pi-fast-jev-compaction

Pi extension: verbatim context compaction with TypeSafe Jev decisions

How it uses Jev

@joelhooks/pi-fast-jev-compaction

Highlights

  • Sends a compact representation of tool calls and surrounding conversation to TypeSafe's /v1/systemone endpoint.
  • Asks two noul questions per eligible tool call: keep the call and keep its result.
  • Keeps the first message and recent messages pinned.
  • Applies three monotonic decisions:
  • keep : preserve the pair.
  • drop result : preserve the tool call and a deterministic head of its result.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to pi-fast-jev-compaction

Browse all
omp-jev-compaction project preview
Agent tooling
Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter
opencode-context-pruner project preview
Continuous verbatim context pruning for OpenCode, powered by TypeSafe Jev. Port of fast-jev-compaction adapted to OpenCode's context hook.
pi-jev-context (Nyarlathoteppppp) project preview
Cache-neutral context trimming for the pi coding agent, powered by TypeSafe Jev: long tool output cut to verbatim key lines before it enters context, with lossless recall. Measured, with pre-registered benchmarks.
jev-compaction project preview
Demos & playgrounds
A context compactor that can only score, never write — so an agent's memory can't hold a fact the transcript never contained. Working demo, runs offline.
hermes-jev-skills project preview
Browser & computer use
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
unclutter project preview
Browser & computer use
WXT browser extension: Jev-powered page clutter removal with reusable template rules.
barrunto project preview
Browser & computer use
A Chrome extension that brings TypeSafe's Jev to X.com to analyze posts as you browse
jevmory project preview
Benchmarks & research
Coding-agent memory where every fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence. Local-first, SQLite receipts, zero dependencies.