Backpass

backpass

Gradient descent for your agent memory.

This blog post explains the why and how.

backpass helps you improve your AGENTS.md, CLAUDE.md and skills with scientific rigor.
It finds the agent sessions that actually ran in your repo, reads
what happened in them, and proposes evidence-backed edits to your memory surface - the
memory file and project skills - under a token budget, gated by you.

- Local-first - Reads the transcript stores of seven agent harnesses directly from disk,
  locally or over SSH to your own machines. No API, no upload; transcripts never leave your
  machines except into an agent you already authenticated, and obvious secrets are redacted
  before they do.
- Evidence-gated - Every proposed edit carries verbatim quotes from real sessions,
  and every add, rewrite, or remove edit needs evidence from at least two distinct
  sessions. Small, noisy, bounded steps - not a rewrite.
- Human in the loop - Analysis never writes.
  See Apply - the human gate for review and explicit scripted decisions.

One run is one bounded gradient step.

Quick Start

Requires Node >= 22.5 and acpx on your PATH.
The default backpass apply review UI also requires lavish-axi
on your PATH; install it with npm install -g lavish-axi. To review in the terminal instead, run
backpass apply --no-ui.

backpass has no API keys of its own. Every model call goes through acpx to a harness
you have already authenticated.

User-level memory

A run is one scope. The default is the checkout you are in. backpass --scope user
trains the always-loaded user file and user-level skills from Claude Code and Codex
sessions across projects, and writes only those files. A project-scoped run never
writes a user-level file.

Canonical user memory is the first existing file in this order:…