I made a DuckDB extension where you can use @typesafeai 's Jev to do quick classification of rows in any csv/parquet file or duckdb table about 10sec for 1k rows ~ better than using an LLM, way more ergonomic than a classifier game-changing for data analysis!
SkillRanker
A Rust CLI that ranks agent skills for the next step with a two-stage Jev pass plus lexical prefiltering, with Claude Code hooks, a TUI, abstention, and --why-not explanations.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- Dicklesworthstone
- Added
- 2026-09-20
Tagscommunityrustclicoding-agentskills
Highlights
- Two-stage Jev ranking: a wide comparison followed by detailed reranking of a shortlist.
- Quill lexical prefiltering handles rosters above 254 skills before Jev sees them.
- Commands include sr rank, sr demo, sr hook claude, sr tui, and sr eval.
- Advisory only: it never loads or executes a skill, and explicit requests resolve locally.
Watch out
Requires your own TypeSafe API key; it is not an offline model, and offline replay and demos are non-actionable.
More like this
A Python asyncio runtime that puts Jev in a supervision loop above Codex or OpenCode workers: it judges completion, test sufficiency, and stuck loops, then steers, retries, or stops the job.
Tools & Integrations#community#python#coding-agent
Communityforeman
A local decision ledger for Jev-class models: caches decisions keyed by redacted model, schema, and state, replays them deterministically in CI, and publishes bundles without raw state.
Tools & Integrations#community#rust#caching
Communityjevcache
A staged code-review workflow that uses Jev for bounded judgments over Git diffs or whole codebases, with a local dashboard. Policy and thresholds stay in code while Jev screens five risk areas.
Tools & Integrations#community#typescript#code-review
Communityjev-review
From the community
Posts from builders shipping with Jev right now.
Classifying rows in DuckDB
The launch post
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x Show more
