Python agents

RL2Grid is a standardized benchmark for reinforcement learning (RL) agents in realistic power grid environments. Built on top of Grid2Op, it models real-time operations such as topology optimization and redispatching, with full AC power flow simulation, stochastic events, expert-informed heuristics, and safety-critical constraints.

Open source Python program for automating gain staging. part 1 of a series for automating audio processing tasks, end goal is to create a full set of tools for an AI to use for automating Audio processing for Music, Film, Game and any other possible applications. UI for AutoGain is very basic but the app is very functional. currently only for MacOS

Improve safety, security, and privacy of AI systems at build, deploy and run stages.

CS294/194-196 Large Language Model Agents

The repository for the scripts and materials for the paper "Simulating Opinion Dynamics with Networks of LLM-based Agents"."

[AAAI 2026] Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization

Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.

xiaozhi AI

In this tutorial we will learn how to create a powerful AI chatbot using LangGraph, FastAPI, and Streamlit.Learn to define a FastAPI backend endpoint for processing requests, integrate LangGraph agents with dynamic model selection, and design an intuitive Streamlit UI for seamless user interaction.

Advanced agent skills for real-time web intelligence. Features specialized focus modes, AI-powered answer synthesis, parallel search, and smart filtering. Built on the Agent Skills open standard.

The Generative AI Toolkit is a lightweight library for building, testing and evaluating AI agents in Python, using any of the LLMs supported by the Amazon Bedrock Converse API.

[ICLR 2026] SR-Scientist: Scientific Equation Discovery With Agentic AI

A collection of agentic iOS/watchOS audit skills and playbooks for IDE agents and CLI tools. Extracted from the development of Haptix.

A terminal coding agent, and a Python SDK for embedding on-device models in your own apps.

图像生成插件，支持生图和改图，可以自动获取头像作为参考等。

Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cursor, Windsurf, VS Code Copilot. 30 tools, 1121 tests.

Market Map agent eval suite for the Reforge AI Evaluation course

[arXiv:2510.06261] "AlphaApollo: A System for Deep Agentic Reasoning"

用 ~5000 行 Python 还原 CC 的核心 Agent Runtime。

Skill to control an Android device with an agent

Your coding agent spends 90% of its tokens finding code, not writing it. Reduce your token usage by 50x with CodeDrift !

A compact operating covenant for AI agents.

A comprehensive benchmarking framework for evaluating and optimizing CPU-centric agentic AI systems across multiple workloads, reproducing results from the research paper: "A CPU-Centric Perspective on Agentic AI"

From idea to shipped product: high-quality engineering workflows for AI agents.

[AAAI 2026 Oral] Automatic Multi-agent Communication Topology Design

[ACL26 Findings] LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning

SAFi is an open-source runtime governance engine for agentic AI that enforces your policies, governs agent actions, and records every decision for audit.

[NeurIPS'25] ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions

This project implements a comprehensive framework for Knowledge Graph Retrieval Augmented Generation (KG-RAG). It focuses on financial data from SEC 10-Q filings and explores how knowledge graphs can improve information retrieval and question answering compared to baseline approaches.

Home Assistant custom integration — Mistral AI as conversation agent and Voxtral as speech-to-text engine. ⚠️ Please note this is not an officially supported integration and is not affiliated with Mistral AI in any way.

Train a 29M parameter GPT from Scratch

Spore Agent——更加友好的人机交互Agent。Spore Agent — An AI agent built for better human interaction.

面向 AI Agent 入门者的教学项目。通过一个完整的电商客服 Agent，让你亲眼看到每一轮对话中 Agent 内部经历了哪些环节、做了什么决策、调用了什么工具、生成了什么 Prompt。

Official Repo: AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

A token-efficient open-source AI assistant that remembers, adapts, and improves — secured, self-hosted, and entirely yours.

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

更新、移植、修复碧蓝档案/蔚蓝档案mod的工具 | Updating&Porting&Fixing Mods for Blue Archive | Steam&Android

LLM tools for Home Assistant that extends Voice Satellite with weather, financial, image and video search capabilities. Provides tools that conversation agents (OpenAI, Google Generative AI, Anthropic, Ollama, etc.) can use to search for images and YouTube videos, with results displayed directly on screen.

Code samples for building AI applications on AWS with Amazon Bedrock, including Converse API, tool use, RAG with Knowledge Bases, guardrails, and a full agent built with the Strands Agents SDK.

CLI fleet management for AI agents on local networks - deploy, upgrade, and monitor OpenClaw/ZeroClaw/IronClaw across hosts via Ansible

한국투자증권 OpenAPI Python 래퍼 — CLI · Python SDK · LLM Agent · 실시간 WebSocket. 문서: unohee.github.io/kis-agent

[ACL'26 Main] Official code for "LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning".

An AI coding harness that shaped itself - repo awareness, surgical edits, validation, recovery, and safe diff approvals.

专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（codex，claude code 等） 调用。

Zero-dependency multi-agent workflow orchestration engine. YAML pipelines, shared event bus, auto-recovery, real-time dashboard.

Make your AI agent think before it codes.

Dynamic dual-granularity skill bank for agentic RL, jointly evolving policy and skills to improve long-horizon decision making in agentic tasks.

A self-hosted Claude agent that actually remembers — verbatim memory palace at zero retrieval cost, Discord + web UI, and 90%-cheaper repeat calls via prompt caching.

Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools

觀瀾 · A-share research workstation with 24 AI sub-agents — one command, deep-dive report in ~10 min.

