Local-first 🧠memory for Hermes Agent that lives in your Obsidian vault and remembers project context. Nightly 😴 dream passes turn repeat corrections into confirmed preferences with measurable confidence. Adapters ship for Claude Code, Codex, and OpenClaw, with an MCP server for anything else.
Variant 1: Sibling "promises" family with one shared counterparty selector
- Approach: Add a new page family at
Brain/promises/<slug>.md, built likeobligations.ts(path constants, typedPromiseError, write-time validators, a soft reader, injected clock). Its keys are distinct:promise_due,promise_status,evidence_quote, plus new relation keyspromised_to/owed_byadded toDEFAULT_RELATION_TYPES, so the edges come in through the existing frontmatter-relations path. The feature is one new tool,brain_promise(operations add/done/list/show/remove/intake). Theintakeoperation copies thebrain_intake_entitiescontract: validate the whole payload, refuse before any write, use duplicate-refusing upserts, stamp provenance, and derive trust from cited sources. One pure kernel,selectCounterpartyItems(entity, now, limit), does the shareable-only filtering throughstrictestVisibilityOf, then dated-first ordering, then the 3-item cap. Two things call it: a newhooks/counterparty-brief.ts(flag checked first, injection ledger, operator-declared intent vocabulary in config, a single confidentanchorEntityFormsmatch) and a newentityFacts?: booleanoption onpackContext, resolved at the tool seam. - Trade-offs:
- Pro: there is no clash with the existing
commitment:tier, and the obligations pattern is copied exactly, so reviewers know what to look for. - Pro: the push brief and the pull
entity_factssection can't drift apart, because both render from one selector. The pull side has no dependency on promises: it reads facts, and promises only add dated items when they exist. - Pro: edges and facts come out of the existing indexer and link-graph with no new projection code. Default packs stay byte-identical through the conditional report member and projection.
- Con: one new MCP tool means the full four-census registration (parity test, visibility registry row, reach predicates, path-safe responses).
- Con: the shared selector has to serve two budgets (3 items for the hook, a per-entity recency list for the pack), so its parameter surface needs careful design.
- Pro: there is no clash with the existing
- Complexity: medium
- Risk: low
Variant 2: Generalize obligations to one-off items
- Approach: Extend the existing obligations family and the
brain_obligationtool.cadencebecomes optional, a one-off item carries a fixeddueplusevidence_quoteand acounterpartyrelation, and the tool gains anintakeoperation. No new tool and no new family. The counterparty hook and the context-packentity_factsoption read obligations directly. - Trade-offs:
- Pro: the smallest surface. There is no tool registration, the due-sorted list and overdue flag already exist, and the files land under the 50-70 budget.
- Pro: a single "what is due" view covers both recurring and one-off items.
- Con: it changes the semantics of a shipped family. The cadence math,
done(which advances or archives), list ordering and existing tests all branch on the cadence type, so recurring-obligation behavior risks a regression in the same PR. - Con: agent-extracted promises with provenance and evidence sit beside hand-declared obligations. Trust and provenance stamping would leak into a family that never had it.
- Con: the push and pull paths each query obligations their own way, so the shareable filter and the cap are duplicated. That is two places for the privacy rule to drift.
- Complexity: small
- Risk: medium
Variant 3: Facts-first intake with thin ledger pages
- Approach: A dedicated
brain_intake_commitmentstool copiesbrain_intake_entitiesone-for-one. Each validated extraction writes a thin promise page as an audit ledger and, as its main output, a dated atomic fact anchored on the counterparty entity. A second tool,brain_promise, covers list/done. Both the hook andentity_factsread only from the fact store, so pages are evidence and facts are the queryable surface. - Trade-offs:
- Pro: dated items and ordinary recent facts share one storage shape, so
entity_factsand the brief are the same query with aduefilter. - Pro: the intake contract is a byte-faithful mirror of an existing reviewed tool, which keeps validation risk low.
- Con: two new tools means two four-census registrations, and the PR goes past the ~70-file budget.
- Con: the truth is split. Pages are the source of truth, yet the brief reads a derived fact store, so done/remove on a page must invalidate facts (more truth-maintenance code). A hand edit to a page's due date stays invisible until the facts are re-projected.
- Con: it inverts the project rule that Markdown pages are canonical, and it adds a new projection path instead of reusing frontmatter relation edges.
- Pro: dated items and ordinary recent facts share one storage shape, so
- Complexity: large
- Risk: high
Recommended: Variant 1
Rationale: It is the only variant that keeps all three: pages as canonical truth, the precedent for a new page family, and the separation from the existing commitment: tier. It also costs exactly one deliberate tool registration and fits the file budget. Using one shared selector in both the hook and the context-pack option means the privacy rule (shareable-only) and the 3-item cap live in one place. The pull side ships independently, and the push side only turns on once the promise supply exists, which matches the order the two cards depend on.