# Hillock

- [Hillock: Local Neuro-Symbolic Memory for AI Agents](https://hillock.mintlify.app/introduction.md): Hillock is a three-tier neuro-symbolic memory engine: SQLite Knowledge Graph, Hebbian plasticity, and HDC for hallucination-free, fully offline AI memory.
- [Quickstart: Run Hillock Locally in Under 5 Minutes](https://hillock.mintlify.app/quickstart.md): Install Hillock via pip, connect to a local Ollama model, ingest your first document, and query the interactive CLI with the HDC hallucination gate active.
- [Hillock vs. Traditional RAG: A Technical Comparison](https://hillock.mintlify.app/rag-comparison.md): Compare Chroma and Pinecone-style vector RAG against Hillock on VRAM usage, hallucination risk, retrieval determinism, and fully offline deployment.
- [Hillock's Three-Tier Memory Architecture Explained](https://hillock.mintlify.app/architecture/three-tier-system.md): How Hillock combines a SQLite knowledge graph, Hebbian synaptic memory, and 10,000-dim HDC/VSA vectors into a coherent neuro-symbolic memory engine.
- [TALON Extraction Engine: From Raw Text to SPO Triples](https://hillock.mintlify.app/architecture/talon-extraction-engine.md): TALON converts raw documents into SPO triples via a 3-stage pipeline: FCoref coreference, MiniLM predicate routing, and GLiREL relation extraction.
- [Deterministic Gating: How Hillock Prevents Hallucinations](https://hillock.mintlify.app/architecture/deterministic-gating.md): How Hillock's HDC cosine gate blocks ungrounded queries before any LLM call — the same query always produces the same pass/block decision, guaranteed.
- [Use Hillock as an Embedded Python Library in Your App](https://hillock.mintlify.app/guides/python-library.md): Import IntegratedHillock directly into your Python app to ingest documents, query the knowledge graph, and get grounded responses — no CLI required.
- [Configure Hillock to Run with Any Local Ollama Model](https://hillock.mintlify.app/guides/ollama-integration.md): Configure Hillock to use any Ollama model for LLM rendering — swap models at runtime, tune the endpoint, and keep every token 100% local.
- [Connect Hillock to Open-WebUI, AnythingLLM, and Local UIs](https://hillock.mintlify.app/guides/open-webui.md): Start Hillock's FastAPI server and connect any OpenAI-compatible frontend — Open-WebUI, AnythingLLM, Obsidian, or curl — in under five minutes.
- [Hillock CLI: Complete Interactive Command Reference](https://hillock.mintlify.app/reference/cli-commands.md): Reference for all 9 slash commands in Hillock's terminal: ingest documents, inspect entities, switch models, and adjust debug verbosity.
- [Hillock API Reference: HTTP Endpoints and Python SDK](https://hillock.mintlify.app/reference/api-reference.md): Full reference for Hillock's FastAPI HTTP endpoints, IntegratedHillock Python class methods, and the ingest_document_parallel ingestion function.
- [Hillock Licensing: AGPL-3.0 and Proprietary License](https://hillock.mintlify.app/commercial/licensing.md): Hillock is dual-licensed under AGPL-3.0 (free, copyleft) and a proprietary commercial license at $49/month or $499/year for closed-source use.
- [Hillock Community: Discord, GitHub, and Getting Help](https://hillock.mintlify.app/commercial/community.md): Join the Hillock Discord and GitHub for real-time help, bug reports, feature requests, and contributing to local AI memory development.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.