Sgai – Goal-driven multi-agent software dev (GOAL.md → working code)
Hey HN, We built Sgai to experiment with a different model of AI-assisted development. Instead of prompting step-by-step, you define an outcome in GOAL.md (what should be built, not how), and Sgai runs a coordinated set of AI agents to execute it. - It decomposes the goal into a DAG of roles (developer → reviewer → safety analyst, etc.) - It asks clarifying questions when needed - It writes code, runs tests, and iterates - Completion gates (e.g. make test) determine when it's actually done Everything runs locally in your repo. There’s a web dashboard showing real-time execution of the agent…
In plain words
Sgai is an AI-assisted development tool that automates software creation by taking a goal written in GOAL.md and executing it through coordinated AI agents. Instead of step-by-step prompting, users define the desired outcome and the system decomposes it into roles like developer, reviewer, and safety analyst that work together. It writes code, runs tests, iterates until completion gates are met, and displays progress through a web dashboard. Everything runs locally in the repository without auto-pushing changes.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, We built Sgai to experiment with a different model of AI-assisted development. Instead of prompting step-by-step, you define an outcome in GOAL.md (what should be built, not how), and Sgai runs a coordinated set of AI agents to execute it. - It decomposes the goal into a DAG of roles (developer → reviewer → safety analyst, etc.) - It asks clarifying questions when needed - It writes code, runs tests, and iterates - Completion gates (e.g. make test) determine when it's actually done Everything runs locally in your repo. There’s a web dashboard showing real-time execution of the agent graph. Nothing auto-pushes to GitHub. We’ve used it internally for prototyping small apps and internal tooling. It’s still early and rough in places, but functional enough to share. Demo (4 min): https://youtu.be/NYmjhwLUg8Q GitHub: https://github.com/sandgardenhq/sgai Open source (Go). Works with Anthropic, OpenAI, or local models via opencode. Curious what people think about DAG-based multi-agent workflows for coding. Has anyone here experimented with similar approaches?
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 · 26d ago · cactuscompute.com
