mimicry

Rewrite AI drafts in your own voice with a bounded TypeSafe feedback loop.

How it uses Jev

Set OPENAI API KEY and TYPESAFE API KEY in the local .env file or process environment. Keys stay server-side. References and draft text are sent to OpenAI and TypeSafe; requests and responses are saved locally under ignored runs/mimicry/ . Optional STYLE WRITER MODEL and STYLE JUDGE MODEL override the defaults gpt-5.6-luna and jev-1.13.0 . The writer uses the OpenAI Responses API.

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

Keep exploring

Similar to mimicry

Browse all
jev-voice project preview
Applications
Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.
draftpulse project preview
Applications
Experimental: live X draft viral scorer powered by TypeSafe Jev
jevibe-check project preview
Applications
A live tone labeler for Bluesky posts and drafts, using TypeSafe's Jev API.
jev-paper-judge project preview
Demos & playgrounds
Feedback on your paper in seconds.
Jev for robotics
A MuJoCo xArm7 pick-and-place experiment. Jev selects an intent and bounded Cartesian directions; the shared controller applies motion and checks physical feedback. The published comparison is one recorded trial per controller, not a success-rate benchmark.
decido project preview
SDKs & clients
Probabilistic decisions for Python. Use Jev or bring your own provider; crawl with Playwright.
laya-browser-agent project preview
Benchmarks & research
Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwright/CDP, MCP-friendly.
jev-code project preview
Agent tooling
Bounded TypeSafe Jev workflows for coding agents.
jev-mobile project preview
Browser & computer use
Fast structured Android control loops with TypeSafe Jev and Mobile MCP