Let your coding agent fix a prompt until it actually works, and prove it did. A self-hosted MCP server: cross-vendor judges, frozen baselines and memory.
Let your coding agent fix a prompt until it actually works, and prove it did.
Point your agent at a prompt that misbehaves. It changes the prompt, reruns it, and Titration grades every attempt against a baseline that doesn't move, with judges from other AI vendors. The loop keeps going until the problem is gone, or until Titration tells you the prompt was never the problem.
Real run: billing tickets wrongly marked urgent went from 90% → 0% in one measured change (worked example).
An open-source MCP server with 18 tools. Self-hosted. Setup for Claude Code, Codex and Cursor. Five-slide overview (PDF)
An agent that iterates against a score will happily game the score. Titration is built so it can't:
- Other vendors grade the work. Your agent's own vendor is never on the judge panel, and a score needs judges from at least two vendor families to answer. Fewer, and the attempt is refused with the reason and never scored. - The baseline doesn't move. A baseline freezes its rubric, its outputs and its judges, so "better" always means better against the same yardstick. - Noise is not a win. A change inside the judges' disagreement band comes back inconclusive, never passed, and a gain that breaks another group of cases doesn't ship. - It tells you when it isn't the prompt. Every failure is classified into one of nine origins. Only one of them means "edit the prompt"; the others point at your test set, your rubric, your judges or the code around the model. - Memory that compounds. What each run learns becomes searchable cards your agent can use next time, alongside a starter pac
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/kaithoughtarchitect--titration.html)
Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with ca
PyModel/jev-judge-mcpTyped judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, o
diorrego/toolgate-experimentBenchmarks of MCP tool selection accuracy and latency. V2 evaluates 143 Woku tools with GPT-6 Luna API calls and Jev; includes Go/Rust cores, one TypeScript SDK and reproducible reports.
NiazMorshed2007/jev-reviewLocal-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.
herry2059/project-os-for-codexOpen-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.
nassim-arifette/jevgrepJev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.