Python agents

A neutral protocol for coordinating intent across humans and agents. Goal lifecycle, state, auditability.

Local-first agent OS. Spawn persistent AI agents that collaborate, write code, and use tools autonomously. Multi-model (Claude, Codex, LM Studio). Config-driven with pre-built agent presets.

Blackwall is an intelligent security agent built on top of the Swarms framework that provides real-time API protection

Madrox — Multi-Agent Orchestrator for Claude & Codex. MCP server that spawns, delegates, and coordinates parallel AI agent teams via tmux.

🤖 Orchestrate AI agents for seamless teamwork in software development, enabling efficient collaboration through dependable messaging protocols.

Enable multi-agent orchestration for Claude Code with parallel execution, automated quality checks, and coordinated management tools.

Professional multi-AI development environment with intelligent cost optimization (<5/month)

Open Source 24/7 Autonomous Agentic AI System

Super simple autonomous agent that can organize complex projects, surf the web, write code, and run commands locally on your machine. Uses a free Gemini API key.

Optimal stopping agents powered by generative large language models

A Pydantic Ai powered app that converts social media posts or videos into structured cooking recipies.

Eval-first AI agent that triages property maintenance emails. The real work is the eval system around it: trace-driven error analysis, code graders and validated LLM-as-judge (TPR/TNR), component and end-to-end evals, a failure taxonomy, and a CI regression gate. LangGraph, FastAPI, Langfuse.

A standalone cognitive memory system for AI agents with advanced human-like learning patterns.

An Openclaw-like assistant designed to be lightweight and intuitive.

The protocol to give AI apps your life's context

An AI agent that decides how I spend my hour. Composes a daily commute briefing from email, podcasts, AI videos, and gym classes — narrated by ElevenLabs, mixed with Lenny's actual podcast voice, delivered to my iPhone.

Structured OpenAI Agents SDK guide with daily topic updates, practical code examples, and inline explanations.

Meta-Agentic Ai Orchestration Platform For Developers and Data Scientists Developing Full-Cycle(E2E) AI Projects

Build and manage intelligent hybrid AI agent systems that combine multiple models to enhance automation and decision-making.

Analyze and rate KOL pricing and reach with data-driven tools for clear, efficient influencer marketing decisions on Douyin and similar platforms.

Airline customer service agent on AWS Bedrock AgentCore with dual-memory: conversation history + Solutions Memory for successful cases. Users click "Like" to save resolutions for future reference. Includes Gateway policy engine, MCP tools, and Cognito auth. Handles refunds, delay compensation, and loyalty rebooking.

AI-driven design optimization of a 3D-printable anti-glugging vortex funnel. Automates the loop: parametric CadQuery geometry → OpenFOAM CFD (interFoam VOF multiphase via Docker) → multi-fidelity Bayesian optimization (scikit-optimize) — driven end-to-end by a Claude Code skill.

Unified MCP server for all League of Legends Riot API endpoints.

Convert natural language to terminal commands using AI. Simply AI helper in the Terminal

A Model Context Protocol server for Microsoft SQL Server

Anti-Gravity: The Agentic OS that turns AI (Antigravity, Cursor, Codex, Claude Code, Gemini CLI, OpenCode, VS Code) into disciplined senior engineers. A 150+ file architecture featuring persistent memory, execution workflows, and state-of-the-art UI/UX generation.

AI-powered Medical Chatbot providing health-related assistance and symptom checking using NLP techniques.

🤖 NoCapGenAI is a Retrieval-Augmented Generation (RAG) chatbot built with Streamlit, Ollama, MongoDB, and ChromaDB. It features a clean, modern UI and persistent vector memory for context-aware conversations. Easily integrates with Ollama-supported models like phi3:mini, llama3, mistral, and more. Designed to support customizable assistant modes

JARVIS-level AI assistant with 70+ features: Voice control, Computer Vision, AR, Gesture recognition, Multi-provider LLM (6 providers), Bug bounty automation, Code generation, Business intelligence. 2-4x more powerful than ChatGPT!

An AI-powered portfolio analysis assistant for Zerodha Kite users, built to learn MCP + LLM + RAG + Agentic AI fundamentals

Self-hosted AI character roleplay system. 100% local, zero data leaks. Your conversations stay on YOUR computer. Open-source Character.AI alternative using Ollama.

🧬 灵魂存档 — 通过日常对话静默构建你的数字人格克隆体 | A silent engine that builds digital personality clones through everyday conversations

A Telegram chatbot I spent $800 vibe coding

AI SMS Auto-Responder for Android. Turn your Android device into an autonomous AI communication hub. A Python-based SMS auto-responder running natively on Termux, powered by LLMs (OpenRouter/Ollama) with a sleek Web & Terminal UI.

