Python agents

A modular framework for benchmarking LLMs and agentic strategies on security challenges across HackTheBox, TryHackMe, PortSwigger Labs, Cybench, picoCTF and more.

MCP server for AutoCAD LT v3.1: freehand AutoLISP execution, 8 consolidated tools, File IPC + ezdxf backends, focus-free dispatch, undo/redo, P&ID symbols, and robust IPC with ESC prefix and UTF-8 fallback. Companion agent skill: puran-water/autocad-drafting

客服机器人，Chinese Retreival chatbot（中文检索式机器人）用到的一些QA模型，基于tf-idf，lsa，cnn，transformer，bert等

LLMs and Machine Learning done easily

A universal flight control tuning framework

Flocks is an agentic SecOps platform.

Measuring and evolving with the frontier of agent work

Anonymous Multi-Agent Path Finding (MAPF) with Conflict-Based Search and Space-Time A*

Guardrails for secure and robust agent development

An open-source implementation for training LLaVA-NeXT.

Any research. One Claw. 🦞 From any materials to research with fully autonomous & skill-driven researcher.

AI-powered stock trading backtesting system with LLM-based decision analysis, FastAPI backend, and Next.js frontend.

Power BI CLI - semantic models (.NET TOM) and PBIR reports for token-efficient AI agent usage, built for Claude Code

Google AntiGravity IDE for Vibe Coding

AI Chatbot for analyzing/extracting information from data in conversational format.

The official implementation of "ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning"

GEO (Generative Engine Optimization) toolkit — audit, optimize, and make websites visible to AI search engines (ChatGPT, Perplexity, Claude, Gemini). Based on Princeton KDD 2024 research.

Open-source Wyckoff trading agent and AI stock screener for volume-price analysis, A-share screening, CLI workflows, and MCP tools.灵感来自秋生trader @Hoyooyoo

Future of Agentic Development in Emacs

What if we could pack single purpose, powerful AI Agents into a single python file?

RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.

Llama Agents + Workflows are an event-driven, async-first, step-based way to control the execution flow of AI applications like agents.

Your First LLM-Wiki Conversation Knowledge Base

gradio region:us

Easily train AlphaZero-like agents on any environment you want!

Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment

面向 AI Agent / Codex 的本地 CTF 逆向工程流程技能。加载后通过“真心为你”进入逆向模式，默认在本地沙盒、CTF、crackme、wargame 或训练靶场环境中工作，按“分析 → 报告 → 逆向 → 深度逆向 → 漏洞研判 → 用户选择下一步”的流程推进。

A tool for generating function arguments and choosing what function to call with local LLMs

AI context optimization platform for files, conversations, RAG, code, logs and AI agents with context compression, evidence preservation, content-addressed recovery and auditable Context Receipts.

Python toolkit for building graph-enhanced GenAI applications

🛡⚔️AI-Powered Penetration Testing Framework with automated vulnerability scanning, multi-agent system, and compliance reporting🛡⚔️

🗿 FableCodex is a Codex-style coding agent workflow that plans like Fable.

gradio region:us

[ICLR 2026] DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle

Stealth Chromium engine that stops scrapers and browser agents from getting blocked, with one line of code change.

transformers pytorch baichuan text-generation custom_code en

Create a data analysis AI agent with Claude Code. Make data analysis as simple as having a chat!​​ 别忘了！claude code也是agent框架，类似langgraph,crewAI，autogen等等agent框架。我改造claude code搞一个数据分析智能体AI。 让数据分析变得像聊天一样简单！

A cautious, explainable AI-like text risk analyzer for local workflows and coding agents.

A database operations and data analysis AI agent

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

Agent-driven alpha factory — LLM autonomously designs, backtests, and submits factors to WorldQuant BRAIN

End-to-end platform for building voice first multimodal agents

a Lightweight library for sequential learning agents, including reinforcement learning

Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

Agentic RAG R1 Framework via Reinforcement Learning

Governed shared memory for AI agent fleets — multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration

RAG LLM Ops App for easy deployment and testing

[CVPR 2025 Highlight] Official code for "Olympus: A Universal Task Router for Computer Vision Tasks"

Code and data for GeneGPT.

The best way to use AI is on your own computer. Use local or paid API models, and ctrl+k to show/hide the chat UI. Experience the future of AI, and help build it too!

[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"

An autonomous LLM-agent for large-scale, repository-level code auditing

Chat2Graph: Graph Native Agentic System.

Integrate AI Assistants with Django to build intelligent applications

🧬 Extend EvoScientist with Installable Skill & Knowledge Packs

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

Practical AI collaboration playbook for research, writing, reading, and coding: article, prompts, agent rules, and reusable skills.

Multi-agent end-to-end application - General-purpose artificial intelligence agent for multimodal agent collaboration

AI agent can create video content better than you. No reason why you do it manually in google flow!

Multi-Plugin python-based Agent for NewRelic's Platform

multi-agent deep reinforcement learning for large-scale traffic signal control.

[CVPR' 2026] JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization

An unofficial Python wrapper for OpenAI's ChatGPT API

🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/

基于大语言模型(LLM)和多智能体(Multi-Agent)，探究AI写小说能力的边界

An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder can help you to build your own agents and tools.

MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.

Practical system design, tools, and hands-on resources for building Gen-AI agents & agentic AI systems.

Agentic Resource Discovery (ARD) specification

Unlock 650+ MCP servers tools in your favorite agentic framework.

[ARCHIVED — migrated to forcedotcom/afv-library] Salesforce Skills for Agentic Coding Tools — Apex, Flow, LWC, SOQL, Agentforce, Data Cloud, OmniStudio. Read-only archive; active development continues at github.com/forcedotcom/afv-library.

Open-source AI agent for web automation and scraping.

[unmaintained]

🤖 Deep Reinforcement Learning Chatbot

Mean Field Multi-Agent Reinforcement Learning

Open source code for ICLR 2026 Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

AI-powered assistant workbench for FreeCAD — generate 3D models from natural language

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual intelligence (image/table captioning), agentic streaming chat, and inline citations. Powered by Gemini or local Ollama models.

Give Claude Code's ultracode mode to ANY model you already pay for. A tiny local proxy + one config.json. Point your AI at AGENTS.md and it sets itself up.

✔️Contextual word checker for better suggestions (not actively maintained)

Project CodeGuard is an AI model-agnostic security framework and ruleset that embeds secure-by-default practices into AI coding workflows (generation and review). It ships core security rules, translators for popular coding agents, and validators to test rule compliance.

Redis Vector Library (RedisVL) -- the AI-native Python client for Redis.

HarnessX is a harness foundry: forge any number of agent harnesses from reusable processors and bundles, pair each with any model, and evolve them through training.

Lightweight LLM Interaction Framework

Fully neural approach for text chunking

Gym Electric Motor (GEM): An OpenAI Gym Environment for Electric Motors

AI agent tooling for data engineering workflows.

The missing bridge between your ML models and your AI agents.

基于LangChain、FastAPI和React的RAG项目，主分支为基于RAG的智能笔记助手，base-rag分支为开箱即用的基础RAG项目供学习使用

🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL

🤖 Agentfy is a modular microservices architecture designed to process user requests and execute workflows across multiple social media platforms. ASK ONCE, LET THE AGENT DO THE REST!

transformers safetensors qwen3 text-generation conversational en

Build robust LLM applications with true composability 🔗

SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration

Browser Use Box: a 24/7 Claude Code agent for Playwright-style browser automation with Browser Use Cloud, Telegram, and a real browser on any box you own.