Results for Semantic · 2.621s

Sponsored
News for “Semantic”
20 results • 2618 ms server time
Show HN: Rememex – Semantic file search that runs 100% locally (Rust/Tauri)IMAGE
github.com• Feb 19, 2026• 1 min read
Show HN: Rememex – Semantic file search that runs 100% locally (Rust/Tauri)Hey HN, I built Rememex a semantic search layer for your local files. The problem: I kept losing files. Not because they were deleted, but because I couldn't remember the exact filename or keyword. grep needs the exact word. Everything only searches filenames. I wanted to type what I meant and find what I needed. How it works: - Indexes 120+ file types (code, docs, images, configs) - Hybrid search: vector embeddings + full-text + JINA cross-encoder reranking - OCR on images via Windows UWP engine - Reads EXIF GPS → reverse geocodes to city names ("photos from istanbul" works) - EXIF dates → human language ("summer morning" finds a July 8am photo) - Smart chunking per language (Rust at fn/struct, Python at def/class) - Built-in MCP server so AI agents can use it as a tool Everything runs locally. Embeddings use a local ONNX model (Multilingual-E5-Base) by default, though you can optionally plug in OpenAI/Gemini/Cohere. Named after Vannevar Bush's Memex (1945) his vision of a device that
Security Layer 4.0 – First semantic firewall blocks malicious intent"IMAGE
news.ycombinator.com• Nov 29, 2025• 1 min read
Security Layer 4.0 – First semantic firewall blocks malicious intent"*Title:* Show HN: BETTI v2.0 – First semantic GPU firewall (93% cost savings, 100% cryptojacking detection)*Body:*I built BETTI, a distributed computing system that applies 14 natural physics laws to resource allocation. New in v2.0: Security Layer 4.0 for GPUs - the world's first semantic GPU firewall.## The ProblemGPU training costs $3/hour (AWS), takes "3-8 weeks" (unpredictable), and cryptojacking steals $5B/year. Current security is reactive - firewalls block AFTER seeing patterns. Resource limits are arbitrary: "You get 4 cores", "10GB RAM max".## The SolutionBETTI applies 14 physics laws:• Kepler's 3rd Law (T² ∝ a³): Task scheduling based on orbital periods • Einstein's E=mc²: Energy cost calculation • Newton's Laws: Resource conservation • Fourier, Maxwell, Schrödinger, TCP, Thermodynamics, etc.This is the first system to apply Kepler's orbital mechanics to computing.## Security Layer 4.0 for GPUs (NEW!)Traditional anti-malware: 60% cryptojacking detection (pattern-based, react
Advertisement
Moozonian News
github.com• Aug 19, 2026• 1 min read
Show HN: Minna – On-device semantic search across your own documents (macOS)Hi HN! Minna is a new tool geared towards people who have a knowledge base so big they forget where things are.- Chat answers are constrained to retrieved results. The model has to search your knowledge base first and cite the document it pulled from. It won't answer from outside your knowledge base which means you can trust the LLM instead of having to be weary about what it outputs. - Hybrid retrieval — BM25 over an inverted index for exact and keyword matches, plus a vector index for semantic matches, results are fused using Reciprocal Ranked Fusion. - Embeddings and inference both run on-device. Search uses bge-small-en and run on the neural engine. Chat uses Qwen3 4B running on MLX. - Search latency is ~12 ms across 250 documents split into 30,000 chunks on Apple Silicon.What’s not done; OCR scanning on PDFs is limited, the app is currently Apple Silicon only, and there are some rough edges in the UI.It’s a TestFlight beta (apologies, but it is the cleanest distribution path right
Advertisement
Moozonian News
github.com• Jul 21, 2026• 1 min read
Show HN: Semglot – Sqlglot for Semantic LayersHey HN, I’m André, one of the people that is building benchouse.ai, a public leaderboard for analytics agents.To score every agent fairly, we need to give them equivalent semantic context. Every agent has their own format ranging from dbt docs to Snowflake semantic views or custom yaml formats. I was porting them over manually, but every change in the reference context meant updating multiple docs. Quite annoying.So we wrote semglot, it reads one semantic model and emits another one. Similar to sqlglot but for semantic layers. Today it reads dbt and writes to 6 different targets. Many more to come as we add more agents to benchouse.aiMIT licensed.
Advertisement
Sponsored