Python agents

Give your AI agents persistent memory.

Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"

MaverickMCP - Personal Stock Analysis MCP Server

🔍 Better text detection by combining multiple OCR engines (EasyOCR, Tesseract, and Pororo) with 🧠 LLM.

🤖 AI-powered software engineering multi-agent system with researcher and developer agents that automate code implementation through intelligent planning and execution. Built with LangGraph multi-agent workflows

An application for running LLMs locally on your device, with your documents, facilitating detailed citations in generated responses.

Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案

xLAM: A Family of Large Action Models to Empower AI Agent Systems

Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.

An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.

An AI-app that allows you to upload a PDF and ask questions about it. It uses OpenAI's LLMs to generate a response.

An open-source LLM based automatically daily news collecting workflow showcase powered by Agently AI application development framework.

LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and medical agentic benchmarks.

A collection of multi agent environments based on OpenAI gym.

Open-source framework for developing real-time multimodal conversational AI agents.

🔥🔥🔥 [NeurIPS2025] MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem

🤖 AI-Powered MCP Server for Polymarket - Enable Claude to trade prediction markets with 45 tools, real-time monitoring, and enterprise-grade safety features

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.

transformers pytorch baichuan text-generation custom_code zh

transformers safetensors deepseek_v2 text-generation conversational custom_code

transformers safetensors qwen3_5_moe image-text-to-text moe vlm

API to run VirtualHome, a Multi-Agent Household Simulator

[ACL 2025] Graph-guided agentic framework for code localization https://arxiv.org/abs/2503.09089

OpenChatBI is an intelligent chat-based BI tool powered by large language models, designed to help users query, analyze, and visualize data through natural language conversations. It uses LangGraph and LangChain to build chat agent and workflows that support natural language to SQL conversion and data analysis.

A very quick project that transforms research papers into engaging three-person discussions, offering an intuitive and thought-provoking listening experience. Perfect for podcast enthusiasts seeking a fresh way to explore academic content.

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

The ultimate playground to learn, experiment with, and compare modern open-source AI agent frameworks — from basics to production-ready setups.

OpenSail is the open-source alternative to Codex App, Claude Desktop, Cursor, and Cowork for agentic software work.

这是一个 LangChain 1.0 和 LangGraph 1.0 的学习仓库，学习如何进行agent开发，涵盖从基础概念到实战项目的完整学习路径。

Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.

Agent communication SDK. The open-source agent communication layer for AI agents — email, WhatsApp, Slack, Discord, Telegram, SMS. Python & TypeScript.

PyTorch implementations of various Deep Reinforcement Learning (DRL) algorithms for both single agent and multi-agent.

21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a tech pro.

Bridge between LLM-Agent and Cadence Virtuoso. A new infrastructure for Agentic Analog and Mixed-Signal Design.

File your Indian income tax return (ITR) from your terminal. Deterministic tax engine, both regimes, AY 2026-27. Claude Code / Codex / Gemini skill.

MLGym A New Framework and Benchmark for Advancing AI Research Agents

AI-Hedge-Fund for Crypto 🚀 AI-powered hedge fund for cryptocurrency trading, leveraging LLM agents for intelligent decision-making.

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

freephdlabor: customizing personalized multiagent systems that researchs 24/7 on your own scientific problem

Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.

KaliGPT: an Agentic AI (built with Gemini, ChatGPT, Ollama, OpenRouter Models) fine tuned for ethical hackers & students in offensive security making workflows smarter, faster, and more accessible.

Chain together LLMs for reasoning & orchestrate multiple large models for accomplishing complex tasks

A wechat robot based on ChatGPT with no risk, very stable! 🚀

Home Assistant MCP server agent. Enable Claude Code, Cursor, VS Code or any MCP-enabled IDE to help you vibe-code and manage Home Assistant: create and debug automations, design dashboards, tweak themes, modify configs, and deploy changes using natural language

把中文全渠道内容（抖音 / B站 / 小红书 / 公众号 / X / 播客）采集进个人知识库的 13 个 AI Skill：图文存图、视频转文字稿、字幕优先免 GPU，附带知识库 MCP server。 ｜ Ingest Chinese content into your personal knowledge base — image/video routing, subtitle-first transcription, and a KB MCP server.

Python API to develop chatbot on Facebook Messenger Platform

A distributed framework for LLM agents

Integrate LLM in any pipeline - fit/predict pattern, JSON driven flows, and built in concurency support.

kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

GraphRAG4OpenWebUI integrates Microsoft's GraphRAG technology into Open WebUI, providing a versatile information retrieval API. It combines local, global, and web searches for advanced Q&A systems and search engines. This tool simplifies graph-based retrieval integration in open web environments.

