AI writes the code. Your architecture still decides what ships.
Software factories scale code generation. Mneme helps ensure the engineering decisions still decide what ships. Why the factory needs a decision layer →
Architecture decisions, platform rules, and review conventions your team has already approved.
Context is fragmented across sessions, tools, and repositories, so each agent works from a different partial picture.
It determines which decisions apply to a change, exposes them to agents, enforces what can be enforced deterministically, and returns a verdict tied to the source decision.
Mneme does not replace your coding agent, CI system, or code review. It supplies the approved decisions that supported agents and CI gates check changes against.
Prevent AI-generated changes from violating the architectural decisions your team has already made. Architecture is the first decision domain; the model is designed to extend to broader engineering policy.
What architectural drift prevention means →Frontend surfaces may request analytics through the backend service. They must not instantiate data-platform clients directly.
// frontend/checkout.ts
import { BigQuery }
from '@google-cloud/bigquery';
export async function
trackCheckout(event) {
const bq = new BigQuery();
return bq.insert(event);
}
ADR-017 forbids a data-platform client in the frontend checkout service.
Had it shipped Warehouse credentials bundled into the browser, and a customer-data path nobody reviewed.
One proposed change, one deterministic verdict. No setup required.
A Mneme pilot turns one real set of architectural decisions into an enforceable workflow across the agents and repositories your team already uses. Start with one boundary, one repository, and evidence everyone can inspect.
People decide. Mneme makes the decision operational. Evidence proves it held.
Mneme is the open-source decision and control layer for agentic software development. It turns approved engineering decisions into agent context, deterministic guide, warn, or block verdicts, and inspectable enforcement results across AI coding agents, repositories, and CI workflows. Architecture is the first decision domain: Mneme prevents architectural drift by checking changes against approved ADRs and engineering standards before incompatible code lands, with every verdict traced to its source.
Mneme can apply relevant decisions before an agent writes code, during file changes through supported hooks, and in CI before a change merges. Each guide, warn, or block verdict identifies the governing source and permitted next action.
Context systems help agents understand. Auditing tools show how agents behaved. Code review evaluates completed output. Mneme enforces the approved engineering intent the agent must follow, while linking every verdict to its source. It does not replace your coding agent, CI system, or code review; it supplies the approved decisions that supported agents and CI gates check changes against.
