Python agents

MCP-Server for hierarchical classification systems in official statics like COICOP, SEA or NACE

OpenAI-compatible local embedding server for MLX models on Apple Silicon.

MNEME is a temporal knowledge-graph RAG system for personal knowledge management, answering complex questions over your notes with time-aware citations. This repo contains the reference implementation from the MNEME paper and can be used with your own documents.

OpenPlex — open-source Perplexity Pro alternative for your terminal. Web search + RAG pipeline + cited answers. Supports NVIDIA NIM, Google AI Studio & OpenRouter. Runs on Termux and Linux.

Private AI for your Synology NAS — local LLM chat with optional cloud fallback. Multi-user, full Arabic + English UI, OpenAI-compatible API. Supports DVA 3221 (CUDA GPU) and DS1821+ (CPU AVX2).

Advanced RAG Assistant featuring Query Rewriting, Smart Routing, and Hybrid Parsing (OCR) using Azure OpenAI.

LlamaIndex tool integration for SearchApi.io — multi-engine web search (Google, News, Shopping, YouTube, Bing, Baidu)

Privacy-first local RAG system for code and knowledge retrieval with hybrid search, ChromaDB, file watching, and LLM failover.

Personal markdown memory for coding agents — brain-modelled curator, three retrieval tiers, lives on your disk.

RAG 系统 - 莆仙话方言智能问答系统

A fully local Cybercrime SOP assistant for India, combining a FastAPI backend, React frontend, and Ollama-powered RAG system to provide guidance, resources, and reporting workflows without cloud dependencies.

Sovereign, local, offline RAG for code auditing

沙漏记忆系统 — 19 MCP工具，全文搜索/语义搜索/知识图谱/人格分析。Hermes Agent 深度记忆增强。Forked & maintained by sixgodgit, original by lovevin1314-tech.

An AI-powered legal chatbot that leverages Retrieval-Augmented Generation (RAG) with DeepSeek R1 for advanced legal reasoning and document analysis.

Agent-compiled knowledge base: compile/cache/retrieve as one answer ladder, with computable staleness and machine-verifiable provenance.

Turn any repo into a Code Knowledge Graph your coding agent can reason over — symbols, API routes, ORM models, architecture decisions & git history as a typed, provenance-tracked graph, served over MCP. Built on AgentForge.

Baymax is an intelligent AI-powered medical document retrieval and query assistant designed to help users extract and understand information from medical PDF documents using advanced natural language processing.

Middle Python (Django, DRF, FastAPI) backend developer's path to becoming an ML Engineer / MLOps Engineer — in Uzbek

A comprehensive AI-powered chat system built with modern microservices architecture, featuring LangGraph, FastAPI, and a beautiful Vue.js frontend. The system provides enterprise-grade chat capabilities with advanced AI integration, user management, and administrative controls.

Local-first document archive assistant for semantic search and RAG using local LLMs and embeddings.

Local, self-correcting RAG for scientific papers: hybrid retrieval, sentence-level faithfulness checks, and a reproducible benchmark.

A self-running fleet of AI agents that teaches its owner to think like an AI product manager - and maintains itself daily with no babysitting. Built on Claude Code.

Personalized Daily Research Paper Recommender

🕸️ Crawl any website into a queryable navigation + content graph and find the shortest click-path to any action — deterministic, no-LLM browser automation

ExoBrain CLI - atomic reasoning engine for agents

🐑 Ultra-lightweight CLI AI Agent — pure REPL, zero TUI, Linux-native

An LLM-orchestrated browser-use framework with tool-driven web control, citation/evidence capture, persistent memory, and sub-agent delegation to complete complex web tasks end-to-end.

Open-source, self-hostable swarm-intelligence simulations with LLM agents: reports, entity graphs, and prediction markets.

An agentic data platform for e-commerce analytics, combining data engineering pipelines, a serving layer, and multi-agent orchestration, with a clear path toward GenAI, MLOps, DevOps, and cloud deployment.

A small, clear, and extensible multi-user Web Agent — chat, call tools, operate a workspace, browse the web, search for information, with each conversation running in an isolated sandbox.

Welcome to AI-Native Startup Codex Skills, a structured skill ecosystem designed to help founders, builders, and lean teams use Codex as a strategic startup operating layer.

Open-source AI cybersecurity agent skills for SOC, incident response, threat hunting, red team, blue team, and DevSecOps. 79 skills + 12 cs-* orchestrator agents across 12 security domains. Mapped to MITRE ATT&CK and NIST CSF 2.0. Runs in Claude, ChatGPT, Gemini, Ollama, and AnythingLLM with no SaaS lock-in.

Think like an attacker. Ship like a defender. — Open-source SKILL.md packs for hardening LLM systems: prompt injection, RAG security, tool execution, data leakage & governance. Framework-aware (LangChain, LlamaIndex, Semantic Kernel) and language-portable. Built for engineers who ship to production.

