Stars
A lightweight MPEG-TS splicer multiplexer with automatic failover. Works in the uncompressed domain (no transcoding), so it runs on extremely low-end hardware—think $5/month VPS for an always-onlin…
gpt-5.1 enhanced commit messages. git commit -m "blah blah blah" looks at diff and turns it into something nice.
Benchmark that evaluates LLMs using 759 NYT Connections puzzles extended with extra trick words
This benchmark tests how well LLMs incorporate a set of 10 mandatory story elements (characters, objects, core concepts, attributes, motivations, etc.) in a short creative story
A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private conversations, form alliances, and vote to eliminate each other
A simple demonstration agent using the ReACT methodology for analyzing and executing tasks.
Annotated version of the Mamba paper
Language Modeling with the H3 State Space Model