Memory
tackroom runs no memory system. It captures nothing from sessions, indexes nothing and never writes a memory file. What it does is delivery: a file you list under instructions: goes into each harness's root instructions, so a memory file you keep reaches every session.
instructions:
- ~/agent-memory/MEMORY.md
Where a listed file arrives
Each harness's root file carries AGENTS.md followed by the files under instructions:, in order (setup.md).
- Claude Code gets a short
~/.claude/CLAUDE.mdof@pathimport lines, so your edits reach it without a sync. - Codex, Factory Droid, Pi, OMP, Qwen Code, GitHub Copilot CLI, Grok Build, DeepSeek Harness, Antigravity CLI, Devin, Gemini CLI and Amp get a generated copy. Run
tackroom syncafter you edit a listed file.tackroom statusreports the copy as drifted until you do, and the periodic job runs that sync for you. - Cursor and OpenCode get no root file from tackroom, so a listed file does not reach them.
- Kimi Code reads
~/.agents/AGENTS.mditself and gets no root file, so a listed file does not reach it either.
Where each root file lands is in harnesses.md.
Lay out the memory
Use the Agent Memory Repo format (MIT):
- Keep memory in its own git repository, not in your config root and not in a project.
MEMORY.mdis the entry point every session loads. Keep it short.- Each entry is one line, with optional metadata at the end:
[source: ...; added: YYYY-MM-DD]. [[path]]links to topic files. Paths start at the memory root and leave out.md. An agent reads a linked file when it needs it.
List MEMORY.md under instructions:, after the files that sit beside AGENTS.md:
instructions:
- SOUL.md # beside AGENTS.md in the config root
- ~/agent-memory/MEMORY.md # the entry point of your memory repository
A harness sees only the text tackroom copies or imports, not the folder it came from. Start MEMORY.md with one line that says where the linked files live:
# Memory
Linked files are in ~/agent-memory. A [[path]] link is relative to that folder.
- Prefers pnpm for Node work [added: 2026-11-16]
## Index
- [[projects/payments]]
Only what you put in MEMORY.md is loaded into every session. That is the review step: a fact reaches your agents once it is in that file, and not before.
Capture with rem
rem is a separate tool for review-first capture and consolidation. Install and use it as its repository describes. tackroom only registers its hook, like any other hook (hooks.md):
hooks:
- name: rem-session-start
enabled: true
event: SessionStart
command: ~/.local/share/rem/hooks/session-start.sh
timeout: 15
agents: [claude, codex]
Then run tackroom sync. The hook gives each session context at its start, including the head of the vault's MEMORY.md, so a harness that runs the hook gets that file twice if you also list it under instructions:. Notes you take with rem add stay unreviewed, and its dreams land on a branch you merge. tackroom does not install rem, so the script has to exist on every machine that syncs the hook.
Native harness memory
Some harnesses have a memory of their own. These are each harness's own features: tackroom only writes the key you declare under settings: (setup.md), and does not run, read or move that memory.
- Claude Code:
autoMemoryEnabled, on by default in local sessions, andautoMemoryDirectoryfor where it keeps that memory. Written to~/.claude/settings.json. See Claude Code memory. - Codex:
features.memories, off by default. Written under[features]in~/.codex/config.toml. See Codex memories. - OMP:
memory.backend,offby default. Other values such aslocalpick a backend. Written to~/.omp/agent/config.yml. See OMP memory.
To turn Claude Code's auto memory off on every machine:
agents:
- name: claude
enabled: true
detect: claude
settings:
autoMemoryEnabled: false
Removing a key from settings: leaves the value in the native file. To switch a feature back, set the key to its other value and run tackroom sync.
Other memory tools
A memory tool that is an MCP server or a skill is added like any other: see mcp.md and skills.md. engram and Basic Memory are examples of MCP memory servers; their own docs give the command to run.
The Agent Memory Repo skill is an external skill source:
tackroom skill sources add AgentMemoryRepo/agentmemoryrepo --skills agent-memory-repo
This pins a commit at least 3 days old and syncs the skill to your harnesses. The skill does its work only when you invoke it.
Coming from the bundled memory
Releases up to 2.8 shipped memory tiers (setup --memory basic or memsearch), memory scripts under memory/ in the config root, and the rem and knowledge-sync tools. They are gone. setup --memory is still accepted and does nothing (upgrading.md).
A config set up with an older release keeps working:
- The
memory-session-start,memory-session-endandmemory-stopentries intackroom.yamlare ordinary hooks now.synckeeps registering them as listed and never adds, edits or removes them. - While a hook entry in
tackroom.yamlpoints at a script undermemory/hooks/(in the config root or in~/.agents), every file undermemory/stays, whether the hook is enabled or not. The firstsyncorsetupdrops those files from.tackroom-starter.jsonand printsmemory/ in <root> is yours now. tackroom no longer updates or removes them, and deleting the hook entries later does not change that: remove the files yourself. - If you delete those hook entries before the first
syncorsetupwith this release,syncremoves the scripts undermemory/hooks/andmemory/lib/that you never edited. It lists each script you did edit once, askept (modified by you), and leaves it alone from then on. A hook registration in a harness's own config that still runs a removed or missing memory script, such as the Pi or OMP module an oldmemory-session-startentry generated, is removed with it and backed up first; one that runs a script you edited stays. - Go sources under
memory/tools/, theremandknowledge-syncbinaries in~/.local/binandmemsearch.confstay where they are. Nothing builds or updates them.
rem and knowledge-sync now come from the rem repository. To stop an old memory hook, set enabled: false on it and run tackroom sync (hooks.md).