{"repo":"HiveForensics-AI/knolo-core","free":true,"listed":false,"github":"https://github.com/HiveForensics-AI/knolo-core","clone":"git clone https://github.com/HiveForensics-AI/knolo-core.git","description":"KnoLo Core is a local-first knowledge base engine built for small language models (LLMs). It packages your documents into a compact .knolo file and enables fully deterministic querying — no embeddings, no vector databases, no cloud services required. Designed for on-device and edge LLM deployments.","language":"TypeScript","stars":40,"topics":["document-retrieval","edge-ai","edge-computing","knowledge-base","lexical-search","local-first","offline-first","offline-llm","on-device-llm","rag-alternative"],"license":"Apache-2.0","category":"productivity","readme_excerpt":"🧠 Knolo Knolo is a local-first knowledge base engine built around deterministic retrieval and portable .knolo packs. It provides: @knolo/core — pack format + deterministic retrieval engine, LivePack overlay, and Cortex memory layer @knolo/cli — build workflows for .knolo artifacts, including live ICP canister commands packages/icp-canister — live Internet Computer knowledge canister (lexical search on-chain) create-knolo-app — instant Next.js starter with playground @knolo/langchain — LangChain-style retriever adapter @knolo/llamaindex — LlamaIndex-style retriever adapter Knolo prioritizes: Deterministic lexical retrieval Optional hybrid semantic reranking Zero vector database requirement Local-first execution (offline capable) Portable binary knowledge packs Optional ICP deployment for on-chain knowledge retrieval Strict runtime contracts (optional advanced features) ⚠️ knolo-core (unscoped) on npm is deprecated. Use @knolo/core . --- 📊 Retrieval Benchmark (March 2026) Knolo was evaluated using a deterministic lexical-first + optional rerank configuration. Run: 2026-03-01 TopK: 5 Aggregate Metrics Metric Score ----------- --------- Precision@5 0.490 Recall@5 1.000 MRR@5 0.867 nDCG@5 0.900 Interpretation ✅ Recall@5 = 1.0 → All relevant documents were retrieved in every test query. ✅ High MRR (0.867) → Relevant documents appear near the top. ✅ Strong nDCG (0.900) → Ranking quality is consistently high. 🔍 Precision reflects lexical grounding before rerank — by design, Knolo ","default_branch":null,"files":null,"tree":[],"storefront":"/r/HiveForensics-AI","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/HiveForensics-AI/knolo-core/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}