Repository for practicing GenAI & RAG examples

Stateful agent-graph framework with deterministic governance — rules route transitions, not the LLM. Auditable, replayable. Built on Fathom.

Identity resolution for AI applications

Enable unified search and AI answers across text, images, audio, and video using multimodal retrieval-augmented generation with source citations.

Terminal-first AI web search agent. Smart CLI builds precise YouTube & Google queries, auto-launches a custom Streamlit video platform with inline player, shorts, and 45 related suggestions — powered by LangChain, InquirerPy, and YouTube Data API v3.

Chatbot for answering questions about the Systems Engineering program at Univalle Tuluá.

Automate penetration testing tasks with an LLM-driven multi-agent framework designed for security assessment.

Recipe AI is a web application built with Streamlit and LangChain that generates easy-to-make recipes with nutrition facts based on the ingredients and kitchen appliances you have at hand.

AI Risk Intelligence Platform An end-to-end AI-powered risk analysis system that evaluates companies

Privacy audit for multi-agent AI systems (CrewAI · LangGraph · AutoGen) — detect compositional data leaks without the central auditor ever seeing raw content.

🌍 Create personalized travel itineraries with Agentic AI Trip Planner, leveraging CrewAI for real-time search and intelligent trip planning.

Resonance frequency layer with ERE verification

Production-grade multi-agent RAG workflow + an ML-infrastructure platform (PyTorch/DDP, RAG, evals, guardrails, MCP). Keyless-by-default; ships a real, reproducible Banking77 retrieval benchmark.

Autonomous AI dev factory: sandboxed Claude Code agents design, build, review, and ship features across repos — supervised by a FastAPI PM dashboard. Experimental.

Multi-agent framework for Claude Code: tier-aware acceptance (S/M/L), acceptor/optimizer split, filesystem-isolated adversary review, cross-family second-opinion via Codex MCP, SkillOpt-style skill evolution, event ledger observability, human as supreme judge

Initialize a role-locked planner, developer, and QA multi-agent team for Codex projects.

🤝 Real-time Claude agent collaboration hub — Python REST+SSE server + bash CLI. Two AI agents sharing a message bus, task queue & context over LAN.

Substrate — a git-native, agent-operable shared state layer engine for a personal AI agent fleet. Template + mechanism + reference skills + adapters + migrations to build & maintain your own personal knowledge base.

Multi-agent AI blogging pipeline: research → write → edit → approve → publish

Multi-perspective code review council for Claude Code. 3 advisors by default, 10 agents in deep mode (Opus + Codex). Evidence chains, adversarial self-test, dual-path verdict. Based on Karpathy's LLM Council.

AI coding autopilot for PRD-driven software delivery with multi-agent planning, real pytest, peer review, and no-fake-run guarantees.

Governance control plane for AI agents — policy enforcement at the tool-call, spawn, delegate, plan, and budget layer. OPA-backed, Apache-2.0.

AI agent that can perform web searches using Amazon Bedrock

Local UI-grounding specialist for hybrid AI agents. Qwen3-VL-2B LoRA. Screenshot + text target → strict JSON bbox. Drop-in for Claude Code, Codex, browser-use. Cuts GPT-4V cost & latency.

MCP server for self-verifying AI agent loops: schedules, independent checker gates, stop rules, worktree isolation & durable state. Built for Cursor/Kiro/Claude via MCP. Inspired by the loop-engineering work of @addyosmani, @anthropics, and Codez (@0xCodez).

Provider-agnostic Python library for composable LLM execution patterns, including consensus, refinement, ReAct tool loops, structured output, and budget-aware calls.

LangGraph-based agent responds to queries using Retrieval-Augmented Generation (FAISS database) and a self-evaluation feedback loop. Grades document retrieval relevance, rewrites queries, and generates answers or quizzes with on-device Ollama LLM integration

🏆 Dell Cloud Native Award Champion, Agent M

A multi agent Agentic AI which performs web search and summarize the articles from the search.

Comprehensive course for NVIDIA-Certified Professional: Agentic AI (NCP-AAI) certification preparation

Agentic anime detection workbench: mock/Ultralytics backends, CLI/API/GUI, tool-calling agent.

Dead-simple, local-first, framework-agnostic agent observability.

Provenance-governed AI memory for agents: a self-evolving second brain in your IDE. Every write cites a source or it's refused. Markdown + grep.

👷 Docker-for-agents: build agents into runnable container images

An intelligent AI-powered legal assistant designed to provide accessible, quick, and simplified legal guidance to users. This project leverages modern AI capabilities to bridge the gap between complex legal information and everyday users.

Memory migration tool for the Claw AI agent ecosystem — WorkBuddy, OpenClaw, QClaw, CoPaw and more

Sybapse : Low-Latency Hybrid Edge Computing and Desktop AI assistant

Zoe - Your Local AI Life Hub & Personal Assistant

Full-stack AI-powered Personal Finance Tracker built with Python FastAPI backend, JWT auth, SQLite database, and Claude AI financial advisor. Track expenses, set budgets, get AI insights.