CompBioBench: A benchmark of 100 diverse, verifiable questions for agents for computational biology (scripts for running agents)

A place to store and share useful agent skills

[ICRA 2026] Official codebase for NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions

JobSearch-Agent automates job searching by scraping listings, filtering based on user preferences, and managing applications. Easily customize search criteria, track progress, and streamline your job hunt with this efficient, Python-powered tool.

Frontend UI Studio built into the Hermes Agent Web Dashboard

A collection of skills for AI coding agents working with Azure Cosmos DB. Skills are packaged instructions and scripts that extend agent capabilities.

你的专属 AI CRM 销售助理，可集成至 OpenClaw、WorkBuddy 等任何 Agent，覆盖 L2C 整个链路。

AFSIM-SKILL 是一款专为 AFSIM（Advanced Framework for Modeling, Simulation, and Command & Control）仿真引擎设计的 AI 编程助手，让你在 Cursor / Trae / VSCode 中通过自然语言快速生成、调试和优化 AFSIM 场景代码。 AFSIM-SKILL is an AI coding assistant for AFSIM (Advanced Framework for Modeling, Simulation, and Command & Control). Generate, debug, and optimize AFSIM scenario files directly in IDE

闲鱼 Agent 化购物助理。LLM 可直接调用工具完成搜索、订阅管理、收藏及任意复杂页面操作；支持关键词订阅轮询、上新降价检测、LLM 推荐排序与 WebUI 管理。本地或远程部署均可，远程模式下 AstrBot 宿主机无需 Playwright。

Curated agentic AI skills for AWS platform engineering, delivered through any coding agent

🔁 Build reliable recurring AI-agent systems: 968 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive atlas, and a structured dataset.

transformers safetensors qwen2_moe text-generation chat conversational

transformers safetensors qwen2 text-generation feature-extraction mteb

LemonClaw, an open-source, universal AI digital employee agent

OTel Plugin for Hermes Agent

Official Implementation of VisualClaw: A Real-Time, Personalized Agent for the Physical World

Team of Codex agents that collaborate through a spec-driven development process. Full Stack Developer parent orchestrates dynamically sized pools of specialists: Coding, DevOps, Review, and Solutions Architect agents.

Human-gated, capability-slotted collaboration workflow (SOP) for coding agents — discovered rosters, condition-based roles, cross-vendor review, signoff gates

openclaw-data-china-stock 是为 OpenClaw 打造的中国市场数据底座：覆盖 A 股、ETF、指数、期权、资金流、技术指标与宏观分析；为 OpenClaw Agent 提供统一行情采集、58 指标计算，并以“工具+Skill”成对输出投研能力；解决了从行情、技术指标到宏观数据的采集、计算与智能分析全链路需求。内置多数据源自动降级（AkShare/新浪/东财/Tushare），确保你的策略与研究流程不因单点故障而中断。你可以把它当作给 OpenClaw 装上的一体化 A 股投研引擎。

[L0 CONSTITUTION] arifOS — constitutional MCP kernel. Law, identity, F1–F13, VAULT999. Judges but never executes. DITEMPA BUKAN DIBERI.

Read-only Dashboard and Desktop plugin for inspecting Hermes Agent memory.

AI-native quantitative research framework

Agent Skills for ABAP Developers

Memory as state, not search — deterministic, dependency-free memory for AI agents. The memory lives in a Markdown file.

一款开源的基金估值、智能理财Agent框架

一个面向 Web 版桌面 安全测试的 AI Agent 平台，集成侦察、分析、规划、工具调用与反馈学习，实现自主完成渗透测试工作流An AI Agent platform for web-based security testing, integrating reconnaissance, analysis, planning, tool orchestration, and feedback-driven learning to autonomously execute penetration testing workflows.

Keep your skills sharp. Intelligence for agent context.

Benchmark framework that measures cost, quality, and duration of coding agents across any AI Coding Assistant CLI, any model, and any use case — with pluggable verification and real-repo support.

AI-ready MCP server for KiCad: automate schematic, PCB, ERC/DRC, DFM, BOM and manufacturing review from Claude, Cursor, Copilot and other AI agents.

Run an After Action Review after any AI session and write concrete lessons so your agent stops repeating mistakes. A manual Reflexion loop, built on the US Army's AAR method.

Local session-mining loop for staging AI agent improvements and public-safe content ideas

多智能体小说写作框架 | Multi-agent novel-writing framework — 每个角色都有自己的脑子,每一章都有质量门禁

AI-powered data visualization assistant - Automatically generate professional charts from natural language descriptions. Supports 7 chart types and OpenAI/DeepSeek/Ollama platforms.

Async dynamic CRUD framework for Django Ninja — built-in auth, filtering, pagination, automatic serialization, and MCP tools for AI agents.

EasyGEE agent plugin for Google Earth Engine, geemap, GeoMaster, and local map workflows

A lightweight CLI coding agent focused on speed, determinism, and developer control

🎱 AI Agent Governance Framework — Constrain how AI Agents behave in your project. pip install pattern8

集成了众多功能的API节点，只需要一个API-key即可以调用全网的API接口能力，低配电脑也能顺利运行

Advanced MCP tool for Perplexity and OpenRouter API integration.

Open Source Embeddings Optimisation and Eval Framework for RAG/LLM Applications. Documentations at https://docs.vectorboard.ai/introduction

Amazon Bedrock AgentCore – Multi Framework Examples

Langchain Models for RAGs and Agents

LangChain + LiteLLM that works

Qualitative Data Analysis done by AI (or LLMs). 🖥️ Streamlit & 🔗 Langchain

This Streamlit application provides a user interface for connecting to MCP (Model Context Protocol) servers and interacting with them using different LLM providers (OpenAI, Anthropic, Google, Ollama).

基于 Langchain，快速集成GLM-4 AllTools 功能的插件