v0.3.0 — Hybrid Retrieval Engine (94% accuracy)
What's New
Hybrid Retrieval Engine
The core memory recall system has been upgraded from single-strategy vector search to a multi-strategy hybrid pipeline:
- Vector search — semantic similarity via OpenAI embeddings
- BM25 full-text search — exact keyword matching via PostgreSQL tsvector
- Trigram fuzzy search — typo tolerance via pg_trgm (handles "PostgrSQL", "Typscript", etc.)
- Reciprocal Rank Fusion — merges results from all three strategies
- Temporal decay — recent memories score higher (90-day half-life)
- Context compression — large result sets compressed via GPT-4o-mini
- Relevance threshold — irrelevant queries return 0 results instead of noise
Benchmark Results (94% overall)
| Category | Score |
|---|---|
| Semantic (paraphrased queries) | 75% |
| Keyword (exact technical terms) | 100% |
| Typo tolerance (misspelled queries) | 100% |
| Cross-domain (business + meetings) | 100% |
| Preference (coding style) | 100% |
| Negative (irrelevant queries filtered) | 100% |
| Overall | 94% |
New SDKs & Integrations
- Node.js SDK on npm:
central-intelligence-sdk - Python SDK updated on PyPI:
central-intelligence - OpenAPI spec at
/docs/openapi.jsonfor ChatGPT Custom GPTs - Demo endpoint at
/demo/recall— try without signup - "When to use" metadata in
.well-known/mcpand.well-known/agent.json - Integration cards: Lovable, Perplexity, Antigravity, GitHub Copilot
- ClawHub skill published