MAD: The first work to explore Multi-Agent Debate with Large Language Models :D

Elevate vibe coding to vibe engineering: Get consistent Github Copilot custom instructions, Cursor, Roo Code, Cline, Windsurf, Claude Code, Gemini Cli, Codex CLI, kilo code, warp custom rules via a universal, managed template. Features vibe coding memory bank & best practices for large codebases.

Open-source RAG platform with multi-LLM support. Build AI agents that connect to your data, tools, and workflows - no code required.

Are Copilots Local Yet? The frontier of local LLM Copilots for code completion, project generation, shell assistance, and more. Find tools shaping tomorrow's developer experience, today!

YT Navigator: AI-powered YouTube content explorer that lets you search and chat with channel videos using AI agents. Extract insights from hours of content in seconds with semantic search and precise timestamps.

Intelligent data acquisition framework for GitHub and web sources

DeepPaperNote is an agent skill for deep-reading a single paper and generating high-quality Obsidian-style research notes. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Self-evaluating interview for AI coders

Question answering system for PDF files

Build high-performance AI models with modular building blocks

Converse with book - Built with GPT-3

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

Failure archive for ChatGPT and similar models

Uses ChatGPT API, Bard API, and Llama2, Python-Nmap, DNS Recon, PCAP and JWT recon modules and uses the GPT3 model to create vulnerability reports based on Nmap scan data, and DNS scan information. It can also perform subdomain enumeration to a great extent

Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.

CookHero是一个基于 LLM + RAG + Agent + 多模态的智能饮食与烹饪管理平台，支持智能菜谱查询、个性化饮食计划、AI 饮食记录、营养分析、Web 搜索增强，以及可扩展的 ReAct Agent / Subagent 工具体系，帮助厨房新手轻松成为“烹饪英雄”。

MCP-Universe is a comprehensive framework designed for RL training, benchmarking, and developing AI agents for general tool-use.

Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.

AI agents that guide you from idea to working code, with you in control at every step.

gradio llm perf leaderboard llm performance leaderboard llm performance leaderboard region:us

[CVPR 2025] Video Narration as Vocabulary & Video as Long Document

[ICML 2026] Official resources of "Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning".

TimeCopilot: the GenAI Forecasting Agent. Built on LLMs and Time Series Foundation Models, it lets you forecast, cross-validate, and detect anomalies using multiple foundation models through a single API. From finance and energy to web analytics, TimeCopilot turns natural-language queries into production-ready forecasts.

A Claude Code skill by Hao (駱君昊) that learns your Facebook voice and auto-posts to FB / IG / Threads / X with a 14-day content calendar. Mega-viral validated: 80K reach / 448 likes / 500 comments on first post. Includes Day 2 flop postmortem.

appbuilder-sdk, 千帆AppBuilder-SDK帮助开发者灵活、快速的搭建AI原生应用

Ollama alternative for Rockchip NPU: An efficient solution for running AI and Deep learning models on Rockchip devices with optimized NPU support ( rkllm )

transformers safetensors qwen2 text-generation en dataset:AI-MO/NuminaMath-CoT

AI-first security scanner with 76 analyzers, 9,600+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo

See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.

AI writing agent powered by kimi-k2-thinking - autonomously creates novels and stories with deep reasoning

Excel-to-Neo4j knowledge graph examples: legacy py2neo v3 plus modern Neo4j GraphRAG/vector search.

transformers pytorch safetensors llama text-generation conversational

Make Office/WPS more powerful and easier to use with AI, similar to Office Copilot and WordGPT.

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.

Enterprise-grade AI marketing automation for Claude Code, Cursor, GitHub Copilot, and any AI assistant supporting agents & skills

Run LLaMA (and Stanford-Alpaca) inference on Apple Silicon GPUs.

[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

Personal-Model First Self Evolving AI Agent 🐘

ZerePy an open-source framework for AI agents written in Python

An MCP Multimodal AI Agent with eyes and ears!

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

The first agentic payment network: policy-controlled, gasless, and real money-ready. OmniClaw CLI + Financial Policy Engine let autonomous agents pay and earn safely at machine speed.

Find issues worth your attention.

电商视觉文案设计SOP Skill - 让电商设计小白也能一键做出5年资深设计经验的商品图片.兼容 Claude / Codex / Cursor / Workbuddy 等 SKILL.md Agent

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

A comprehensive list of Python projects

ICT/SMC trading-knowledge skill for AI coding agents (Claude Code / Codex / OpenClaw / Hermes)

gradio leaderboard region:us

the framework/ sdk that lets you build browser controlling agents in 3 lines of code. join chat @ https://discord.gg/umgnyQU2K8