nipunbatra8/legalos

Stripped to OpenAI only

One architectural decision: drop the Claude/Gemini code paths and route all LLM calls through OpenAI. No other meaningful divergence from upstream is documented.

View on GitHub →

nipunbatra8's legalos fork swapped out the multi-provider LLM backend - Claude and Gemini are gone, OpenAI is the only inference target. That's the extent of the differentiation tracked here.

What's in it

OpenAI-only stack Every AI-powered feature runs through a single provider - OpenAI - instead of mixing Claude and Gemini.
Simplified deployment One vendor to configure, key, and bill for, which can mean a leaner setup if your shop already lives in the OpenAI ecosystem.

Direction

infrastructure

Activity

Themed changes and pull requests touching this fork, newest first. Themed changes that haven't been turned into a public post yet still appear — they're real work even without a published writeup.

📝 nipunbatra8 tears out every AI brain but OpenAI 1 commit 2mo ago infrastructurechat-ui draft

This fork drops its Anthropic and Google model support and bets everything on a single provider.

Threads of work (detailed view)

2 threads have been distilled into posts.

nipunbatra8 tears out every AI brain but OpenAI

This fork drops its Anthropic and Google model support and bets everything on a single provider.

infrastructurechat-ui

1 commit · latest 2mo ago

Claude and Gemini removed; fork goes OpenAI-only

nipunbatra8 rips out both existing LLM backends in a single commit and replaces them with an OpenAI-only implementation. A large, sweeping rewrite that touches 20 files and deletes ~980 lines. Not a feature addition - a fork-direction decision.

infrastructureintegration

1 commit · latest 2mo ago