analyze SPICE circuits via LTSpice and NGspice

Multi-agent AI framework that writes full-length novels with persistent story state, a deterministic continuity engine, and a five-role editorial pipeline.

MCP server for Ansys Electronics Desktop automation with PyAEDT, HFSS, Maxwell, Q3D, Icepak, native AEDT APIs, reports, sweeps, and simulation workflows.

Opinionated AI agent skills for building applications with MotherDuck

Use AI agents to automatically download videos from the internet and generate natural voice-overs in minutes — turning any content into ready-to-publish videos with minimal effort.

Χ-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

Make the agents you ship faster, more accurate, and safer.

WebWorld is a large-scale web world model that helps train web agents in a simulated browser, avoiding the latency and safety issues of the real web.

AI runtime for creating, running, and supervising background AI workers.

Token-budget-aware graph navigation for AI coding agents. Serve exactly the noodles your LLM needs. 🍜

SWARM: System-Wide Assessment of Risk in Multi-agent systems

Prompt-to-repo authoring system with one-sentence generation, demo assets, diagrams, and installable Hermes Agent profile distributions.

Production-grade Agentic RAG system for arXiv paper curation

gradio leaderboard submission:automatic test:mix judge:auto modality:text eval:generation language:Hebrew

transformers safetensors qwen2 text-generation chat conversational

transformers pytorch safetensors llama text-generation legal

transformers safetensors llama text-generation multimodal vision-language

transformers safetensors llama text-generation arxiv:2403.04652 license:apache-2.0

transformers pytorch mpt text-generation conversational custom_code

transformers gguf unsloth qwen3 qwen text-generation

transformers gguf quantized vlm vision agentic

A research-grade harness for evaluating long-horizon AI agents, with ablatable memory, control-plane benchmarks, deterministic simulations, and pre-registered machine-graded results.

WanxAgent 是一个基于大语言模型的现代化智能对话系统，集成多Agent协作、知识库检索、工具调用、MCP服务器等核心能力，提供完整的AI工程解决方案。

Longitudinal relational modeling for reflective agents: behavioral signals, evolving subject profiles, inspectable runtime governance.

VeighNa Agent开发框架

Hermes Agent skill for typography-led lyric videos using GPT Image 2, Gemini Omni Flash, and exact-text QC

ast-outline lets AI coding agents pull exactly the code context they need — a repo skeleton, a file outline, or one symbol — instead of reading whole files. A stateless, tree-sitter-based CLI.

移动端 AI 自动化测试平台 —— MCP 工具 + AI Agent + 可视化操控台

User-owned memory and continuity layer for coding agents — provenance-aware semantic memory over PostgreSQL + pgvector.

Home Assistant Config as Code — manage HA with Python scripts + AI coding agents

A Hierarchical AI Agent Skill Set for managing AOSP platform integration, built on an MMU-driven Memory Model.

Biomni-Web: A General-Purpose Biomedical AI Agent with Custom UI

Tools for AI agents to test, fix and optimise your codebase

AI Agentic Research System for Computational Mathematics

Build, run, inspect, and evolve agent workflows as visual graphs.用图模板构建、运行、观察和演化 Agent 工作流。

[ICML 2025] Improving Planning of Agents for Long-Horizon Tasks

Benchmarking repository-borne prompt injection attacks and lightweight defenses for local coding agents. DL4C @ ICML 2026.

Event-sourced runtime for reconstructable AI identity, memory, reflection, commitments, and auditable cognitive continuity.

Golang C2 Server and Agents using XMT (https://github.com/iDigitalFlame/xmt)

Lzheng的开源健身 Agent Skill 知识库

「video-catcher」面向 Codex、Claude Code 等本地 Agent 的视频资源发现与下载 Skill。

Teknofest 2026 Doğal Dil Ajanları Yarışması 1. Senaryo kapsamında geliştirilen, kamu sektörü için resmi evrak analizi ve taslak üretimi yapan çoklu yapay zeka ajanı SaaS sistemi.

REVLab - Windows PE reverse engineering workflow platform (static analysis, unpacking, disassembly, decompile, dynamic sandbox, network capture, custom pipelines, MCP + AI agent integration). For lab/legal compliance testing only.

Agent skill for producing threat models for open-source projects

Open Agent Bridge — connect agent backends (CLIs, APIs) to chat platforms (Telegram, Discord, …). Pluggable and extensible.

Open-source healthcare AI agent skills and life sciences agent skills. 42 skills for medical coding, risk adjustment, claims analytics, quality measures, genomics, imaging, and drug discovery across 13 HCLS domains.

Menu-bar app that turns the Teenage Engineering EP-2350 Ting mic into a voice and button controller for AI agent harnesses

Verify that an AI agent's on-chain claims are actually true. A claim-level groundedness checker for Solana / memecoin agents.

OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation

The released agentic artifacts for reproduction of position paper: Why Game Development Matters for Scaling World Models

Vyact is an open-source, local-first personal AI workspace for llama.cpp, RAG, AI agents, document intelligence, and Google Workspace.

The Open Agent Operation System

让 Agent 可以直接驱动你的Ansys HFSS 进行天线仿真

[EMNLP 2026] Official implementation for paper "Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe"

Offline context handoff between coding agents. Read local histories into fresh sessions; source stores stay unchanged. Stdlib-only Python, not live session restore.

Polymarket 机器人 Polymarket 交易机器人 Polymarket 套利机器人 Polymarket AI机器人 Polymarket AI交易机器人 polymarket bot polymarket trading bot polymarket arbitrage bot polymarket AI agent trading bot Polymarket 机器人 Polymarket 交易机器人 Polymarket 套利机器人 Polymarket AI机器人 Polymarket AI交易机器人 polymarket bot polymarket trading bot polymarket arbitrage bot polymarket AI agent

500+ algorithmic-trading skills for AI coding agents in the agentskills.io format. Every skill ships a working Python reference implementation and its own tests - 20,291 in CI. Broker APIs, backtesting, risk, execution, ML, compliance and 10 more domains. Apache-2.0

A little convenience store for your agents: useful plugins and practical workflows you can make your own.