This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
Summary
AI summaryIntroduces a three‑store architecture, Hebbian graph overlay, and modular RAG retrieval with new lifecycle operations.
Full changelog
Features
- Three-store architecture (episodic/semantic/implicit) + Hebbian graph overlay
- 7 lifecycle operations: consolidate, transform, forget, perfume, emergent ontology, RIF, purge
- Modular RAG retrieval: BM25 + vector + graph + RRF fusion + semantic/preference enrichment
- Bjork dual-strength forgetting with retrieval-induced suppression (RIF)
- LTD (Long-Term Depression): Hebbian link decay weakens unused associations each transform cycle
- Enriched retrieval: query results include semantic knowledge and preferences alongside episodes
- Tombstone tracking: cascade deletion records audit trail for every purged node
- Zero-dependency Rust library with SQLite WAL + FTS5
- Category hierarchy with
parent_id— categories form tree structures; auto-split when too broad - Cross-domain bridging via
MemberOflinks — spreading activation traverses category boundaries - EmbeddingProvider trait —
embed()+embed_batch()wired intostore_episode()andquery() - ExtractionProvider trait —
extract()enables auto-consolidation;LlmExtractionProvider(behindllmfeature flag) calls any OpenAI-compatible API - 13 MCP tools —
remember,recall,learn,status,preferences,knowledge,maintain,purge,categories,neighbors,node_category,import_claude_mem,import_claude_code - Auto-lifecycle — auto-maintenance every 25 episodes; auto-consolidation (or prompt) after 10 unconsolidated
- 442 tests across unit, integration, property-based (proptest), and doc tests
Environment Variables
| Variable | Default | Description |
|----------|---------|-------------|
| ALAYA_DB | ~/.alaya/memory.db | Path to SQLite database |
| ALAYA_LLM_API_KEY | (none) | API key for auto-consolidation (requires llm feature) |
| ALAYA_LLM_API_URL | https://api.openai.com/v1/chat/completions | OpenAI-compatible endpoint |
| ALAYA_LLM_MODEL | gpt-4o-mini | Model name |
Build
# MCP server only
cargo build --release --features mcp
# MCP server with auto-consolidation
cargo build --release --features "mcp llm"
Full Changelog: https://github.com/SecurityRonin/alaya/compare/v0.1.0...v0.2.0
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About SecurityRonin/alaya
Neuroscience-inspired memory engine for AI agents. Stores episodes, consolidates knowledge through a Bjork-strength lifecycle (strengthening, transformation, forgetting)
Related context
Related tools
Beta — feedback welcome: [email protected]