Open source gpt-4 projects

Every project in the registry tagged gpt-4, ranked by real GitHub adoption.

projects 9 combined stars ★ 146K refresh nightly
01 Aider ★ 49K

AI pair programmer that works inside your terminal

last push4 months ago languagePython licenseApache-2.0
02 graphrag ★ 36K

A modular graph-based Retrieval-Augmented Generation (RAG) system

last push30 hours ago languagePython licenseMIT
03 DB-GPT ★ 20K

open-source agentic AI data assistant for the next generation of AI + Data products.

last push40 hours ago languagePython licenseMIT
04 Botpress ★ 15K

Build powerful AI agents with cutting-edge LLM technology

last push3 hours ago languageTypeScript licenseMIT
05 E2B ★ 14K

Secure cloud environments for enterprise AI agents

last push10 hours ago languagePython licenseApache-2.0
06 langroid ★ 4.1K

Harness LLMs with Multi-Agent Programming

last push36 hours ago languagePython licenseMIT
07 ruby-openai ★ 3.2K

OpenAI API + Ruby! 🤖❤️ GPT-5 & Realtime WebRTC compatible!

last push5 months ago languageRuby licenseMIT
08 DeepBI ★ 2.4K

LLM based data scientist, AI native data application. AI-driven infinite thinking redefines BI.

last push21 days ago languagePython licenseMIT
09 obsidian-textgenerator-plugin ★ 2.0K

Text Generator is a versatile plugin for Obsidian that allows you to generate text content using various AI providers, including OpenAI, Anthropic, Google and l

last push1 months ago languageTypeScript licenseMIT

Related tags

← all tags

Frequently asked questions

How many open source gpt-4 projects are there?

This registry tracks 9 projects tagged gpt-4, with 145,504 GitHub stars between them. The most-adopted is Aider at 49,021 stars.

Are these gpt-4 projects free to use?

Yes — 9 of the 9 carry an explicit open-source licence across 2 distinct licences, so there is no licence fee. Where a project also sells a hosted or enterprise version, the self-hosted path remains free.

Which gpt-4 project should I choose?

The list above is ranked by GitHub stars, but stars measure attention rather than fit. Check three things on each card: the licence (permissive versus copyleft), the language it is written in, and the last-push date — a high-star project that has not been pushed in a year is a liability.

Are these gpt-4 projects still maintained?

7 of the 9 were pushed in the last 90 days, and every card shows its exact last-push date so you can see the rest. Sort your shortlist by that date before committing to a migration.