An interactive learning platform for college classmates featuring an AI chatbot, flip cards, and topic-based resources to make studying easier and more engaging.

Python-Godot bridge for AI character control powered by OpenRouter API. VRM model management, animation playback, expression triggers, event handling, and bidirectional socket/godot-rl communication.

DingTalk group chat bridge for Claude Code. Send messages, receive @mentions, auto-execute prompts via Stream SDK.

Um código que implementa machine learning e IA para criar um chatbox, como chatGPT, que responde perguntas relacionadas ao banco de dados que foi conectado. Isso demonstra o poder da IA + ML para reduzir tempo de procura por respostas simples e assim o foco pode ser em partes mais importantes. Na versão 1.0 é esperado que reduza até 15% do tempo

Welcome to SocialChatBot, your multi-platform, personality-driven chatbot for Instagram and Snapchat. SocialChatBot isn’t just another bot—she’s a fictional 22-year-old art history student in Berlin, with a sharp wit, a unique style, and a memory for your conversations. She’s designed to make every chat feel real.

A local emotional AI chatbot built with Python + LLaMA3 via Ollama. Powered by memories, feelings, and conversation — an AI companion that truly remembers.

Chat with YouTube videos using AI - paste a URL, get transcripts, ask questions

Local Codex CLI prompt refinery: ingest JSON/JSONL histories, dedupe, embed (OpenAI), cluster (sqlite-vec), synthesize atomic/workflow prompts via Responses API (Structured Outputs). FTS5+vector search; Streamlit UI; Typer CLI.

🛡️ Advanced Voice Authentication System using OpenAI ChatGPT & Whisper APIs. Secure voice biometric identification with AI-powered analysis, multi-sample enrollment, and enterprise-grade authentication logging. Python-based with SQLite database.

AI Assistant Manager is an open-source tool designed to simplify the management of OpenAI Assistants. It provides a suite of tools and services for creating, listing, and deleting assistants, as well as handling vector stores and retrieval files.

🌊 GW150914 MCP Signal Search: AI-powered gravitational wave detection using Model Context Protocol (MCP). Features optimization client, analysis server, and automated parameter exploration for LIGO data.

A powerful multi-agent framework optimized for Chinese scenarios and Baidu ecosystem integration

Comprehensive cost & token usage analyzer for Claude Code with detailed breakdowns by model and token type. Uses ccusage CLI tool and LiteLLM pricing data. The raw token usage data is available in ${HOME}/.claude/projects/<project-name>/<conversation-id>.jsonl files.

A Claude skill that turns Claude into a rigorous reasoning and sparring partner — honest engagement, calibrated pushback, current sources, reuse before reinvention.

Multi-model Telegram bot (aiogram v3) with OpenRouter model picker (Llama, DeepSeek, Claude, Grok). FSM, async processing, HTML rendering, anti-flood.

🔍 Extract and analyze your Claude Code conversation history to discover usage patterns, generate insights, and create custom slash commands from your prompting style.

A framework for LLM-orchestrated research and audits. Multi-prompt, multi-session, context-disciplined.

WCAG 2.1 accessibility agent built on Anthropic API. Audits, evaluates and fixes digital products for UX, UI and development teams. Includes an installable Skill for Claude.ai and a full CLI with PDF/DOCX export.

基于 AI 大模型的代码分析系统，自动生成项目功能概述、技术栈分析、架构设计、实现原理，并输出 Mermaid 可视化图表（架构图、流程图、类图、时序图等）。支持实时流式 AI 输出与 Markdown 预览。

Agentic Proposal Generator: Multi-agent AI system using Claude Agent SDK that converts B2B discovery call transcripts into business proposals.

AI-assisted KiCad PCB design using Model Context Protocol and Claude

Multi-Layer AI Quality Assurance for Content Generation. Multiple LLMs evaluate, score, and approve every output before delivery.

Open source regulatory radar for financial services compliance teams. Monitors BoE, FCA, MAS, SEC, and ESMA, mapping publications to six control frameworks with a cryptographic audit trail.

AI decision workflows that turn enterprise documents into traceable decisions, executive artifacts and operational handoffs.

面向小说创作场景的半自动化辅助系统

🧠 Transform documentation chaos into a structured memory system with Mnemos, your self-hosted, multi-context knowledge server for developers.

Turn your PDF collection into clean text your AI can actually read. Mac app.

微信公众号文章总结器 | AI-powered WeChat article summarizer with RAG, GraphRAG, MCP, and multi-platform export

Semantic search over your Gmail, from inside Claude Code. Embeds your full inbox with zembed-1 and reranks with zerank-2 — finds emails by meaning, not keywords.

Wiii is an open-source durable AI workbench for conversations, local and cloud agents, files, tools, memory, artifacts, and permission-aware integrations.

