remember

Run friction analysis, then consolidate session stashes + friction antigens into a single project-local MEMORY.md, and inject into AGENT.md. Friction runs automatically (best-effort) — there is no separate /friction command. A docs reconcile check runs at the end, detect-only.

Guardrails

• Favor straightforward, minimal implementations first and add complexity only when requested or clearly required.
• Keep changes tightly scoped to the requested outcome.
• Precision over recall for hot memory. A false antigen loaded into @MEMORY.md steers every future session. When unsure, do not promote — leave it to recurrence (a ledger observing entry at 2 sessions, nothing at 1).
• Mid-tier model, not hardcoded. Steps 2/3/4a delegate to your tool's balanced default tier — judgment-capable, cheaper and faster than your top reasoning tier. Not the cheapest/fastest tier: on judgment work it measurably degrades (misclassification rates several times higher). Never hardcode a vendor-specific model name.
• Batch stashes, don't fan out. Step 2 gives each extraction agent up to 5 stashes and uses as few agents as possible (3 stashes → 1 agent, 7 → 2). One agent reading several sessions sees the same lesson recur and writes it once; one agent per stash writes it once per stash and leaves the merge to catch the duplicates. If more than one agent is needed, run them concurrently.
• Hot memory is short snippets, not prose. A fact is one line, target 160 characters, hard stop 180, stating a rule the agent should follow next time. Events, history, and narrative are not facts.

What it does

Reads all raw material (.amp/stash/*.md + .amp/remember/friction/antigen_clusters.json), extracts durable facts, episodes, and behavioral antigens into a single .amp/remember/MEMORY.md, then injects a managed memory section into AGENT.md.

Steps

1. Run friction first (best-effort — friction analyzes ALL your usage, not just this repo)

   Friction's signal is global: recurring corrections and frustrations across every project are behavioral lessons worth keeping everywhere. So point it at the tool's global sessions root (all projects), not a per-project directory.

   • Locate friction.cjs — it is bundled next to this command at remember/friction.cjs (the same directory as remember.md, whether installed or run from the package). If it exists nowhere, skip to step 1 (stash-only) and tell the user friction.cjs is missing.
   • Check for a newer liteagents (best-effort, one line, never blocking) — bundled beside friction.cjs as remember/version-check.cjs. Call it by its absolute path, exactly as step 7 calls docs-builder.cjs: the cwd here is the target repo, not this package, so a cwd-relative path fails everywhere except the liteagents repo itself.

     node ~/.config/amp/commands/remember/version-check.cjs
     

     If that path does not exist, use the directory you just resolved for friction.cjs — the two ship side by side, so that directory is correct for a non-default install and when running from a checkout, where the path above would point at the installed copy instead of the one under test. It prints one advice line if the installed version is behind the registry, and prints nothing otherwise. It exits 0 on every path, caches the registry answer for 24h, and is bounded to ~2s, so it cannot stall this run. If it prints a line, relay it verbatim in your final report; never act on it and never run the install yourself.
   • If the script is missing from both locations, say so — one line, same rule as step 7's "applicable but could not run". A failed check (offline, registry down, timeout) stays silent by design: it is a once-a-day nudge, not a result anyone is waiting on. A missing script means the install is incomplete, which is worth a word.
   • Resolve the global sessions root — probe this list top-to-bottom, use the first that exists and contains .jsonl files directly, or one level down in per-project subdirectories (friction.cjs scans exactly those two levels, not a deep recursive walk). Never prompt the user.

     # ── Add your own global sessions root at the TOP so it is checked first ──
     ~/.claude/projects/                 # Claude Code
     ~/.factory/projects/                # Droid / Factory
     ~/.config/amp/projects/             # Amp
     ~/.config/opencode/projects/        # opencode
     ~/.codex/sessions/                  # Codex CLI  (use $CODEX_HOME/sessions/ if set)
     ~/.gemini/antigravity-cli/brain/    # Antigravity
     

     Note: friction.cjs parses Claude Code's session schema. The Codex/Antigravity roots will resolve but yield no signals until friction learns their formats — open an issue to request one: https://github.com/hamr0/liteagents/issues

   • Run node <friction.cjs> "<resolved-root>". friction writes its output to .amp/remember/friction/ in the current project.
   • On any miss — loud, never silent. If no root resolves, or friction errors, or it finds no usable sessions, print this and continue with stash-only consolidation:

     ⚠️ Friction didn't run — no sessions found. To enable it, open this command file (remember.md) and add your tool's global sessions root to the TOP of the probe list in step 0, then re-run /remember. Consolidating stashes only this time.