Multi-source brains

A single modusbrain database can hold multiple knowledge repos. Each one is a source: a logical brain-within-the-brain with its own slug namespace, its own sync state, and its own federation policy. The rest of this guide walks the three canonical scenarios.

The three scenarios

1. Unified knowledge recall (wiki + gstack)

You have a personal wiki and a gstack checkout. Both belong to you, both are knowledge you want your agent to recall across. When you ask “what did I learn about X?” you want the best hit whether it lives in the wiki or in a gstack plan.

# Register the gstack source, federate so it joins cross-source search
modusbrain sources add gstack --path ~/.gstack --federated

# Pin the directory so `modusbrain sync` knows which source it's walking
cd ~/.gstack && modusbrain sources attach gstack

# Initial sync
modusbrain sync --source gstack

# Now `modusbrain search "retry budgets"` returns hits from BOTH wiki and
# gstack. Each result includes source_id so the agent can cite properly.

Result: wiki pages and gstack plans are separate (different source_ids, different slug namespaces) but share the search surface.

2. Purpose-separated brains (team-media + personal-list)

You run two completely different content pipelines on the same backend. Team Media covers portfolio news and founder profiles. Shubham’s List is personal writing. You explicitly DON’T want them mixed in search — company portfolio content leaking into essay searches is a bug, not a feature.

# Two sources, both isolated (federated=false)
modusbrain sources add team-media --path ~/team-media --no-federated
modusbrain sources add personal-list --path ~/writing --no-federated

# Pin each checkout directory
(cd ~/team-media && modusbrain sources attach team-media)
(cd ~/writing && modusbrain sources attach personal-list)

# Sync each independently
modusbrain sync --source team-media
modusbrain sync --source personal-list

Result: searching from neither directory returns the default source (your main brain). Searching from inside ~/team-media returns only team- media hits. Searching from inside ~/writing returns only personal-list. Federation is opt-in, not leaked. To search across them explicitly on demand:

modusbrain search "tech layoffs" --source team-media,personal-list

3. Mixed (wiki federated + sessions isolated)

Your main wiki is federated with a few trusted sources. Your session transcripts (coming in v0.18) land in a separate isolated source so they don’t dominate every search result.

# Federated sources
modusbrain sources add gstack --path ~/.gstack --federated

# Isolated source (future v0.18 — sessions use this shape today for ingest)
modusbrain sources add sessions --path ~/.claude/sessions --no-federated

Resolution priority

When any command needs to pick a source, modusbrain walks this list (highest first):

Explicit --source <id> flag.
MODUSBRAIN_SOURCE environment variable.
.modusbrain-source dotfile in CWD or any ancestor directory.
A registered source whose local_path contains the CWD (longest prefix wins for nested checkouts).
The brain-level default set via modusbrain sources default <id>.
The seeded default source.

So inside ~/.gstack/plans/ on a brain that pinned gstack to ~/.gstack via .modusbrain-source, modusbrain put-page implicitly writes to the gstack source. Outside any registered directory with no env/dotfile set, it writes to the default.

Federation flag

Every source row stores config.federated: boolean in its JSONB config.

Value	Meaning
`true`	Source participates in unqualified `modusbrain search "X"` results.
`false` (default for new sources)	Source only searched when explicitly named via `--source <id>` or qualified citation.

The seeded default source is federated=true so pre-v0.17 brains behave exactly as before — every page appears in search. Flip later with modusbrain sources federate <id> / unfederate <id>.

Commands

Full subcommand reference:

modusbrain sources add <id> --path <p> [--name <n>] [--federated|--no-federated]
                               Register a source. id: [a-z0-9](?:[a-z0-9-]{0,30}[a-z0-9])?
modusbrain sources list [--json]   List all sources with page counts + federation state.
modusbrain sources remove <id> [--yes] [--dry-run] [--keep-storage]
                               Cascade-delete a source (pages, chunks, timeline).
modusbrain sources rename <id> <new-name>
                               Change display name only; id is immutable.
modusbrain sources default <id>    Set the brain-level default.
modusbrain sources attach <id>     Write .modusbrain-source in CWD (like kubectl context).
modusbrain sources detach          Remove .modusbrain-source from CWD.
modusbrain sources federate <id>
modusbrain sources unfederate <id>

Citation format for agents

When agents receive multi-source results they MUST cite pages in [source-id:slug] form. Example:

You told me about the distillation protocol — see [wiki:topics/ai] and [gstack:plans/multi-repo] for where this came from.

The citation key is sources.id (immutable). Renaming a source via modusbrain sources rename changes the display name only; existing citations keep working.

