jevskill

Teach your coding agent to stop burning context. Jev (System One) via OpenRouter or TypeSafe: 325ms, 0.000013 USD per decision. A/B tested 99.3% fewer input tokens with accuracy up. Ships a reversible reduce and a ledger that learns when Jev pays off.

How it uses Jev

▶ Live today at 20:00 — Jev vs ASTRA6: building the fastest ComputerUse, live in Claude Code

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to jevskill

Browse all
limpet project preview
Agent tooling
A Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev.
jevymarket project preview
Agent tooling
Polymarket trading bot driven by Jev (TypeSafe AI) via OpenRouter
hermes-jev-approvals project preview
PoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.
jev-mode project preview
Benchmarks & research
I kept watching coding agents burn context on decisions that aren't hard - triage 400 tickets, tag 600 files, route to one of six teams. jev-mode moves those verdicts to a typed-judgment model. I A/B'd it: 78% fewer tokens, 16x less work-attributable input, accuracy 96.1% vs 93.7%. Python, no deps, MIT.
stuntd project preview
Demos & playgrounds
Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.
jev-search (larguesa) project preview
Benchmarks & research
Experimental semantic line search with TypeSafe Jev via OpenRouter. Python CLI with no runtime dependencies.
Browser & computer use
A browser agent that turns a single goal into a sequence of lightning-fast actions.
typesafe-vs-deepseek project preview
Benchmarks & research
TypeSafe (Jev) vs DeepSeek-flash: side-by-side speed/token/cost/accuracy comparison across invoice extraction, email classification, and reranking
jev-ultrafast-mcp project preview
Browser & computer use
Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome.