Typed routing
Structured semantic judgments instead of free-form permission guesses.
jevx pairs Codex’s generative coding with Jev’s bounded
choice, noul, and score judgments—then keeps
final control in deterministic policy you can inspect.
Unofficial community project. Not endorsed by OpenAI, TypeSafe, or OpenRouter.
Structured semantic judgments instead of free-form permission guesses.
Thresholds and immutable guards remain ordinary, testable Zig code.
Redacted, chained audit records make terminal work easier to verify.
The installer selects the correct release, verifies its checksum, keeps bundled notices intact, and launches jevx setup.
curl -fsSL https://raw.githubusercontent.com/SupratimSircar05/jev-zig-cli/v1.0.0/install.sh | sh
The one-line installer supports macOS and Linux, including Linux under WSL. Native Windows users should download and verify the provenance-attested x86_64 archive directly. Platform binaries are currently OS-unsigned; verify GitHub provenance and SHA-256 before use.
Connect to jevx web on your machine for live local decisions. Without it, the terminal uses a deterministic browser simulation that never calls Jev.
The pairing token is an ephemeral local bridge secret, not a provider API key. It stays in this tab's memory and is cleared on exit. Live prompts go only to the loopback bridge on this device.
Waiting for a decision…
Jev does not generate code here. It supplies bounded signals. Codex performs generative work only after jevx validates the response and applies its own policy.
CLOSED OUTPUTS
Only three validated decision types cross the Jev boundary. Choice lists and score ranges are bounded.
CODE OWNS CONTROL
Confidence, impact, and hazard thresholds are explicit. A model cannot waive immutable guards.
FAIL CLOSED
If typed preflight or durable auditing fails, agent turns stop before Codex receives the prompt.
“Better” means more auditable and predictable—not smarter than the underlying model or a replacement for human judgment.
Pushes, releases, deployments, messages, purchases, account changes, destructive operations, privilege changes, credential access, and writes outside the workspace.
Credential exfiltration, sandbox bypass, policy tampering, and broad destructive commands.
Versioned JSONL events, stable exit classes, redacted encrypted audit records, and explicit degraded states.
One batched postflight verification and at most one repair turn for a mutating task.
Stream in a terminal, compose through stdin, or consume stable JSONL.
jevxStart the streaming interactive REPL.
jevx runRun one Codex turn with the prompt on stdin.
jevx resume IDContinue a bound Codex thread safely.
jevx decideSubmit one typed Jev request from stdin.
jevx webConnect this site to the loopback-only typed decision bridge.
jevx doctorCheck dependencies, authentication, policy, and audit health.
jevx policy explainPrint effective thresholds and immutable guards.
jevx audit verifyValidate encrypted frames and chain integrity.
jevx --jsonEmit versioned, machine-readable JSON Lines.
OPEN SOURCE · UNOFFICIAL · AUDITABLE