Hey HN! I am Roan, and I built Hillock: a 100% local, offline neuro-symbolic memory engine built for consumer hardware (runs in <1.2 GB VRAM on a GTX 1070 or on pure CPU laptops).
Why not standard vector RAG?
Dense vector databases and 8B+ extraction models are heavy on local hardware, suffer from semantic drift, and still hallucinate when out of context. Hillock explores a deterministic alternative:
SQLite Knowledge Graph: Stores ground-truth facts as relational Subject-Predicate-Object triples (zero vector drift).
Hebbian Plasticity Engine: Gradient-free associative learning across turns to surface primed context.
10,000-D Hyperdimensional Computing (VSA/HDC): Sub-millisecond similarity gating directly on CPU in discrete bipolar space.
TALON Extraction Stack: 3-stage local extraction (Fastcoref + MiniLM + GLiREL) with type-constrained schema validation, running offline without cloud calls.
Refusal is Control Flow (Not Prompting)
Instead of prompting an LLM to "only answer if you know", Hillock's gate is an actual programmatic check. If candidate facts fail our similarity threshold with positive predicate intent, it returns a hardcoded refusal immediately. The local LLM (Ollama) is never called with un-evidenced context, saving 100% of GPU compute on unanswerable queries.
What is New in v0.6 (HYDRA & HyperGraph)
HYDRA (Bipolar MaxSim): Adapted ColBERT-style token-level MaxSim to discrete bipolar vectors. A 2,000-D Sub-Dimensional Projection Cascade early-rejects ~95% of candidates on CPU in ~0.5ms.
HYPERGRAPH-HDC: Uses positional cyclic shifts to break binding commutativity, encoding 2-hop and 3-hop relational paths without combinatorial RAM explosion.
Benchmarks (Unseeded 32-query run on a laptop CPU)
Answerable Retrieval Accuracy: 54.5% (Fast-eval in 1.16s on CPU)
Hard-Negative Block Rate: 60.0% (stops trick queries cold)
Extraction Recall: 59.1% | Pooled Gate Accuracy: 56.2%
Known Limitations
Retrieval quality is strictly bounded by extraction recall: if the extractor misses a fact during ingestion, the gate honestly refuses (producing a false block).
The project is AGPL-3.0 licensed with 1-click quickstart launchers (run.bat / run.sh) and a standalone 21-point CPU verification suite (verify_hillock.py).
I did not try to play with it yet, but from what I read - it is a great idea.
Hey HN! I am Roan, and I built Hillock: a 100% local, offline neuro-symbolic memory engine built for consumer hardware (runs in <1.2 GB VRAM on a GTX 1070 or on pure CPU laptops). Why not standard vector RAG?
Dense vector databases and 8B+ extraction models are heavy on local hardware, suffer from semantic drift, and still hallucinate when out of context. Hillock explores a deterministic alternative:
Refusal is Control Flow (Not Prompting)Instead of prompting an LLM to "only answer if you know", Hillock's gate is an actual programmatic check. If candidate facts fail our similarity threshold with positive predicate intent, it returns a hardcoded refusal immediately. The local LLM (Ollama) is never called with un-evidenced context, saving 100% of GPU compute on unanswerable queries. What is New in v0.6 (HYDRA & HyperGraph)
Benchmarks (Unseeded 32-query run on a laptop CPU) Known LimitationsRetrieval quality is strictly bounded by extraction recall: if the extractor misses a fact during ingestion, the gate honestly refuses (producing a false block).
The project is AGPL-3.0 licensed with 1-click quickstart launchers (run.bat / run.sh) and a standalone 21-point CPU verification suite (verify_hillock.py).
GitHub: https://github.com/roandejager/Hillock
I would love to hear your thoughts, feedback, and critiques!