Maximem Synap — Agent Memory Skill (Codex)

Synap is a managed memory layer for AI agents: it ingests conversations/documents, extracts structured knowledge (facts, preferences, episodes, entities), and serves ranked, scope-aware context back at retrieval time. No vector DB to run, no retrieval pipeline to build.

This is the Codex edition. The integration knowledge — reference/, scripts/, examples/ — is byte-for-byte identical to the Claude Code skill; only this manifest and AGENTS.md differ. Read only the reference files you actually need.

Sandbox & approvals (read first)

This skill does real work in the user's repo, so the procedure needs capabilities Codex gates behind approval. State what you need before you start; don't assume silent execution:

• Network access — to pip install maximem-synap / npm install @maximem/synap-js-sdk and the framework package, and for the SDK to reach Synap Cloud at runtime.
• File writes — to add integration code and (if missing) a git-ignored .env.
• A secret — the synap_... API key. Ask the user to provide it; never print it back or commit it.

If running with restricted network/filesystem, tell the user which commands to run themselves.

Procedure — the order to do this in

There is no CLI. Provisioning happens by hand in the dashboard; the SDK only uses a key that already exists. Do not skip the PAUSE.