Jev agents, skills & apps

Browser-grounded social research using Jev to choose bounded operations and socai CLI to execute them. Requires a configured provider and your own authenticated browser session.

Video search through MCP tools and an agent skill. Jev screens contact sheets and checks candidate frames to return timed matches; image support is experimental.

A coding-agent hook that asks Jev to assess tool-call risk, untrusted instructions and skill files. Coverage and approval behavior depend on the host integration.

A search application that uses Jev or another configured decision model to choose sources and rank results. It returns links, snippets and relevance scores rather than generated answers.

A self-hosted, versioned skill library with MCP access and scoped clients. Optional Jev recommendations rank skills for a task using your own provider key.

Kubernetes incident triage that keeps deterministic rules in code and sends only the judgement calls to a model.

A live multi-agent news pipeline at news.aatf.ai: GLM-5.3-Flash writes, Jev decides what goes in and where.

An experimental CLI that selects uncertain examples for labeling and uses GEPA to improve Jev AI Functions. Proposed changes require review; higher training scores do not auto-accept them.

Test agent skills against tasks in local or remote sandboxes. Inspect traces and choose a grading backend; TypeSafe/Jev is optional and requires its own key.

A browser agent with an indexed action space: Jev picks the operation and the target element, and a small LLM handles TYPE_TEXT.

Voice-controlled browser automation: speech becomes text, Jev selects intent and observed targets, and Playwright executes validated actions. Requires Chrome or Edge speech support and a TypeSafe key.

Routes Codex model calls using Jev choices for capability, thinking effort and route duration. Includes local fallbacks and decision logs. Requires a compatible Codex setup and provider credentials.