AI product Open source
backpass is a local-first command-line tool that analyzes coding-agent session transcripts and proposes evidence-backed edits to an agent memory file such as AGENTS.md or CLAUDE.md, plus project skills. It treats the memory file as weights, agent sessions as forward passes, and their on-disk transcripts as a loss signal, then collects sessions for the current repository, distills failures, aggregates repeated instruction changes, and produces diffs and skill extractions.
The tool reads transcript stores from seven agent harnesses directly from disk, requires evidence from at least two independent sessions for a new instruction, and limits each run to at most five edits. Proposed changes include verbatim session quotes; analysis never writes files, while `backpass apply` presents each edit for human acceptance or rejection before applying it. It is distributed through npm or npx, requires Node.js 22.5 or later and `acpx`, uses no API keys of its own, and sends no transcripts to a separate service; obvious secrets are redacted before model calls through an already authenticated harness.
1 use taken from transcripts — each links to the moment in the video.
A tool that analyzes local coding-agent transcripts for repeated failures and proposes small instruction changes. Proposals quote real sessions, require evidence from multiple sessions, and wait for approval before writing rules.
1 in the library.