# Reverify

> MIT claim-verify loop for agents — MCP + deterministic tools

**Category:** AI Agents  
**Pricing:** open-source  
**URL:** https://github.com/2akouwu/reverify  
**GitHub:** https://github.com/2akouwu/reverify  
**Added:** 2026-10-02

---

## The Hook

Reverify stops agents from asserting facts unchecked — the model proposes a claim, deterministic tools check ground truth, and only VERIFIED/REFUTED evidence becomes fact (CLI + MCP).

## What's Good

MIT (2akouwu/reverify). PyPI `reverify` (HTTP 200). `reverify verify` and an MCP server for Claude Code / Codex / Gemini CLI / OpenCode; `reverify rollover` hands long sessions to a file instead of lossy auto-summary. Strongest demos in binary/RE hallucination, but the claim→tool→evidence loop is the product.

## The Catch

★1254 in about 5 weeks (~251 a week): judge it on the verify fidelity, not the star count. Vs unlazy / promptfoo / ragas: unlazy is a completion-discipline skill (and uses “reverify” as a verb — different project); Promptfoo/Ragas are eval suites — Reverify’s catch is runtime claim verification against artifacts via tools/MCP. Coverage is only as good as the checkers you wire; pin PyPI and which harness MCP config you ship.

## Verdict

MIT claim-verify MCP/CLI when agents invent APIs and offsets — not unlazy’s Depth Tree skill and not Promptfoo/Ragas eval lanes; treat the star spike with caution.