Repo · Safety & guardrails
Models are getting smarter.
Models are getting smarter.
Open github.com ↗From the repository
Intent as Code | the workflow language for AI. One file, 4 verbs, one Rust binary. Local-first, any model, AGPL-3.0. 🦋
agentsaiai-agentsai-workflowsautomationclidagdeveloper-toolsdevopsllmlocal-aimcpollamarustself-hostedstructured-outputworkflowworkflow-automationworkflow-engineyaml
How builders describe it
Models are getting smarter. I care about what they’re allowed to do next. I’m building Nika, an open-source governed runtime for AI workflows. You describe a workflow in .nika.yaml, Nika checks what it’s allowed to do before execution, runs models/tools/agents, can stop for human approval, and…
The decision Jev makes
Allow, flag or escalate a message, tool call or action.
Where it fits
Screening messages, tool calls and outputs before they cause trouble. Jev gives a fast, calibrated verdict that can sit in front of every request or agent action. All 229 safety & guardrails projects →
Related projects
Safety & guardrailssnapifRust crate and CLI that scores one agent tool call against a shipped policy and returns Auto, Review or Escalate, using TypeSafe Jev…GitHub · ★ 2 · snapif
Safety & guardrailsjev-sec.github.ioJev IDS website: one flow.GitHub · ★ 2 · jev-sec
Safety & guardrailsclaudetiquetteClaude Code plugin that rewrites a hostile prompt into a plain request.GitHub · ★ 2 · zahlekhan
Safety & guardrailsdsh-backdoor-guardGuard for DeepSeek Harness: every model-requested tool call is judged by a decision model, hosted TypeSafe Jev or a self-hosted LiquidAI d1, before…GitHub · miketako3
Safety & guardrailsopencode-auto-classifierOpenCode plugin that sends each shell command, file read, and edit to TypeSafe Jev for typed classifications, then folds those answers into…GitHub · schemaitat
Safety & guardrailspi-thunder-guardSafety guard for Pi: before each bash call (and writes outside the repo) TypeSafe Jev must be at least 85% sure the call keeps to a short restriction…GitHub · Mandalorian007