bicameral

Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.

How it uses Jev

A hybrid coding harness for Pi. System 2 (any LLM Pi runs) writes the code. System 1 (TypeSafe Jev , trained with Reinforcement Learning for Calibrated Decisions / RLCD) returns typed probabilities. Deterministic policy code turns those scores into allow / confirm / block / warn / steer .

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 bicameral

Browse all
reflex (kaustav1996) project preview
A coding agent and personal assistant with System One reflexes (TypeSafe Jev) on top of the Pi coding agent
athena-jev project preview
Agent tooling
ATHENA gives coding agents reflexes - an open-source cognitive control layer powered by TypeSafe Jev.
jevmem project preview
Agent tooling
Jev decides. The LLM writes one line. Your project never forgets. Jev-powered memory layer for AI coding tools.
jev-browser (vinilana) project preview
Browser & computer use
Hybrid browser harness: an LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, Playwright acts.
jevcumber project preview
Browser & computer use
Write Cucumber tests with just the .feature file. No step definitions — Jev (TypeSafe AI) resolves each Gherkin step and Playwright runs it.
jev-gate project preview
Benchmarks & research
Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.
evoke project preview
SDKs & clients
Software, by reflex. A sentence becomes a call of a small program, chosen by Jev, TypeSafe AI's classifier, and run only when it is sure enough. Reflexes are recipes anyone can write, share and improve. A CLI you talk to, a package manager for reflexes from git, and a TypeScript SDK.
hundred project preview
Games & simulations
100 AI NPCs live in a tiny town. Jev chooses the next action; the world writes the story.
jev-compaction project preview
Demos & playgrounds
A context compactor that can only score, never write — so an agent's memory can't hold a fact the transcript never contained. Working demo, runs offline.