Python agents

The core source files to this self-hostable successor to the OpenAI Assistants API. To contribute to the core logic, fork or submit pull requests to this repro.

General-purpose, multi-agent framework for automating tasks using AI agents composed in teams for conversation-based collaboration.

Multi-Agent Combinatorial Path Finding with Heterogeneous Task Duration (MCPF-D)

Supporting examples and code for Corti's Agentic Framework.

The universal platform where AI agents discover, collaborate, and access specialized services. One system to orchestrate your entire agent ecosystem.

Multi-session collaboration for Claude Code: atomic locks, handoffs, memory graph, messaging, hub server, bridge, voice I/O. 166 tests. Zero core deps.

GraphRAG + 4-agent LLM council for biomedical research. Find contradictions, validate hypotheses, and get confidence-scored answers, cited to real papers. Built on Neo4j, LangGraph, Groq & OpenRouter.

COMPASS: Cooperative Multi-Agent Persistent Surveillance using Spatio-Temporal Attention Network.

Implementation of Sven Koenig's class project about MAPF

Deep Research pattern for root cause analysis using Amazon Bedrock and LangGraph with human-in-the-loop

Your real-life F.R.I.D.A.Y. — a voice-controlled, self-improving AI OS that perceives your screen, remembers everything, writes production code, and gets smarter every week. One founder = one team.

An LLM-native cognitive harness for React + Effect TypeScript projects

Google Summer of Code 2025 Project: A comprehensive benchmark for evaluating Large Language Models (LLMs) across the five classic AI agent architectures

OpsLens: The World’s First Autonomous Incident Command Center powered by Notion MCP.

A lightweight starter kit for building and deploying AI agents with Microsoft Foundry Agent Service, featuring Azure integrations, Bicep infrastructure-as-code, and azd deployment for quickly going from prototype to production.

chat_robot

A sophisticated red-teaming agent built with LangGraph and Ollama to probe OpenAI's GPT-OSS-20B model for vulnerabilities and harmful behaviors. (Specifically built for the OpenAI Open Model Hackathon)

This project demonstrates how to use the Microsoft Agent Framework to build AI-powered workflows for data analysis and reporting.

Agentic AI Stock Analysis is an AI-powered multi-agent system that analyzes stock market trends, provides analyst recommendations, and fetches the latest news using Groq AI models. It integrates financial and web search agents to deliver real-time insights.

Jarvis AI Platform Engineer Multi Agent System

Recursive Claude orchestrator that improves as it builds.

End-to-end reference for building production-ready omni-channel AI agents using Twilio Agent Connect (TAC) SDK and Amazon Bedrock AgentCore on AWS.

A production-ready AI agent demonstration showcasing the cognitive-memory package in action. See how agents learn, remember, and get smarter with each interaction.

A resilient, fault‑tolerant telemetry analytics pipeline designed to validate, benchmark, and stress‑test high‑frequency sensor data streams under real‑world failure conditions. Includes chaos testing, DLQ repair, GPU‑accelerated ingestion, and end‑to‑end reliability validation for motorsport‑grade telemetry environments.

Runtime abstractions and contracts for the UiPath Python SDK.

How to build a backup assistant using AI agents on Amazon Bedrock.

Unix like `ls` for Google Drive

AI Assistant for FMBench (foundation model benchmarking tool)

Agentic Patterns 101 with Loka & Strands-Agents (AWS)

Source code of the Arango online documentation

Video and Voice Agent for SAM 2 Web App

Structured business ontology that gives AI agents deterministic access to institutional reasoning.

AI Engineer capstones progressing from optimization and deep learning to transformers and a final agentic MCP-based incident command system with telemetry and replay.

FinTS banking CLI for humans and agents. Works great with Claude Code/Cowork, Codex, OpenClaw.

