GitHub - Rudekwydra/burnless: Stop replaying the transcript: capsule session state + rolling memory for LLM CLIs (Claude Code, Codex). Measured: −90.3% vs no-cache / −30% vs cached replay at turn 10, reproducible bench. MIT, provider-agnostic.

Show HN: Burnless – 1,590 tokens of context for a 1.44M-token workday

Stop replaying the transcript: capsule session state + rolling memory for LLM CLIs (Claude Code, Codex). Measured: −90.3% vs no-cache / −30% vs cached replay at turn 10, reproducible bench. MIT, pr...

2 points by rudekwydra 85 days ago github.com 0 comments

Summary not yet generated for this article.

Original Text

I got pissed off at hitting my Claude token limit (who hasn't?). Watching tokens burn on every prompt more and more got me thinking.

So I built Burnless to fix this shit. MIT license, grab it and go.

Comments (0 of ) ⌛

Loading more comments... ⌛

Scroll down to load more comments

No comments available.