Git Based Memory Storage for Conversational AI Agent

Project management system for Claude Code using GitHub Issues and Git worktrees for parallel agent execution.

What the Package Does (One Line, Title Case)

D2 is a modern diagram scripting language that turns text to diagrams.

A CLI tool to access ChatGPT from the terminal without an API key

The Open-sourced Multimodal AI Agent Stack connecting Cutting-edge AI Models and Agent Infra.

MemU is an open-source memory framework for AI companions—high accuracy, fast retrieval, low cost. It acts as an intelligent "memory folder" that adapts to different scenarios, from different compa…

The agentic-research-engine is a next-generation multi-agent research system designed to transcend the limitations of current agentic paradigms. Our mission is to build a system capable of genuine …

Live Deep Research Bench. A challenging, objective benchmark for deep research tasks.

Lightweight MCP integration bringing Google's Gemini AI capabilities to Claude Code with 1M+ token context window, smart model selection, and powerful code analysis tools

EvalBench is a flexible framework designed to measure the quality of generative AI (GenAI) workflows around database specific tasks.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

LangChain/Airflow hybrid orchestrator

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Auto-writes OpenAPI spec & docs

Redacts PHI & outputs compliance notes

A CLI and GitHub Action that unifies multi-agent development workflows, integrating frameworks like AutoGen and CrewAI. It streamlines the coding process by automatically ranking tasks from a backl…

A Cookiecutter template for rapidly building agentic startups. It provides a reusable skeleton that wires together CrewAI, FastAPI, and a React frontend with Shadcn UI components.

Two-agent PR reviewer loop

An interactive playground for an agent that translates natural language queries into SQL. This project adds a comprehensive evaluation framework against standard benchmarks like Spider and WikiSQL,…

Vision: Automate the entire early‑stage startup loop— ideation, validation, MVP delivery, go‑to‑market, and kill‑or‑pivot decisions—using a swarm of open‑source AI agents.

NL-to-SQL with schema discovery

Suggests minimal secure Dockerfiles

A Text-Based Environment for Interactive Debugging