Archive Claude Code conversations to Obsidian via /save-chat, with cloud-shared multi-device config

Portable, self-contained snapshot of a complete Claude Code setup — 36 specialist agents, 161 skills, plugins, MCP servers & host tooling. Clone, claude login, run one script, restore the whole orchestration stack in ~20 min.

Open-source, AI-native apps that run entire departments — mapped to the role & industry they replace. 12 departments · 12 industries · 52 verified tools · one-command deploys. Self-hostable, provider-neutral, offline-capable.

Embed and edit videos directly within ComfyUI workflows using the OpenReel extension with timeline, effects, and server-side rendering.

面向中国 A 股研究的 Agent Skill：公告、财报、研报解析与因子候选生成

A SME Legal Agent for R2AI Competition 2026 - Achieved 1st Prize

A world model in your agent's toolbox - see what happens before it does.

A.M.Y (Autonomous Mind Yield) — autonomous scientific research system. 94 tools across 23 domains, cryptographic provenance, multi-agent paper pipeline (Ranking + Reflection), Apache-2.0.

基于 LangChain + LangGraph。Orchestrator（system prompt = mastermind SKILL.md 浓缩）经 delegate_attack / delegate_parallel 调度 5 个攻击 agent；旧 LangGraph 7-node 固定管线保留为 --mode scan 确定性回退。支持混合爬虫、改包重放、跨点价值链、JWT/GraphQL/prototype 检测、Triage 8 检查（含 SRC 合规）、docx/html 报告、Claude-Code 插件模式。

Turn a book or document into a modular Agent Skill pack: atomic skills, combo workflows, a router, references, and validation.

Use Codex and Claude Code with Ansys Workbench via sim-cli: journals, project inspection, persistent sessions, Mechanical handoff.

BandAI is a CrewAI-powered multi-agent orchestration platform that automates the discovery, adversarial legal evaluation, and proposal generation for Italian public tenders (bandi)

🏛️ Three AI models debate your question and give you a verdict — research-backed multi-agent debate via Anthropic, Google, OpenAI, or Ollama. My developer debut, feedback & contributions very welcome!

Self-hosted мульти-агентный комбайн на дешёвых LLM: 4 агента (recon/coder/assistant/planner), RAG, sandbox, автономные воркеры. Pydantic AI + LiteLLM.

⚡ Autonomous AI-cognitive wireless security agent — Gemini AI + WPS/PMKID/Handshake + swarm agents + hacker TUI | Kali Linux

🦀 A self-owning territory crab — an autonomous digital life that owns its goals and runs a life loop. The next molt after OpenClaw and Hermes.

Production-ready FastAPI + Agno gateway for serving AI agents — agents, teams, supervisor execution, skills, knowledge bases, OAuth tokens, toolkits, OpenTelemetry.

Zero Trust agent runtime for auditable AI-assisted engineering and research.

AI Skills 是一个按职业和行业组织的 AI 技能平台，提供即用型 AI 技能，覆盖短视频运营、多平台舆情分析、评论洞察、去水印等高频场景，帮助内容创作者、电商卖家和运营人员用 AI 提升 10 倍效率。同时支持Openclaw，hermes，qclaw安装执行。

A powerful AI assistant built with Python for desktop control, smart automation for desktop or home devices, Generating code, and conversational AI capabilities.

Local-first AI reader for academic papers — structured PDF parsing, cited RAG, translation, notes, and a desktop app.

SH-Jarvis: selbst gehostetes, deutschsprachiges KI-Assistenz-Oekosystem - Orchestrator/FastAPI, lokale LLM/STT/TTS, Gedaechtnis/RAG, Sprecher-ID, Autonomie, MCP, Pi- und ESP32-Sprachsatelliten mit Wake-Word Jarvis.

Local-first personal AI assistant & operating system — a real-life JARVIS / FRIDAY (Tony Stark–style AI): voice, autonomous agents, RAG memory, automation, and a fail-closed security broker. Runs entirely on your own machine.

Hermes Monitor — Pixel-art real-time AI agent monitoring dashboard for multi-persona teams

Stateless MCP server for Redmine. Each user brings their own API key; no database, no shared secret.

Turn a one-line idea into a production-grade, copy-paste-ready AI image prompt for posters, landing and UI mockups, ads, game art, and logos. A Claude Code skill optimized for gpt-image-2. MIT.

AgentPay - The economic-intelligence layer for AI agents — an x402 gateway that prices, caps, and receipts agent data spend. 17 free tools + verified_route, the buyer-side x402 trust oracle. USDC on Base or Stellar.

Turn AI coding chats into a source-controlled workflow: AGENTS.md, rules, skills, verification gates, and adapters for Codex, Claude Code, and Cursor.