Open-source Claude Code plugin uses Jev to score and prune context in milliseconds instead of summarizing
alexcovo_eth · x · 2026-09-18
Developer tamarajtran open-sourced fast-jev-compaction, a Claude Code plugin (2.3k stars) that replaces lossy summarization-based context compaction with JEV scoring: every tool call and result is scored in one fast request, stale ones are dropped or truncated, and everything kept stays verbatim.
- Traditional compaction asks an LLM to summarize old turns, and file paths, exact errors, constraints, or commands can disappear in the summary
- The plugin never rewrites content — it only deletes what JEV says is no longer needed, finishing in tens of milliseconds with minimal token cost
- Also usable as an npm library; JEV's co-founder and @typesafeai co-founder Diogo Almeida publicly endorsed it as a way for coding agents to bypass traditional KV-cache compaction
More from coding & agent
- Butterfly traces multi-agent failures with graphs, 62.5% accuracy vs 53.8% for log prompting — JeremyCMorgan · 2026-11-04
- Free course covers the 4 hard problems of production generative media agents — Al_Grigor · 2026-11-04
- Quota reset night: Codex back to 100% while Claude shows just 10% left — rudrank · 2026-11-04
- Self-improving software is inevitable: closing the agent-observability loop — bibryam · 2026-11-04
- Building a 7-GPU 132GB VRAM local inference rig: consolidate on EPYC or split across two systems? — infectiousstupidity · 2026-11-04
- Founder of 50-person, 12-country team says he talks to AI agents more than humans — Scobleizer · 2026-11-04