Jabhook – Boxing Training (Computer Vision, 3D Biomechanics, Local LLM)
Jabhook is an experimental boxing training app that uses computer vision and 3D biomechanics to provide personalized coaching. The software analyzes user motion locally by comparing it against a professional sample library and generating advice via a local LLM. Currently available as a beta for Apple Silicon Macs, the app plans to expand to Linux and other martial arts disciplines in the future.
- ▪Jabhook utilizes computer vision to capture 3D motion and compares it to a library of perfect boxing forms created with a professional boxer.
- ▪The application processes biomechanical data using a local Large Language Model to generate specific verbal coaching advice without cloud dependency.
- ▪The experimental beta version is priced at $40 and requires Apple Silicon hardware with macOS 26.2 or later.
- ▪Future updates scheduled for December will include Linux support and expand the app's capabilities to disciplines like kickboxing, parkour, and ballet.
Hacker News (AI / LLM) files mainly under ai. We currently carry 7,440 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 | Jabhook |
| Canonical URL | https://jabhook.ai/ |
| Publication time | Sat, 03 Oct 2026 15:10:54 +0000 |
| Retrieval time | 2026-10-03T15:23:12.737Z |
| Last seen | 2026-10-03T15:23:12.737Z |
| 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 | 4Sa3XXlYO1EJ · 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
What it does Jabhook is an experimental app for boxing training. Set up a custom workout and be verbally guided through combinations. As you train, the camera captures your motion, and AI analysis turns it into personalized coaching. AI analysis In collaboration with a professional boxer, a sample library of combinations was created with perfect form and efficacy. The analysis works by extracting the user’s motion in 3D, comparing it to the sample library, and then using an LLM to process this into coaching advice. The entire process is 100% local. Motion Capture↓ Biomechanics Analysis↓ Local LLM “Drive from your back foot, turn your hips into the punch, snap the arm out — don’t just reach.” Buy Jabhook is available now as an experimental beta for $40.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Jabhook.
Discussion
0 commentsMore from Jabhook
