kunchenguid/compact-adviser
"Work appears completed or recorded. Run /compact to save tokens."
About the project
A plugin for agent CLIs (Pi, Claude Code, Codex CLI, Grok Build) that advises when to run /compact by using the Jev model to judge whether the current work unit is finished.
Useful for
- Get a hint on when to run /compact in Claude Code without losing context mid-task
- Auto-trigger /compact in Pi or Claude Code at a safe session boundary
- Check plugin key and install status via /compact-adviser status
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 0 stars so far today, about 50 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 2 days old and already has 71 stars.
- Top new repositories this week: #161.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 71
- Stars in a day
- 50
- Forks
- 4
- Issues and pull requests
- 37
- Watchers
- 0
- Language
- TypeScript
- License
- MIT
- Latest release
- compact-adviser-v0.1.3 · September 18, 2026
- Created
- September 17, 2026
- Last push
- September 18, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 19, 2026Top new repositories this week: #161
Similar projects
-
9.4
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.
-
8.5
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…
-
8.2
latent-spaces/brag
An agent skill (Claude Code, Codex, opencode, etc.) that turns a project you just built into a short launch video with music, motion, and share copy — in one command. Rendering is powered by Hyperframes.
-
7.2
Tencent/BrowserSkill
BrowserSkill connects AI agents (Cursor, Claude Code, Codex, etc.) to your already logged-in browser via the bsk CLI and an extension, letting the agent work in a separate window without interrupting you.
-
6.6
NandhaKishorM/laya
Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.
-
6.1
hypit-ai/hypit
Hypit gives AI agents a language and system to create video: the agent clones a viral clip as an editable workflow — footage, captions, B-roll and effects anchored to words instead of seconds.