Python agents

Official implementation of "Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning" (CVPR 2026)

AI Operating System for Claude Cowork - install AI infrastructure instead of bouncing between chat tabs. 7 skills, 9-phase guided onboarding, Mac + Windows.

Ragworks — a self-hosted, low-code workbench for building transparent, traceable RAG pipelines. Wire up ingestion and retrieval visually, then see exactly what every run did.

Vision-primitives MCP server for text-only LLMs: describe, locate (coordinates), OCR with bbox, annotate, crop, zoom, automated anomaly scanning, computer use — powered by Xiaomi MiMo V2.5. Single-file Python, Pillow-only dependency.

MCP server that delegates Claude Code subagents to local models (LiteLLM/llama.cpp/Ollama), DeepSeek, AWS Bedrock, or any OpenAI/Anthropic-compatible backend — without losing the Claude Code orchestrator session.

An AI SRE for Kubernetes: connects to your cluster, investigates with real tools, explains the root cause in plain English, and executes the fix only after you approve it. Peer-reviewed — Journal of Grid Computing, 2026.

A character engine for AI agents — persistent affect, provenance-aware memory, gated proactivity, and an auditable forgetting lifecycle. Reference design.

SkillPortrait — skill-centered utility and safety evaluation for agent skill packages

The open-source AI firewall for enterprise MongoDB databases. Safely execute live AI agent queries with zero sensitive data payload egress to LLMs.

Autonomous AI security engineer — multi-agent swarm that scans, exploits, fixes, verifies, and attests. Open source (Apache 2.0).

Multi-agent debate framework for long-form complex research. 11 AI departments cross-validate every claim with confidence annotations. Not one LLM — an adversarial committee. 共识管线：多智能体学术辩论框架，11个AI部门交叉验证，长线复杂任务一站解决。

Hermes Agent platform plugin for Max messenger gateway

Remove Claude/AI attribution from a GitHub repo in one command clean commit history, force-push, and refresh the Contributors graph so @claude disappears.

WardenIQ is an open-source AI test intelligence platform that turns requirements, docs, and code changes into test cases, test plans, coverage insights, and release test cycles for smarter QA.

gradio image-to-image artifact-removal flux region:us

gguf jack-xml j-space agentic long-context qwen3.6

Permission-bound, compiler-style AI Skill for auditable investment investigation. Research only; bilingual docs.

Production-grade Agentic Harness for autonomous AI agents. Features MCP server integration, cost-controlled DAG workflows, and actor-critic loops. Optimized for Claude Code, GPT-4o, and local LLMs. The infrastructure for reliable Agentic AI.

A governed multi-agent software development Skill for Codex

Claude Agent Skill that eliminates generic AI-generated design. Stop your AI shipping the same purple-gradient, Inter-font, three-feature-card website as everyone else.

gradio region:us

An autonomous LLM paper-trading agent that dreams, remembers, and reviews its own trades

Multi-agent research orchestration using Ollama cloud models — parallel workers, web search, shared scratchpad, modular tools.

transformers gguf text-generation zh license:apache-2.0 region:us

gguf llama.cpp gemma python code reasoning

A lightweight Python library for dynamic multi-persona interactions management with LLMs.

将 AI 聊天接入通讯软件的连接与管理程序

transformers safetensors qwen2 text-generation chat conversational

Your Claude Code session sees the 5-hour limit coming, checkpoints its work, and resumes itself when the window resets. Hook-based, stdlib-only, macOS/Linux/Windows.

A local-first app that turns your documents into a personal knowledge base you can read, search, and actually retain — with the LLM running on your own machine.

Provenance-aware memory for AI agents.

EverLingo is an AI language companion that helps you learn in context and remember what you learn. It captures meaningful moments as you explore words, sentences, and ideas, turning them into useful notes. Later, EverLingo recalls those notes when relevant, making your learning more personal, connected, and effective.

AetnaMem /ET-nuh-mem/ is agent Memory delivers fully local long-term auditable, proof-ready memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies, it supports OpenClaw, install it via pip.

Job hunting beyond Thunderdome — a local-first, open-source toolkit that finds roles without the LeetCode/AI-screener gauntlet. Runs your whole search from the CLI, driven by an AI agent.

Local prompt-cache economics for LLM agents: split cache reads/writes from input spend, reconcile dollars to invoices, and surface concrete TTL/marker fixes.

mlx safetensors qwen3_5 qwen3_6 token-efficient efficient-thinking

War - agentic warfare simulation

A scientific calculation and plotting QQ Bot based on Python and CQ-HTTP.

Your personal chatGPT as Telegram Bot

Chat with Github Repositories (w/ multiple filetypes). Provides flexible backend: Select from different Vectorstores, Context Retrieval-methods and LLMs.

📄 Serverless MinerU 2.5 Pro PDF parser on RunPod. Scales to zero. PDF → Markdown + JSON.

Multi-agent LLM trading system implementing arXiv:2510.04787: agents develop grid-trading strategies offline and a low-latency bot executes them on Binance spot. Research implementation under active correction, not for live capital.

Give your agent a memory it can prove. One Python file: local SQLite vault, hybrid FTS5 + vector retrieval, Cloudflare-aware fetching, and a research loop whose [V]/[E]/[H] citations are machine-verified by CLI, not prompt-enforced.

The best-benchmarked open-source AI memory system and the first AI memory built to forget.

🦙 chat-o-llama: A lightweight, modern web interface for AI conversations with support for both Ollama and llama.cpp backends. Features persistent conversation management, real-time backend switching, intelligent context compression, and a clean responsive UI.

Open-source AI-native engineering plugins for Claude Code — project context, code review, security audit, task clarification, and more

Scaffold, run & deploy production LangChain agents — frontend and agent in one command. Built-in proxy, 3 chat UIs, zero CORS.

