# tamaratran/fast-jev-compaction

> Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also usable as an npm library.

- Magnitude: 1.4 out of 10 — Steady
- Stars: 7,832 total · +5 stars measured 2026-11-02, 00:13–20:05 UTC, ≈ 6 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2026-09-17 · Last push: 2026-09-18
- GitHub: https://github.com/tamaratran/fast-jev-compaction · Page: https://gitnova.dev/en/r/tamaratran/fast-jev-compaction

## Useful for

- Install the plugin in Claude Code so /compact keeps exact paths and errors
- Call compactMessages in your own agent to drop stale tool calls without summarizing
- Tune keepThreshold and truncateHeadChars to fit your token budget

## Why it’s here

- Star-counter measurements on 2026-11-02 (UTC), 00:13–20:05: 7827 → 7832 stars (+5). This is the change over that interval.
- Estimated end-of-day forecast: about +6 stars, using observed gains and the previous day.
- The repository is 46 days old and already has 7,832 stars.
- Top new repositories in the last 4 months: #90.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 575
- Issues and pull requests: 156
- Watchers: 14
- Average over the last week: 10 per day
- Usual pace: 33 per day
- Stars in the last hour (measured): 0

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-04 … 2026-11-02: 32, 48, 21, 41, 47, 29, 21, 18, 22, 13, 13, 24, 27, 13, 4, 19, 20, 11, 8, 9, 13, 10, 15, 6, 12, 8, 11, 13, 11, 5

## Magnitude by day, last 14 days

10-20 1.8, 10-21 1.8, 10-22 1.6, 10-23 1.5, 10-24 1.4, 10-25 1.6, 10-26 1.8, 10-27 1.7, 10-28 1.5, 10-29 1.6, 10-30 1.4, 10-31 1.5, 11-01 1.6, 11-02 1.6

## Spotted in now

- Top new repositories in the last 4 months: #90

## More in this category

1. **pingdotgg/t3code** — 9.6 · Breakout · AI agents · TypeScript · +3,387 stars measured 2026-11-02, 00:07–19:53 UTC, ≈ 4,000 by evening
   T3 Code is an agent harness control surface for agents on your machine, with mobile (iOS, Android), web and Electron desktop apps. It works with your Claude Code, Codex, Cursor, Grok Build, OpenCode and Google Antigravity subscriptions if…
   Full card: https://gitnova.dev/en/r/pingdotgg/t3code.md
2. **deepseek-ai/dsh-superagent-prototype** — 9.5 · Breakout · AI agents · TypeScript · +5,520 stars measured 2026-11-02, 00:07–19:53 UTC, ≈ 6,554 by evening
   Research prototype of a proactive coding agent for a single GitHub repository, packaged as a bundle for DeepSeek Harness: it listens to GitHub and Feishu, opens work items and replies in the original conversation, for example with a pull…
   Full card: https://gitnova.dev/en/r/deepseek-ai/dsh-superagent-prototype.md
3. **storytold/craft-anything** — 9.4 · Breakout · AI agents · Rust · +2,523 stars measured 2026-11-02, 00:07–19:53 UTC, ≈ 2,967 by evening
   A pure-Rust reverse-engineering engine with 284 tools that inspects websites, apps and games, then has a coding agent rebuild a similar version and checks the result against the original.
   Full card: https://gitnova.dev/en/r/storytold/craft-anything.md
4. **vercel-labs/agent-desktop** — 8.8 · Breakout · AI agents · Rust · +1,324 stars measured 2026-11-02, 11:38–19:53 UTC, ≈ 1,600 by evening
   Rust CLI that lets AI agents control desktop apps via macOS accessibility trees, with stable element refs and a snapshot-to-action loop. Combines a native binary with a C-ABI cdylib for Python/Swift/Go/Node bindings.
   Full card: https://gitnova.dev/en/r/vercel-labs/agent-desktop.md
5. **Donchitos/Claude-Code-Game-Studios** — 8.0 · Breakout · AI agents · Shell · +1,117 stars measured 2026-11-02, 00:07–19:53 UTC, ≈ 1,330 by evening
   A Claude Code configuration that turns a single session into a structured game studio: 49 specialized subagents, 74 slash-command skills, hooks, rules and templates mirroring a real studio hierarchy. It adds design reviews, QA passes and…
   Full card: https://gitnova.dev/en/r/Donchitos/Claude-Code-Game-Studios.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-02 20:10 UTC, updated every 30 minutes.