CommitCraft
AI-generated Git commit messages in one keystroke
What it does
Tired of writing "fix stuff" as a commit message? CommitCraft reads your staged git diff and generates 3 professional commit message options automatically. Conventional Commits format, scope detected from file paths, breaking changes flagged. Works with every programming language. Free for 30 generations, then $49 lifetime for unlimited.
Does the same job
all alternatives →- GCGenerate commit messages using GPT-32023 · github.com · ▲75
- BTBuild the habit of writing meaningful commit messagesNov 2025 · github.com · ▲110
Too often I find myself being lazy with commit messages. But I don't want AI to write them for me... only i truly know why i wrote the code i did. So why don't i get AI to help me get that into words from my head? That's what i built: smartcommit asks you questions about your changes, then helps you articulate what you already know into a proper commit message. Captures the what, how, and why. Built this after repeatedly being confused 6 months in a project as to why i made the change i had made... Would love feedback!
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 · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d 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 · 27d 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