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.

2 best points · 2 comments · 3 Hacker News posts · 7 GitHub stars · View on GitHub

Hacker News discussions

• Burnless – open protocol that cut my API bill 16x on my heaviest dev day (2 points, 0 comments, by rudekwydra, 2026-05-04)
• Show HN: Burnless – 1,590 tokens of context for a 1.44M-token workday (2 points, 1 comments, by rudekwydra, 2026-07-29)
• Show HN: Burnless makes LLM context a protocol. Token savings are a side effect (1 points, 1 comments, by rudekwydra, 2026-07-30)