longhand
On-device transcripts and summaries of your recorded phone calls. Made for GrapheneOS; nothing leaves the phone.
Get picks like this daily. The day's top launches, AI/tech news, and a weekly opportunity spotlight — straight to your inbox.
This is 1 of 175 launches in AI meeting notetakers and recorders — see how it stacks up on momentum and crowding →
66 other launches read as similar to this one →
Details
- External ID
- 1401208699
- Source
- GITHUB
- Company
- —
- Product
- longhand
- Website domain
- github.com
- Launched
- Oct. 2, 2026
- Cohort
- —
- Upvotes
- 9
- Upvotes percentile
- 0.06116605934409162
- Tags
- android, call-recording, grapheneos, jetpack-compose, kotlin, on-device-ai, privacy, speaker-diarization, speech-to-text, transcription
- Fetched at
- Oct. 5, 2026, 5:02 p.m.
- Updated at
- Oct. 5, 2026, 5:02 p.m.
Enrichment
- Niche
- AI meeting notetakers and recorders
- Vertical
- Horizontal
- Function
- Workflow automation
- Audience
- Prosumer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- on-device call transcription and summarization for grapheneos users
- Manually corrected
- False
Could you build this?
Partial The Android application wrapper and file management are straightforward, but running accurate, fully offline ASR and LLM summarization optimized for GrapheneOS device hardware requires specialized on-device ML runtime integration.
What it would actually take: Requires an Android application (Kotlin) integrated via JNI/C++ with on-device inference engines like whisper.cpp and llama.cpp (or MediaPipe/ExecuTorch). The hard part is tuning quantization, memory footprint, and NPU/GPU hardware acceleration on Google Pixel devices to process long phone call audio recordings without running out of RAM or thermal throttling under GrapheneOS.
Competitors
Other products that read as similar to this one — 66 launches clear the similarity bar, closest 8 shown.
Attention rank: #65 of 67 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 330 days after the earliest competitor.
- Qwen Scribe · hn · 2026-07-29 · 97 upvotes · similarity 0.40
- WhisperDeck · github · 2026-09-10 · 18 upvotes · similarity 0.39
- claude-chat-clean · github · 2026-10-06 · 21 upvotes · similarity 0.39
- foner · github · 2026-10-06 · 16 upvotes · similarity 0.39
- wngmn · github · 2026-09-11 · 11 upvotes · similarity 0.38
- Quartz · hn · 2026-07-21 · 8 upvotes · similarity 0.38
- Kekoso · hn · 2026-09-02 · 8 upvotes · similarity 0.38
- A 150M model that extracts verbatim evidence spans for RAG, no LLM call · hn · 2026-06-10 · 6 upvotes · similarity 0.38
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a workflow automation tool for Real estate yet.