Python agents

Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.

META‑AGENTIC α‑AGI 👁️✨ — Mission 🎯 End‑to‑end: Identify 🔍 → Out‑Learn 📚 → Out‑Think 🧠 → Out‑Design 🎨 → Out‑Strategise ♟️ → Out‑Execute ⚡

llmbasedos — Local-First OS Where Your AI Agents Wake Up and Work

Write your robot software in minutes.

AI-native data platform: 60+ connectors, dlt-based ETL, DAG scheduling, per-source RAG knowledge bases, and sandboxed AI agents that query, chart, and analyze your data.

Official code for article "LLMLight: Large Language Models as Traffic Signal Control Agents".

Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.

[NeurIPS 2024] SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction

A self-hosted AI assistant for academic research — manages your papers, searches literature, tracks deadlines, and answers you on the channels you already use.

Universal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients.

Measuring agents' ability to get work done on a computer

AI video production skill for agents: HeyGen avatars, Seedance b-roll, OpenAI images, Remotion, HyperFrames, screen recording, FFmpeg captions and QC.

A CLI tool to provide LLM context for coding projects by combining project files into a single text file (or clipboard text) with directory tree structure.

KEras Reinforcement Learning gYM agents

The agentic video editing framework

CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities

Turn your ChatGPT or Claude account into a fully working OpenAI-compatible API. No API keys needed. Supports tool calling, vision, file attachments, and image generation.

smart-llm-loader is a lightweight yet powerful Python package that transforms any document into LLM-ready chunks. Spend less time on preprocessing headaches and more time building what matters. From RAG systems to chatbots to document Q&A, SmartLLMLoader handles the heavy lifting so you can focus on creating exceptional AI applications.

Ringer — parallel AI-agent swarm orchestrator. Ringside — its native mission-control HUD. Fable-quality output without Fable-level burn.

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

A full-stack Webui implementation of Large Language model, such as ChatGPT or LLaMA.

Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generation.

Standalone agent runtime core with neutral LLM types, provider clients, tool loop, and extension protocols.

gradio mcp-server region:us

The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, and OpenCode. Zero cloud lock-in.

DEPRICATED! Use the multi-agent suite instead!

SE-Agent is a self-evolution framework for LLM Code agents. It enables trajectory-level evolution to exchange information across reasoning paths via Revision, Recombination, and Refinement, expanding the search space and escaping local optima. On SWE-bench Verified, it achieves SOTA performance

Threat Designer is a GenerativeAI application designed to automate and streamline the threat modeling process for secure system design.

闲鱼 CLI · 原生支持 MCP · 为 AI Agent 而生 | Goofish (Xianyu) automation CLI · MCP-ready · Built for AI Agents

Multi-agent demo platform for Titans (arXiv:2501.00663) — neural networks that learn to memorize at test time. 7 AI agents, native desktop UI.

Consulting firm-style PowerPoint design system for AI agents. 70 layout patterns, flat design, python-pptx. 麦麸风格PPT设计系统。

Open protocol for AI agent work contracts and verifiable execution — authorization, evidence, and acceptance for multi-agent systems

📛 Autoxsh is an open-source tool that utilizes OpenAI's API to automate the generation and publishing of content on Xiaohongshu (Little Red Book), including images, titles, text, and tags.

A python wrapper for the Doc2X API and comes with native texts processing (to improve PDF recall in RAG). | Doc2X API的python封装，同时附带本地的文本处理(提升PDF在RAG中的召回率)。

She's the AI agent you come home to.

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Home Assistant LLM integration for local OpenAI-compatible services (llamacpp, vllm, etc)

热门Skills中文cn学习版+教程，提供7000+Skills，集成claude skills (11w+Star) | awesome-openclaw-skills (4w+Star) | ui-ux-pro-max-skill (4w+Star)等10余个热门Skill项目

OnlyShot · 神仙鱼 AI 短剧工业流水线 Claude Skill — 一句话 → 剧本/分镜/分镜图/视频/剪辑 五步 → 可发红果抖音的完整短剧。集成即梦/Seedance，17 失败模式沉淀。

Software design & development with AI

Find best-response to a fixed policy in multi-agent RL

Running local Language Language Models (LLM) to perform Retrieval-Augmented Generation (RAG)

通过多智能体（Multi-Agent）打造的革命性的安全运营解决方案

OpenCode/Claude Code 技能库 。特色技能：视频生成、图片生成、AI Agent 互联、智能问数等等各场景，持续开发更新中

Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments (ACL 2026)

Agent Skills for Langfuse, the open source LLM engineering platform for tracing, prompt management, and evaluation

A Test Project for a Network Security-oriented LLM Tool Emulating AutoGPT

An extension for oobabooga/text-generation-webui that enables the LLM to search the web

Broccoli turns Linear tickets into shipped PRs — powered by Claude and Codex, running on your own Google Cloud or Blaxel containers.

Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.

Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch. Claude Code, Codex, OpenClaw, and PyPI.

282+ structured privacy & data protection skills for AI agents. GDPR, CCPA, EU AI Act, HIPAA, LGPD, PIPL, DPDP Act.

Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)

[ICML'25 Oral] Multi-agent Architecture Search via Agentic Supernet

MCP server for Mikrotik

Free open-source desktop app that scrapes JAV metadata and generates NFO + cover art for Jellyfin, Emby & Kodi. No Docker, no CLI — one-click install on Windows & macOS. 8 built-in sources + optional Metatube federation (30+ providers), actress collections, cross-language tag aliases, and a REST API for AI agents.

transformers gguf text-generation arxiv:2309.00071 license:apache-2.0 endpoints_compatible

Home of the AI workforce - Multi-agent system, AI agents & tools

AI Agent for Istanbul Stock Exchange and Turkish Investment Fund Data

Requirement-driven evaluation harness for AI agents and LLM applications. Generate behavior-specific test cases, run them against any target (hosted models, callable wrappers, OTel-traced agents), and inspect local-first artifacts.

RAG on codebases using treesitter and LanceDB

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

A simple Python program to implement the search-extract-summarize flow.

LangChain abstractions backed by Postgres Backend

A multi-agent LLM system for detecting and resolving cognitive dissonance.

Octogen is an Open-Source Code Interpreter Agent Framework

use claude code's agent teams orchestraction with any harness

OpenLens AI: A Fully Autonomous Multimodal Research Agent｜ OpenLens AI：全自主多模态科研智能体

Youtu-RAG: Next-Generation Agentic Intelligent Retrieval-Augmented Generation System

Harness for running and evaluating AI agents against RL environments

A multi-agent LLM system for detecting and resolving cognitive dissonance.

All-in-one Web Agent framework for post-training. Start building with a few clicks!

WARC + AI - Experimental Retrieval Augmented Generation Pipeline for Web Archive Collections.

Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code

🔥 Open-source multi-agent orchestration system for OpenClaw, enabling swarm intelligence via unified group chat.

Research-first design skill for AI agents. 150K+ real app screens and flows via Refero MCP.

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.

Build your own LLM-native WIKI (knowledge library). Search, extract, summarize, Q&A with contextual RAG, layered knowledge graph, and reinforced memory. Importantly use selected context to automatically generate skills, empowered by Claude subagents + CodeAct pipeline and gated by human review. **Try Live Demo**: https://byo-wiki-demo.vercel.app

Earn RTC crypto by contributing to the RustChain ecosystem. Bounties from 1-150 RTC. Star, code, write tutorials, find bugs.

Circuit Framework — multi-agent LLM trading research system

Safestclaw is the alternative to openclaw.. You can naturally chat with it via text and voice, and you can choose not to use a language model., By default it picks up on intent and semantics.. No prompt injection while you get over ninety percent of what openclaw does plus tts and voice to text

Multi-Faceted AI Agent and Workflow Autotuning. Automatically optimizes LangChain, LangGraph, DSPy programs for better quality, lower execution latency, and lower execution cost. Also has a simple agent/workflow framework

Agentic AI platform that harnesses Visual LLM Chaining to build proactive digital assistants

Multi-Agents AI LLM Crypto Financial Trading Framework. 开源多代理加密货币交易决策框架。

A Foreign Function Interface package for calling C libraries from Python.

Persistent Agent Workspace — AI agents that remember, collaborate, and never start from zero.

A curated collection of resources, tools, practices, case studies, and opportunities for Forward Deployed Engineers.

Examples of chatbot implementations with Langchain and Streamlit

Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.

🚀 K8s Agent Orchestration System: Managing the KAOS in your large-scale distributed multi-agent systems

Zero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA · TRL+MPS/MLX on Apple Silicon. Automates env setup, LoRA training (SFT, DPO, GRPO, vision), post-hoc GRPO log diagnostics, evaluation, and export end-to-end. Part of the Gaslamp AI platform.

Accelerate your Gen AI with NVIDIA NIM and NVIDIA AI Workbench

Main Kagenti repo - installer, UI and docs

🧠 AI Agent Skills Repository - A curated collection of specialized skills for AI coding agents (Claude Code, GitHub Copilot, Cursor, Windsurf). Created by Yuval Avidani using GitHub Copilot via VS Code Insiders.

Local-first, multi-agent Skill governance, collaboration panel, and shadow routing (v5.0).

Towards Large Multimodal Models as Visual Foundation Agents

Production-grade DSPy 3.2.x agent skills + validated end-to-end examples for Claude Code and Codex CLI — fundamentals, evaluation, GEPA, BetterTogether, and RLM.

Build AI that feels. Open-source persona engine — personality emerges from neural drives, not prompts. Inspired by Her.

A self-hosted, secure, feature-rich memory system for AI agents and assistants. Provides intelligent fact extraction and deduplication, with an artifact store for detailed content.