ExtraBrain
Private AI copilot for interviews and meetings
What it does
ExtraBrain is a free macOS AI copilot for live interviews, system design rounds, debugging calls, and technical meetings. It runs as a private overlay visible to you, can stay out of macOS screen recordings/screen sharing where supported, listens/transcribes, reads selected screen context, and gives concise real-time analysis with local transcription, BYO providers, custom endpoints, and built-in profiles.
Does a similar job
all alternatives →
- ClaudoscopeApr 2026 · claudoscope.com · ▲106
Browse, search & track costs across Claude Code sessions
- EAEmbra – A fast, Chat-GPT like assistant for your Mac. App integrated2023 · ▲13
Hey HN! We're building Embra, an always-one-second away GPT assistant that integrates into your OS, apps, and workflows. Everyone is talking about the "context problem" as it relates to GPT, in that the answers you get out are only as good as the information you put in. And, well, a lot of users don't want to type in a bunch of text. With Embra, you can pick and choose which context to feed the AI within the interface itself. And that context can be anywhere on your computer -- text in a PDF document, any tabs within Chrome, etc. One of the primary use cases is improved coding, debugging,…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 28d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com