Sprint 0 - Repository scaffold
Complete
Outcome: a binary the team can ship. Cargo workspace, schema v4 DDL, CI/release workflows.
Roadmap
Quaid moves through three arcs. Each arc is a directional bet, not a feature list. The phases inside each arc have hard ship gates: no phase begins until the previous one passes.
Arc 1 - Local memory that holds Shipped
Section titled “Arc 1 - Local memory that holds ”The foundation. Storage that doesn’t lose data, retrieval that doesn’t hallucinate, and a sync engine that follows your editor without dropping writes. This arc is complete.
Phase 1 - Storage, CLI, search, MCP
Complete
Outcome: a memory you can read, write, and query without a network. Import, export, FTS5 + vector hybrid search, 5 core MCP tools. Released as v0.1.0.
Phase 2 - Intelligence layer
Complete
Outcome: links, contradictions, and progressive retrieval that survives token budgets. Temporal links, assertions, contradiction detection, 16 MCP tools. Released as v0.2.0.
Phase 3 - Skills, benchmarks, polish
Complete
Outcome: workflow logic that ships in the binary, plus a regression gate that catches retrieval drift. All 8 skills production-ready, BEIR regression gate, benchmark harnesses (LoCoMo, LongMemEval, BEAM adapters). Released as v0.9.2.
Phase 4 - vault-sync engine
Complete
Outcome: memory that stays current as you edit in Obsidian or any editor, with write-safety interlocks under concurrent agents.
Landed: Collections model (quaid collection add/list/info/sync/remove); .quaidignore with atomic validation and live reload; quarantine lifecycle (list/export/discard; Unix narrow restore with no-replace contract); Unix CAS write interlocks plus crash-safe sentinels; live file watcher with 1.5s debounce (macOS/Linux); UNIX-socket single-file write proxying; restore/remap two-phase safety pipeline; UUID lifecycle and opt-in write-back (migrate-uuids); memory_collections MCP tool; background embedding queue and worker.
Deferred to future work: Full IPC proxy for bulk rewrites; online restore handshake; Windows quarantine restore. See the Deferred section below.
Arc 2 - Agents that compound In progress
Section titled “Arc 2 - Agents that compound ”Phase 5 shipped conversation memory and the local Phi-3.5 Mini extraction path. Phase 6 foundations also shipped in the current public release: graph autowiring, graph path output, quaid graph extract-entities, and graph retrieval controls. The remaining Arc 2 work is performance, entity-graph follow-ons, and benchmark reruns.
Phase 5 - Conversation memory + SLM extraction
Section titled “Phase 5 - Conversation memory + SLM extraction”Outcome: an agent that remembers the right things from a conversation turn, not just the turn itself.
Namespace isolation
Complete
Per-namespace memory isolation for multi-agent and multi-session contexts. Drops LongMemEval benchmark runtime from 3-6 hours to under 30 minutes.
Large corpus performance
Pending
Optimize for 10K+ document stores. Current import: ~437s for 350 docs. Target: under 60s. Validate Quaid at the scale real users need (GBrain operates at 75K files).
Conversation ingestion + SLM extraction
Complete
Ingest conversation turns, extract structured facts using a local Phi-3.5 Mini SLM, store as typed pages. Non-blocking background queue, fully airgapped. Supersede chains, head-only retrieval by default, memory_add_turn / memory_close_session / memory_close_action MCP tools, correction-via-file-edit path.
Contradiction resolution
Complete
Supersede and version stale facts. “I used to work at X, now Y” resolves correctly rather than keeping both facts active. Version chains, temporal-latest query mode. Per-fact dedup/supersede/coexist resolution with embedding-backed scoring.
Phase 6 - Knowledge graph foundations
Section titled “Phase 6 - Knowledge graph foundations”Outcome: a graph that already wires itself from page structure today, with richer entity-centric traversal still ahead.
Frontmatter and wikilink autowiring
Shipped in v0.22.0
links:, parent:, children:, related:, and body [[slug]] references now create derived graph edges automatically. The current published release (v0.23.0) carries this foundation.
Path explanations and retrieval controls
Shipped in v0.22.0
memory_graph and quaid graph return paths, and quaid query/search --hops N plus graph config keys are live. Retrieval expansion is still default-off until the published benchmark gate is cleared.
Entity-pattern backfill
Shipped with a limit
quaid graph extract-entities ships now, but it writes assertions only. It does not yet promote durable entity edges into the graph.
Entity-centric query API and multi-hop follow-ons
Still pending
The current public release does not include memory_graph_query(entity, hops), durable entity-edge promotion, or default-on graph expansion. Those remain follow-on work.
Arc 3 - Memory that thinks Later
Section titled “Arc 3 - Memory that thinks ”The features that turn a memory store into a memory system. With the graph foundation shipped and conversation memory working, the runtime can be proactive instead of just responsive.
Phase 7 - Intelligence layer
Section titled “Phase 7 - Intelligence layer”Outcome: memory that updates itself when new content arrives, deduplicates noise at scale, and compresses what it sends to an LLM.
Active memory enrichment
Depends on #107, #133
When new content arrives, existing entity memories update proactively. GBrain v0.23.0’s headline feature: “Your brain actually gets enriched from your conversations.”
Noise reduction + deduplication
Result deduplication and relevance filtering. Implementable at any point but most valuable when the corpus is large.
Context compression (REFRAG)
Compress retrieved chunks before sending to an LLM. Reduces tokens and cost while maintaining quality. High value at production scale.
Build order summary
Section titled “Build order summary”For contributors. The arcs above are the public roadmap; the table below is the remaining implementation order for incomplete work.
| Priority | Issue | Feature | Depends on |
|---|---|---|---|
| 1 | #134 | Large corpus performance | - |
| 2 | #107 | Durable entity extraction follow-on | #105 (coordinate) |
| 3 | #72 | Self-wiring graph follow-on and edge promotion | #107 |
| 4 | #133 | Entity-centric graph query API | #72, #107 |
| 5 | #74 | Multi-hop traversal | #133 |
| 6 | #136 | Active memory enrichment | #107, #133 |
| 7 | #75, #76 | Noise reduction, context compression | Any |
Deferred
Section titled “Deferred”These are known design choices, not oversights.
| Feature | Status | Reasoning |
|---|---|---|
| npm, Homebrew, winget | Planned | Registry ownership and release automation not yet in place |
| WASM compilation | Possible | Strong Rust support, not yet a priority |
| Collaborative / multi-user | Not planned | Single-writer by design. No auth, RBAC, or CRDTs. |
| LLM-assisted contradiction detection | Deferred | Binary stays dumb. Cross-page reasoning lives in the maintain skill. |
| Room-level palace filtering | Deferred | Wing-only until benchmarks prove room-level helps. |
| vault-sync IPC proxy (bulk rewrites) | Deferred | Full multi-file write proxying to v0.14.0+; current surface is single-file UNIX socket only. |
| Online restore handshake | Deferred | Requires live serve+CLI coordination with crash-durable guarantees; CLI narrow restore shipped for Unix offline use. |
| Windows quarantine restore | Deferred | Unix narrow no-replace restore shipped; Windows path requires separate design work. |