UditAkhourii/quicksilver
Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.
About the project
A Claude Code skill that offloads bulk yes/no judgment calls (which files, lines, or tickets matter) to TypeSafe's Jev model and returns only a shortlist to Claude. Cuts Claude token usage by 86% and speeds up such tasks up to 20x.
Useful for
- Filter 187 repo files down to the ones handling auth
- Triage 3000 log lines to find real failures
- Classify support tickets by intent (Banking77)
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 0 stars so far today, about 7 expected by the end of the day.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 3 days old and already has 73 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #179.
- Recent forks include notable developers: @IoTeacher (360 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 73
- Today
- 0 · ≈ 7 by evening
- Forks
- 4
- Issues and pull requests
- 0
- Watchers
- 2
- Language
- JavaScript
- License
- MIT
- Created
- September 25, 2026
- Last push
- September 25, 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 28, 2026Top new repositories this week: #179
More in this category
-
9.0
vectorize-io/hindsight
Hindsight is a long-term memory system for AI agents that stores facts and observations rather than just conversation history, reporting state-of-the-art results on the LongMemEval benchmark. It runs as a server…
-
8.7
paperclipai/paperclip
Open-source Node.js and React platform for orchestrating a team of AI agents: goals, org chart, budgets, tickets and audit. Suits teams running autonomous agents (Claude Code, Codex, Cursor, etc.) and wanting to manage…
-
7.7
dzhng/jevgrep
A CLI for coding agents that finds relevant files and source excerpts in a repository from a question about code behavior. It uses Jev for relevance ranking and requires a Vercel AI Gateway, TypeSafe, or OpenRouter key.
-
6.9
mvschwarz/openrig
OpenRig is a harness orchestrator for AI coding agents: a team of agents (Claude Code and Codex) is defined in YAML and booted with one command, turning scattered terminal sessions into a managed team with a lead agent.
-
5.8
Contrastive-LM/CLM
CLM is a class of System One language models trained contrastively to connect states and actions; the repo serves CLM-8B behind a TypeSafe-compatible API for fast agent decision-making.
-
5.5
AgentSystemLabs/agent-office
A 3D cartoon office where a team hires Claude Code, OpenCode or Codex workers at desks, watches their live terminals, chats by voice, and tracks GitHub issues and PRs per project floor.