0556GitHub
Jevwire: verify claims against cited evidence
An MCP server and decision library use Jev to judge whether evidence supports a claim, rank candidates, and classify proposed agent actions.
Public request code and tool policies were inspected on October 1, 2026. Claim verification can return supported, conflicting, or unaddressed verdicts with source locations and confidence-based escalation. Its Claude Code plugin adds advisory checks and a stop check. The builder explicitly says the agent can answer its tripwire and that it is not a security boundary. No claim of guaranteed safety or hallucination prevention is made here.
Brainwires/jevwireREADME ↗
# jevwire **Jev** is TypeSafe AI's [System One](https://docs.typesafe.ai/concepts/system-one) model: a fast, calibrated classifier. You give it a state and a map of typed questions — yes/no, pick-one, rate-on-a-rubric — and it answers every one in parallel with a probability over the answer space *you* defined. It never generates text, so the answer is always inside your schema. **jevwire** wires it into a harness. The repository is [Brainwires/jevwire](https://github.com/Brainwires/jevwire); the npm package is still published as `jevwire` and the Claude Code plugin is `jev`. It is three things: - **7 MCP tools** — `jev_rank`, `jev_pick`, `jev_verify`, `jev_evaluate`, `jev_gate_action`, `jev_next_step`, `jev_list_models`. - **An embeddable library** — `JevDecisionModel` plus a pure `run*` function per tool, so mandatory checks can live in your harness instead of in a tool an agent may decline to call. - **A Claude Code plugin** — hooks that put judgments at the harness boundaries: before a tool call, after a fetched result, before the turn ends. Everything they decide is addressed to Claude, not to you: a note about a call that already ran, or a single `deny` Claude can answer. As of 0.3.0 they never prompt you. It is **not** for generation, arithmetic, counting, date comparison, or multi-hop reasoning. It answers bounded questions over text you hand it. Anything numeric or ordered should be extracted as a choice over enumerated options and compared in code. Release 0.4.0 has been exercised against the live TypeSafe API on **2026-09-18**. Every latency, token count and cost figure quoted in this README comes from that run or the 0.3.0 one it is compared against. ## Install Node >= 20 for all three routes. ### Claude Code plugin ``` /plugin marketplac