Skip to content
JevDirectory.org
CommunityTools & Integrations3 starsVerified 2026-09-22

fast-jev-compaction

A Codex plugin and npm library that wraps native session compaction: Jev scores every tool call and result, and the verbatim history it keeps is re-injected after Codex summarizes. The README does not recommend using it.

Open github.comleonaaardob/fast-dev-compaction
Category
Tools & Integrations
Published by
Community
Author
leonaaardob
Added
2026-09-22
Tagscommunitytypescriptcodexcompactioncoding-agent

Highlights

  • PreCompact replays the rollout JSONL, pairs tool calls with results by call_id, and asks two noul questions per non-pinned call.
  • After Codex compacts, a SessionStart hook emits the kept history as additionalContext capped at FAST_JEV_CONTEXT_CHARS with a pointer to the full file.
  • PostCompact reports kept, truncated, and dropped counts, state size, and request count as a systemMessage.
  • The README warns against using it and cites Theo's critique that pruning on a probability threshold misunderstands compaction and cache rewrites.
  • It falls back cleanly: a Jev failure, missing key, unfittable transcript, or insufficient reduction leaves Codex's built-in summary unchanged.

Quickstart

bash
codex plugin marketplace add leonaaardob/fast-dev-compaction
codex plugin add fast-jev-compaction@fast-jev-compaction
export TYPESAFE_API_KEY=YOUR_API_KEY

Watch out

MIT-licensed with the compaction engine from tamaratran/fast-jev-compaction; needs Node.js 18+ and TYPESAFE_API_KEY or a key file, and the author calls it an experimental proof of concept rather than a tool to run.

More like this

save-token-jev
63GitHub stars
A Jev-guided context compaction library for coding agents: instead of summarizing old context, Jev decides which tool calls and results still matter while user and assistant text is kept verbatim.
Tools & Integrations#community#typescript#compaction
Communitysave-token-jev-clean
Yoshi
22GitHub stars
An experimental local context-pruning proxy for Claude Code and Codex that asks Jev, through the Vercel AI Gateway, which history spans to omit, then forwards a rewritten request with omission markers.
Tools & Integrations#community#typescript#compaction
Communityyoshi
Fast Jev Compaction
6.2kGitHub stars
A Claude Code plugin and npm library that replaces transcript summarization with Jev keep-or-drop judgments, deleting stale tool calls and results while kept text stays verbatim.
Tools & Integrations#community#typescript#claude-code
Communityfast-jev-compaction
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Instant compaction with Jev

A Claude session from 1M to 86K tokens

Alex Volkov
Alex Volkov
CoreWeave
@altryne
·

This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be  Show more

Image
Image
tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Watch on X
Reply
Read 164 replies

Vercel's fx safety reviewer, 18x faster

Guillermo Rauch
Guillermo Rauch
Vercel
@rauchg
·

We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.

Pranit
Pranit
Vercel
@fazxes

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

Image
Reply
Read 137 replies

Jev lands on OpenRouter

700 leads scored for $0.09

Beating Gemini Flash Lite on an eval