Flashcat – a local AI assistant for the Mac terminal that asks first
Flashcat A local AI assistant for the macOS terminal. Flashcat chats with you, reads and writes files in the folder you start it in, looks at images, reads PDFs, Word and Excel files (even scans), and can search the web — all with a model that runs on your own Mac through LM Studio. Nothing you ask leaves your computer unless you allow a web request: a private, offline AI chat for your MacBook, powered by a local LLM (Google Gemma 4).
- ▪Flashcat A local AI assistant for the macOS terminal.
- ▪Flashcat chats with you, reads and writes files in the folder you start it in, looks at images, reads PDFs, Word and Excel files (even scans), and can search the web — all with a model that runs on your own Mac through LM Studio.
- ▪Nothing you ask leaves your computer unless you allow a web request: a private, offline AI chat for your MacBook, powered by a local LLM (Google Gemma 4).
Hacker News (AI / LLM) files mainly under ai. We currently carry 6,514 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/TomTomsen765/flashcat |
| Publication time | Sat, 26 Sep 2026 09:24:14 +0000 |
| Retrieval time | 2026-09-26T09:26:00.671Z |
| Last seen | 2026-09-26T09:26:00.671Z |
| 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 | lz9gTjHSOrB_ · 1 stories |
| 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
Flashcat A local AI assistant for the macOS terminal. Flashcat chats with you, reads and writes files in the folder you start it in, looks at images, reads PDFs, Word and Excel files (even scans), and can search the web — all with a model that runs on your own Mac through LM Studio. Nothing you ask leaves your computer unless you allow a web request: a private, offline AI chat for your MacBook, powered by a local LLM (Google Gemma 4). Named after Flash, my cat. 🐈 Install Install LM Studio and open it once. Run this in the terminal: curl -fsSL https://raw.githubusercontent.com/TomTomsen765/flashcat/main/install.sh | bash The installer checks your Mac, installs the flashcat command into ~/.local/bin and downloads the default model, Gemma 4 26B (about 15.6 GB), through LM Studio.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.