LocalVibe – Pure-Rust local AI stack with MCP, in one binary (Apple Silicon)
LocalVibe is a Pure-Rust local AI stack designed for Apple Silicon Macs, offering a terminal-based interface for interacting with quantized language models. It supports on-device inference via Metal, directory indexing with ONNX embeddings, and vector search using LanceDB. The tool is distributed as a single binary and emphasizes local execution without reliance on external services.
- ▪LocalVibe runs on Apple Silicon (M1–M4) and uses Metal for efficient on-device inference through Candle.
- ▪It supports local LLM chat, directory indexing, and vector search using fastembed-rs and LanceDB, all within a ratatui-based TUI.
- ▪The system allows runtime switching between multiple models and vector databases, with configuration managed via TOML files.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,311 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/Sok205/local_vibe |
| Publication time | Sat, 16 May 2026 19:08:03 +0000 |
| Retrieval time | 2026-05-16T19:15:18.988Z |
| Last seen | 2026-05-16T19:15:18.988Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | I1MGHxt8IV8R |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
local-vibe (localvibe / lv) Pure-Rust local coding assistant: chat with a quantized LLM on Metal, index any directory with on-device ONNX embeddings, search it with LanceDB, all from one ratatui TUI. Runs on Apple Silicon (M1–M4). Candle + Metal for inference, fastembed-rs for embeddings, LanceDB for vectors. A TUI screenshot will live here once one is captured — see docs/screenshots/. Quick start Assumes ~/.cargo/bin is on PATH, you are on macOS, and you have a GGUF model supported by Candle (qwen2 / llama family — Qwen 3.5 hybrid SSM is not supported). # 1. install the `localvibe` binary (`lv` alias is also installed) git clone https://github.com/Sok205/local_vibe ~/code/local_vibe cd ~/code/local_vibe cargo install --path crates/lv-cli # 2.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.