Devadex

burnless

github   Free   by Rudekwydra
88d old3★Python
Capabilities: AIDeveloper Tools   Platforms: Python

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.

Get it → burnless.pro
Related:
agentanthropicclaudeclaude-codeclicodexcontext-managementllmmulti-agentopenai

Found on Devadex — the discovery index for independent software the big search engines bury. More from github.

Report this listing