An intelligent local AI agent powered by open-source LLMs, featuring free web search, hybrid memory, and context-aware query rewriting for real-time, grounded answers.

Distributed document RAG system with intelligent GPU/CPU orchestration. Auto-discovers heterogeneous nodes, routes workloads adaptively, and achieves 60x+ speedups through VRAM-aware load balancing. Privacy-first architecture with 4 interfaces (CLI, API, MCP, Web UI). Real distributed systems engineering, not just an API wrapper.

A Genshin Impact Question Answer Project supported by Qwen1.5-14B-Chat

[ICMR 2026] Official Repository for The Paper, Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach

Question-answering system for Zotero libraries with a 3-stage RAG pipeline: FAISS retrieval → CrossEncoder reranking → extractive QA. Features GROBID parsing, question expansion, multi-color PDF highlighting, and Streamlit interface. Ask questions, get answers with sources.

RAG-less document QA that loads an entire document into the LLM KV cache once, saves it to disk, and restores it before every query. No embeddings, no vector DB, no chunking. Drastic latency cut on static corpora.

Partition API used by Agentset

Agentic AI Platform for intelligent database interaction

一个为 Dify Workflow “量身定做”的 Telegram 群聊机器人。

High-performance RAG system for intelligent document Q&A with hybrid retrieval, GPU acceleration, and citation-backed answers. Upload docs, ask questions, get precise responses.

Musubi (結び) — Ai Agent shared memory and thought layer. The braiding of threads between presences.

ZIM-based retrieval augmented proxy for OpenAI-compatible AI

A fully functional conversational AI system for restaurant phone ordering using Twilio, Whisper, LLM, and RAG

This MCP server enables LLMs to retrieve and process web scraping requests using ScraperAPI.

AI-CLI 时代的 data lens:把 Claude Code 的 jsonl 实时镜像成可读 HTML,带跨 session 搜索 / 知识图谱 / 自动周报。零 token,单文件 Python。

Local-first MCP gateway for federating stdio and HTTP servers through one endpoint

An intelligent, stateful Customer Support Agent built with LangGraph and LangChain. It categorizes incoming queries, analyses their sentiment, and either routes them to the right specialist handler or escalates negative-sentiment queries to a human agent.

Autonomous AI Agent for B2B Lead Generation & Enrichment

AI HR Agent is first free and open-source AI chatbot for HCM System

Claude agent for use with the Mangrove Developer API & MCP Server.

Terminal-based agent runner that turns any LLM into a disciplined software engineer. FSM control, circuit breakers, model-agnostic. Bring Your Own Auth.

Claude Plugin for CompChem , Drug Discovery & Organic Chemistry reasoning

Self-hosted A2A client and control plane for managing and invoking multiple A2A agents across web and mobile.

一人公司的 AI 执行团队 — 你说需求，它出成果 | One-Person Company AI Agent: input requirements, get deliverables

Local deep-research multi-agent system: Planner / Finder / Summarizer / Reviewer / Writer pipeline with SSE telemetry, durable session + report persistence (SQLite), PDF + Markdown exports. FastAPI + LangGraph + Ollama on AMD ROCm.

SentinelEye is an Autonomous AI Agent for WhatsApp powered by Gemini 2.0. Features include Contextual Search (Rewriter), Infinite Cloud Memory (MongoDB), Vision capabilities, and Self-Planning logic. Built with FastAPI & Docker.

An agentic AI-powered organizer of your files. Built from scratch (no frameworks, no cloud APIs, fully local via Ollama) as a learning/podcasting exercise.

跨平台资源搜索编排器 for AI Agent — 一句话搜遍 15 个源，找 Skill/MCP/Prompt/开源项目

LLM-driven chess agent with three modes — Battle (you vs AI), Teach (AI-generated lessons), Watch (LLM vs LLM). Plug in OpenAI / Gemini / Claude side-by-side. Voice chat with character personalities + emotional TTS. LangGraph state machine. Optional Interbotix RX-200 robot arm + RealSense camera for physical play.

Security scanner for AI agent SKILL.md files. Static analysis, LLM behavioral prediction, and Docker Sandbox execution.

Access Twitter timelines, bookmarks, and profiles from the terminal without requiring API keys, offering a simple CLI user experience.

Own your AI from any device. Lightweight secure agent (~1100 lines Python) that smart-routes Telegram/Web Chat messages to Claude or Ollama. Docker, 6-layer security, persistent memory. One command to start.

AI chat application that lets you create and expose RAG chatbots

Partner 🤝 Your AI Research Companion. "What have you been doing?"

NJUIM 数据科学与数据分析2026Spring 小组项目

A toolkit for AI agents to explore and attempt Erdős's 1,179 unsolved mathematical problems