Sgai
Goal-driven multi-agent software dev (GOAL.md → working code)
Details
- External ID
- 47153941
- Source
- HN
- Company
- —
- Product
- Sgai
- Website domain
- github.com
- Launched
- Feb. 25, 2026
- Cohort
- —
- Upvotes
- 36
- Upvotes percentile
- 0.7688679245283019
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
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 doneEverything 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/sgaiOpen 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?
Enrichment
- Theme
- developer tools for AI agents
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- multi-agent system to write software from goals
- Manually corrected
- False
Could you build this?
Yes Sgai is an LLM agent orchestrator that decomposes a Markdown goal into tasks and executes bash/file operations using standard LLM API loops and DAG scheduling.
Discussion
20 comments analyzed.
Competitors mentioned: Claude Code (Anthropic), Gas Town (Yegge's concept)
Concerns raised: Custom license may not hold up in court without legal review, UX friction for multi-repository setup requires extra steps, Unclear how DAG decomposition handles multi-service goals, Limited examples of large-scale app generation in practice, One-shot generation capability uncertain for large applications
Feature requests: GOAL.md examples and guidelines for writing effective prompts, Native multi-repository support without manual directory setup, Parallel agent execution for improved output speed, Better documentation on cross-repository file change coordination
Competitors
Other products that read as similar to this one — 396 launches clear the similarity bar, closest 8 shown.
Attention rank: #97 of 397 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 114 days after the earliest competitor.
- First autonomous ML and AI engineering Agent · hn · 2026-01-22 · 5 upvotes · similarity 0.46
- Keen Code · hn · 2026-08-10 · 6 upvotes · similarity 0.44
- Cq · hn · 2026-03-23 · 225 upvotes · similarity 0.44
- Task Manager for AI Agents (MCP, Opensource) · hn · 2026-04-30 · 6 upvotes · similarity 0.44
- OpenTiger · hn · 2026-02-22 · 11 upvotes · similarity 0.44
- Teaching AI agents to write better GraphQL · hn · 2026-02-04 · 6 upvotes · similarity 0.44
- OpenRig · hn · 2026-05-22 · 6 upvotes · similarity 0.43
- Mercury · hn · 2026-04-13 · 6 upvotes · similarity 0.43
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.