Deterministic control plane for Codex Agents with typed delegation, durable lifecycle receipts, and journaled writer isolation.

Ask and query your markdown notes using AI

safetensors llama Arabic English LLM Decoder

gguf code qwen qwen-coder codeqwen text-generation

把学校规章、培养方案和公告变成能提问、可追溯到原始文件与页码的大学 RAG 知识库。

Agentic RAG demo for public patent text (Streamlit + hybrid retrieval + verification)

A voice assistant that can recognize and respond to user’s voice commands using Porcupine, Whisper, pyttsx4, OpenAI GPT, and LangChain.

🌟 Mindstride is a RAG-based chat assistant designed to support mental health, personal growth, and self-improvement. This project leverages advanced AI technologies to provide a personalized and insightful experience, drawing from the wisdom of over 70 books on mental well-being, personal development, and self-discovery.

Audio enabled end-to-end RAG pipeline

pyWhat LLM version | Answer "What is it?" on the command line with the power of large language models

📝 Streamlit App : Weekly News Letter Crew AI Agents 🖋️

Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from

a startup but not simple agent demo using google adk.

An LLM-first AEO analysis skillset for Antigravity, Codex, Claude, Gemini, OpenCode, etc. with 6 specialized sub-skills, 6 specialist agents, and 5 optional utility scripts used as evidence collectors

These #LangChain-powered apps include a Research Assistant that generates reports using web scraping and GPT-4o-mini, and Chat With Video, a #Streamlit app that #transcribes videos and enables content-based Q&A via #embeddings.

Engage in dynamic conversations with PDFs to extract and comprehend information using locally hosted LLM variants of Ollama by integrating RAG.

M1 is a research project exploring large-scale music generation using diffusion transformers. This repository contains the implementation of our proposed architecture combining recent advances in diffusion models, transformer architectures, and music processing.

FastAPI Local RAG Q&A Demo

Production-ready RAG movie recommender with multi-agent architecture, OpenAI embeddings, and conversational web UI. Ask naturally about movies - get intelligent recommendations instantly!

Production-grade RAG pipelines with evaluation baked in

It shows how to use an agent based on LangGraph with MCP.

McPortfolio: A Model Context Protocol server providing 9 specialized tools for LLM-driven portfolio optimization using natural language, covering mean-variance to machine learning approaches.

L'intelligence artificielle qui s'éveille à votre métier. Plateforme IA souveraine, hébergée en Europe, auditable. Conscience v4 per-user, 11 plugins, 8 providers LLM, BSL.

✨ AI Agent that uses tools and functions to autonomously complete multiple tasks.

Pyclaw, your own personal Python AI assistant.

Koro — voice-first AI agent that actually does things. Search, code, execute — all via Telegram voice.

Production-grade evaluation framework for Text-to-SQL and SQL AI agents. 50 metrics. Any LLM. pip install sqlas.

Open-source AI agent to safely kill stray dev servers & free blocked ports in Google Antigravity IDE (and similar agentic IDEs like Cursor). Slash commands: /killservers /listports /nukeports. Intelligent, safe, portable

An intelligent AI-powered system designed to simulate, monitor, and analyze malicious interactions

an agent skill that gives AI assistants full control over macOS Mail.app

AI agentic setup. Backend-agnostic, RAG, tooling

HumanStudy-Bench: Community Edition — Standardized human study replays for AI agent evaluation

AI Code Mentor is a runtime environment designed for building applications with integrated autonomous AI agents.

A secure database access gateway for AI Agents: Empowering LLM (Agents) with database access capabilities.

A5:DB Document. Create DB Schema layout document for AI Agent.

🦞 OpenClaw Pool — multi-tenant AI agent platform on AWS EC2 Firecracker microVMs with per-tenant isolation, auto-scaling, and web management console.

AI cloud-cost investigator. Dual-model (Opus + Sonnet) reasoning over AWS / GCP billing exports with a 7-layer command validator. Paranoid mode by default — never touches your cloud unless you opt in. By MatrixGard.

Streamlit interface for the pandora_ai GPT4 python console package

Structured abstractions for object-oriented Python LLM prompts

🧠 Graph-powered memory for AI agents. NER + co-occurrence graph + Personalized PageRank. Zero LLM cost, CPU-only, 82% faster than vector search. Inspired by SPRIG (arXiv 2602.23372).

Agente de IA especializado em ajudar com pequenos reparos residenciais, construído com LangChain, FastAPI e modelos locais com Ollama

A LangChain tool that enables AI agents to browse safely using deep Web Page inspection. Web access is the #1 attack surface for autonomous AI agents.

精选 Claude Code , Open Code等Agent Skills 合集，覆盖 Agent/Skill 工程化、后端架构、事件驱动、CI/CD、前端设计、文档办公自动化与可视化创作

Your own personal AI interview assistant. Any OS. Any Platform.

This is a project aimed at creating an agent that perpetually thinks and develops itself. It can add entries into an SQLite database and change the structure of that databaase. It also has the ability to search the web when it needs to. It utilizes OpenAI function calling and the responses API. All that is needed to run it is an OpenAI API key.

Android Use Agent

Use a RAG Langchain agent that connects to your supermarket's inventory database and get information about product stocks and locations.

Google Gemini Agentic AI Vision for Wildlife Analytics

Get quick insights from your Data Sources in tables, charts and graphs with with AI-driven audits and optimize your SQL databases.

Chinese metaphysics MCP server — BaZi, Tong Shu, Feng Shui tools for AI agents

LLM powered chatbot of legal domain

A standard protocol that enables LLM applications to interact with EVM-compatible networks.

Test-driven harness engineering for Python agents: own the loop, capture failures, and gate every change.