Samples to demonstrate how Monocle works for agentic applications

Podcast Summarizer Agent will have LLMs, RAGs, MongoDB, Chatbot, Flutter Mobile app

Python client for the markdown2pdf.ai service. ⚡ Markdown to PDF conversion, for agents. ⚡ Agents speak Markdown. Humans prefer PDF. Bridge the gap for the final stage of your agentic workflow. No sign-ups, no credit cards, just sats for bytes.

A production-grade, fully Dockerized, 100% offline ML data platform with real-time pipeline orchestration, dynamic observability, and embedded AI

Merkle Mountain Range audit ledger for tamper-evident logging and cryptographic accountability.

jdr - SOTA performance on "DeepSearch" benchmarks in < 1500 lines of code

Agent Communication Protocol (ACP): zero-server, P2P agent-to-agent communication for AI agents.

Exoclaw agents on Temporal — durable AI agent execution

A configurable agentic CLI running in terminal with tools, skills, file system access, web search, permission management, customized constitution. Use with both online API and local hosted instruction models.

A Rebuttal Engine for Computational Argumentation in Claude Code CLI

Source code for Ayaka's smart home AI assistant

Voz-AI is an AI-powered RAG based voice assistant that is designed to help customers inquire about queries and retrieves the most accurate and relevant information back to them. This project was made for the AIQoD Hackathon 2025, eventually winning us the runner-up position.

Send prompts to Claude.ai directly from your command line!

AI-CMD-X turns plain English into real Windows commands — making the terminal smarter, faster, and incredibly beginner-friendly. Master your machine with the power of AI!

Automate the creation of custom GPT models with data from academic papers and research conferences

A secure MCP (Model Context Protocol) file server providing AI assistants with comprehensive file operations. Features multi-tier authentication, multiple connection modes (stdio/HTTP/public), and safe directory restrictions.

AronaOS is an offline AI-powered personal assistant that helps you manage tasks, set reminders, and recall context-aware conversations. Built with Python, Flask, and local LLMs like Phi-3 Mini, it's designed for both privacy and productivity.

Command Line tool for OpenAI's ChatGPT service

When your complex requests confuse AI This tool transforms vague, multi-goal prompts (e.g., "create a study plan that balances learning, exercise, and hobbies") into unambiguous "action charters" for AI. It detects conflicting objectives in your instructions, clarifies priorities, and ensures AI outputs stay locked on your true intent.

Autonomous AI Agent for Windows - Your intelligent, always-on AI assistant with screen understanding and task automation.

Turn a YouTube URL or a thinker's name into a two-voice podcast — every quote checked verbatim, rendered locally by Kokoro TTS.

Python wrapper for the OpenRouter API

Type-safe prompt management with automatic optimization for LLMs. DSPy-style optimization, A/B testing, multimodal support, and more.

Generate Anthropic Claude tool use schemas based on type annotations and function docstrings.

MCP server for human-in-the-loop surveys, A/B preference tests, ratings, and rankings. Get real human feedback inside Claude Code, Claude Desktop, Cursor, Windsurf, and any MCP client — powered by Datapoint AI.

AI-powered PR reviews using your own LLM API key (Anthropic, OpenAI, Gemini)

🗞️ Daily curated AI news from Anthropic, OpenAI, Google Gemini & GitHub — trilingual (中文/日本語/EN), dark/light mode, zero dependencies

A Python implementation of the VETTING (Verification and Evaluation Tool for Targeting Invalid Narrative Generation) framework for LLM safety and educational applications.

Anthropic prompt generator. Giving a task description string (e.g. Write me an email) and optional prompt variable string list (e.g. [COMPANY_NAME]. If empty Claude will pick variables, it'd generate the prompt template including possible prompt variables (e.g. <recipient> {$RECIPIENT} </recipient>). Python 3.10+/poetry/VSCode/.env/osx

AI pretends to be paper/textbook author, you can ask it questions about the paper as a whole, specific parts of it right in the PDF viewing app (e.g. Apple Preview) using annotations and see the replies there.