Writing to a specific source

# Pass --source explicitly
modusbrain put-page topics/ai ... --source wiki

# Or rely on the dotfile / env / CWD match
cd ~/.gstack && modusbrain put-page plans/multi-repo ...
# → source auto-resolves to gstack

Reads span federated sources by default. Writes require a resolved source (explicit, inferred, or default). The resolver never picks a source silently when ambiguous — it errors with a clear fix.

Durability: keep a brain repo in sync (auto-harden)

A long-lived agent that writes to a knowledge-wiki git repo needs three things to never lose work: pull before it edits, push every write, and not go stale while it sits idle. modusbrain sources harden installs all of that, idempotently. The moment you add a brain repo with a token, it runs automatically:

# Clone + register a GitHub repo, then auto-harden it for durability.
# Use a fine-grained PAT scoped to just this repo.
modusbrain sources add wiki --url https://github.com/you/brain-wiki.git --pat-file ~/.secrets/wiki-pat
#   → clones, then installs: local auto-push hook, scripts/brain-commit-push.sh,
#     always-on durability rules in AGENTS.md/RESOLVER.md, a 30-min pull cron,
#     and a repo-scoped credential. Verifies push works before declaring done.

# Run the same audit on an existing source any time (idempotent):
modusbrain sources harden wiki --pat-file ~/.secrets/wiki-pat

# Pull on demand (the cron calls the --path form, which never opens the DB):
modusbrain sources pull wiki

# Remove the durability scaffolding (also runs automatically on `sources remove`):
modusbrain sources unharden wiki

What hardening guarantees:

Pull-first, conflict-safe. Every pull is a divergence-safe rebase. A dirty working tree is skipped (your in-progress edits are never touched); a rebase conflict is aborted cleanly and flagged for attention, never left half-applied.
Push is never deferred. scripts/brain-commit-push.sh "<msg>" <path> commits and pushes atomically and refuses to report success without a confirmed push. The post-commit hook is a best-effort background fallback; the helper is the guarantee.
No silent staleness. A 30-minute background pull keeps an idle session current. It runs DB-free, so it never contends with a live brain for the PGLite single-writer lock.

Flags: --no-cron skips the scheduled pull, --no-verify skips the push probe, --dry-run reports what would change, --json emits a machine report, --all hardens every source with a remote (same-account only). --no-harden on sources add opts out of auto-harden. Security: the push automation is installed locally per machine (never committed into the repo), the token is wired per-repo (an existing credential helper is reused when present), and it never appears in the repo, the remote URL, logs, or the JSON report. For a self-hosted git server reachable only over a filesystem path, set MODUSBRAIN_GIT_ALLOW_FILE_TRANSPORT=1 (default is HTTPS-only).

Upgrading an existing brain

modusbrain upgrade runs the v16 + v17 migrations automatically. Your existing pages all move under source_id='default'. Behavior is unchanged until you add a second source. To add one:

modusbrain sources add gstack --path ~/.gstack --federated
cd ~/.gstack && modusbrain sources attach gstack && modusbrain sync

Two commands. The existing default source is untouched.

Not in v0.18.0

Session transcript ingest (.jsonl, raised size cap, session PageType) — v0.18.
Per-source retention/TTL (modusbrain sources prune) — v0.18.
ACL enforcement via caller-identity — v0.17.1.
modusbrain sources import-from-github <url> one-shot bootstrap — patch release after the core plumbing stabilizes.

All of these build on the sources primitive shipped here.

Core Concepts

Knowledge Ingestion

Agent Operations

Multi-Source Brains

Multi-source brains

The three scenarios

1. Unified knowledge recall (wiki + gstack)

2. Purpose-separated brains (team-media + personal-list)

3. Mixed (wiki federated + sessions isolated)

Resolution priority

Federation flag

Commands

Citation format for agents

Writing to a specific source

Durability: keep a brain repo in sync (auto-harden)

Upgrading an existing brain

Not in v0.18.0

​Multi-source brains

​The three scenarios

​1. Unified knowledge recall (wiki + gstack)

​2. Purpose-separated brains (team-media + personal-list)

​3. Mixed (wiki federated + sessions isolated)

​Resolution priority

​Federation flag

​Commands

​Citation format for agents

​Writing to a specific source

​Durability: keep a brain repo in sync (auto-harden)

​Upgrading an existing brain

​Not in v0.18.0

Multi-source brains

The three scenarios

1. Unified knowledge recall (wiki + gstack)

2. Purpose-separated brains (team-media + personal-list)

3. Mixed (wiki federated + sessions isolated)

Resolution priority

Federation flag

Commands

Citation format for agents

Writing to a specific source

Durability: keep a brain repo in sync (auto-harden)

Upgrading an existing brain

Not in v0.18.0