8000 The Deck install does not set up the brain, so tier-3 agents have no memory · Issue #21 · simon-inkie/inkie-deck · GitHub
[go: up one dir, main page]

Skip to content

The Deck install does not set up the brain, so tier-3 agents have no memory #21

Open

Description

@simon-inkie

Problem

Tier 3 produces live agents with no long-term memory: no observations, no reflections, no era summaries, no context injection, no recall. Nothing in the Deck repo mentions installing the brain, and the leak gate lists the memory-layer repository's name as a forbidden term (scripts/leak-gate.mjs:211), so Deck's docs cannot even link it today. The brain is its own public repository (inkie-the-brain, v0.3.0) with a QUICKSTART, but that is written for a single Claude Code user, not for Deck's multi-agent layout.

Evidence

Seen in test: a full search of the tree found nothing wiring memory into Deck's install path. Background: an internal integration plan (2026-08-14) recommended a packages/brain inside this monorepo; the memory-layer project has since shipped as its own public repo, so this issue assumes that shape instead.

Things found while reading the memory-layer repo that this issue depends on:

  • Deck's create-agent.sh already writes AGENT_NAME into each agent's .claude/settings.json, which is tier 1 of the memory repo's silo resolution. So once hooks are wired, each agent lands in its own memory silo with no extra routing. Missing: the hooks, a USER_NAME value, and the seed kit that the memory repo's agent init <name> command creates.
  • Paths disagree: create-agent.sh defaults INBOX_ROOT to ~/.the-vault/agents, INSTALL.md uses ~/deck/inbox, the memory repo uses ~/.the-brain/agents. The memory repo's persona-inject hook reads ~/agents/<name>/CORE.md, which Deck's templates do not ship.
  • The memory repo's own setup helper expects the checkout at a fixed path and greps settings for a matching build path; a clone named differently does not match. Its systemd units make the same assumption.

Proposed fix (Deck repo)

This is the Deck-side half of a two-repo fix; see the linked brain-repo issue for the prerequisite work there (memory-loop config, corrected docs, non-interactive install command). Deck-side, once that lands:

  • M1, memory loop, on by default for tier-3 agents. INSTALL.md tier 3 gains a "memory" step that runs the brain repo's install command; create-agent.sh wires the hooks into the agent's own .claude/settings.json (per agent, not global), sets USER_NAME, and calls the memory repo's agent init <name> to seed the silo. If the brain is not installed, create-agent.sh says so and continues (memory off), never fails.
  • M2, semantic search, guided. INSTALL.md gets a "give your agents recall" section: a vector-DB dependency (Docker; on WSL, Docker Desktop's WSL integration or Docker Engine in Ubuntu), an embeddings API key in the brain's own env file, a first index build, and create-agent.sh adds the recall MCP server to each agent's settings when M2 is detected. Mark the paid-key boundary the same way tier 3 marks the model CLI.
  • M3, watcher daemon, guided. One INSTALL.md subsection pointing at the brain repo's systemd units; tie in with issue 8 and requirement A so the watcher starts with Deck.
  • Skills and tools for agents. packages/base/templates/TOOLS.md names the memory layer concretely instead of "if you have a memory/recall system"; create-agent.sh installs the brain repo's recall instruction into each agent home.
  • Deck seam. Relax the leak-gate rule so the public memory-layer repo's name and URL are allowed (with a self-test proving the internal variants still fail); document the path convention (persona in ~/agents/<name>/, memory in ~/.the-brain/agents/<name>/, inbox under INBOX_ROOT) in packages/base/docs; decide whether templates ship a CORE.md for the persona-inject hook. No Deck code imports the brain; integration stays files on disk.

Acceptance criteria

  • A fresh user following only Deck's INSTALL.md (including the WSL section) ends with tier-3 agents that write observations to their own silo after a /compact, and, with M2 done, can find that observation via recall search.
  • Deck still boots, and tiers 1 to 3 still pass, with no brain installed; create-agent.sh reports memory as off rather than failing.
  • pnpm check:leaks and its self-test pass with the brain linked from Deck's docs.

From the 2026-09-27 Windows/WSL install test.

Activity

  1. simon-inkie commented on Sep 27, 2026

    @simon-inkie
    OwnerAuthor

    Brain-repo companion issue (prerequisite work): simon-inkie/inkie-the-brain#11

  2. simon-inkie commented on Nov 19, 2026

    @simon-inkie
    OwnerAuthor

    Slice 1 merged (PR 230): opt-in setup.sh --memory, pinned build, jq and Node 22 checks. Still open: the recall template and a verified real Brain build with a signed-in compaction.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    installInstall / setup flowpriority:P1Blocks a normal user

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions

      0