memoryledger 0.1.0

Auditable long-term project memory ledger and AGENTS.md renderer

memoryledger

memoryledger is an auditable long-term project memory ledger and deterministic AGENTS.md renderer.

AGENTS.md is a generated entry point. Canonical durable memory lives in .memoryledger/.

Quick start

memoryledger init
memoryledger memory create --kind rule --title "Use plans" --text "Always plan before implementation."
memoryledger review accept memory-0001 --reason "User approved project rule."
memoryledger render --print
memoryledger export

The short alias memledger exposes the same CLI.

To build or update AGENTS.md, update memory records first, then render and export. Do not edit generated AGENTS.md files directly.

Rendered targets are owned only when configured and marked with <!-- Generated by memoryledger. Do not edit directly. -->. Do not edit those files directly. Files under docs/agents/ without the marker may be manual. Export refuses to overwrite any manual target, including when --backup is passed. Use memoryledger agents adopt for a read-only preview and memoryledger agents adopt --apply --backup for the dedicated adoption transaction. Adoption creates candidates by default; --accept requires --reason.

Example:

memoryledger memory create --kind rule --title "Use memoryledger for AGENTS" --text "Do not edit AGENTS.md directly; update memoryledger records and export."
memoryledger review accept memory-0001 --reason "User approved project memory workflow."
memoryledger render
memoryledger export

Additional intake commands are templates list/show/apply/sync/remove, evidence scan, and import run-html. All producer output remains candidate memory until explicit review. Structured evidence is managed with memory evidence list/add. Both memoryledger and memledger expose the same commands.