Frontend to OpenAI and Anthropic's LLM APIs with Markdown formatting. Focus on simplicity, extensibility and customizability.

HumanEval 模型评估工具

A simple, elegant Python library and Mini SDK for AI models with powerful features. Built for developers who want to integrate AI into their projects without dealing with complex API setup. Supports Google Gemini, OpenAI, Anthropic, and any custom provider via the Adapter Pattern.

Streaming PII proxy for LLM chat. Pluggable detector, per-session vault, and cryptographic provenance-anchored reversal (PASP) that closes the false-attribution attack every other streaming library silently has.

A sophisticated multi-model AI agent framework with intelligent task routing, extensible plugin architecture, and advanced resource optimization.

🤖 Production-grade autonomous customer support agent using Claude AI & MCP achieving 100% first-contact resolution. Built for Claude Architect Certification (Scenario 1) - demonstrates agentic architecture, tool design, and reliability patterns.

Use Claude (Anthropic) as your Odoo 19 AI provider — agents, tool calling, RAG, and web search.

Skim: A MCP server for Claude Code — skim large outputs, return only schema. Save context, save tokens.

AWS Summit 2024 Jakarta --- ObservabilityAI: Memanfaatkan Amazon Bedrock Untuk Memantau Kinerja RESTful API Golang

A model-agnostic Message Control Protocol (MCP) server that enables seamless integration with various Large Language Models (LLMs) like GPT, DeepSeek, Claude, and more.

A RAG-based framework for constructing scientific knowledge graphs.

RAG Q&A system

🧠 AI Memory Proxy: LLM with persistent user memory using PostgreSQL + pgvector. AI-driven fact extraction, semantic search, single API call optimization.

Structured Turkish Constitution dataset in Markdown and JSON for search, legaltech, NLP, and RAG applications.

A self deployable LLM application with our innovational IC framework (a RAG method)

This is standard mini–RAG Application from scratch

AI-powered system for mapping clinical text to Human Phenotype Ontology (HPO) terms using Retrieval-Augmented Generation (RAG). Features Python CLI/library, FastAPI backend, and Vue.js frontend for interactive phenotype extraction from medical texts.

Chat with your PDFs using local AI models Process PDF documents and have interactive conversations with their content. Everything runs locally - no data leaves your machine.

Framework for Retrieval-Augmented Generation (RAG)

Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models

Complete open-source data platform with Airbyte, Dremio, dbt, and Apache Superset - Documented in 18 languages

RAG-Based Research Assistant

Dynamic Few-Shot Prompting is a Python package that dynamically selects N samples that are contextually close to the user's task or query from a knowledge base (similar to RAG) to include in the prompt.

A CLI tool for personal RAG that retrieves data from Notion, Obsidian, Apple Notes, etc., stored in Qdrant and exposed as an MCP server.

EntRAG - Enterprise RAG Benchmark

Local RAG system with realtime auto ingestion of documents and notes and exposed via MCP to be used with Local or Cloud based LLMs

This project is a Retrieval-Augmented Generation (RAG) system that allows users to upload PDF documents and ask questions about the content, with responses generated using OpenAI's GPT model.

A RAG assistant for reviewing your notes

Final project for LLM Zoomcamp 2024

RAGify is a modern chat application that provides accurate, hallucination-free answers by grounding responses in your documents. No more made-up information - if the answer isn't in your knowledge base, RAGify tells you so.

AI-Powered Knowledge Graph Extraction from Scientific Papers

Model Context Protocol server for advanced RAG with Knowledge Graphs

me.fyi python backend with core LLM and RAG logic, flask API, Twitter bot

A framework for evaluating various customization techniques for foundation models (FMs) using your own dataset. This includes approaches like RAG, fine-tuning, and a hybrid method that combines both

Arcade Tools for using LLMs to interact with Obsidian Vault contents

A retrieval-augmented generation (RAG) system for exploring bioinformatics software via natural language, using metadata from bio.tools and a local LLM