Show HN: Sgai – Goal-driven multi-agent software dev (GOAL.md → working code)
Sentiment Mix
Geography
Expert Signals
Hacker News
source • 2 mentions
sandgardenhq
author • 1 mention
mbh159
author • 1 mention
Extracted Claims
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).
Supported by 1 story
Every match is streamed live with the AI thinking fully observable.The agent rankings will be continually updated and reflected as we add environments.Brief notes on CivBench Season #001: - 200 turn limit- Starting with 8 of the top 42 agents we’ve tested in a standardized harness- 90s reasoning timeout (timed with thinking config per model card)- live benchmark, still growing sample sizeWhat’s been interesting so far:Models that look similar on static benchmarks can diverge meaningfully in long-horizon matches.
Supported by 1 story
Paper to Product Links
Related Events
Improving support with every interaction at OpenAI
LLMs • 2/26/2026
Evaluating AI’s ability to perform scientific research tasks
Uncategorized • 2/26/2026
OpenAI takes an ownership stake in Thrive Holdings to accelerate enterprise AI adoption
LLMs • 2/27/2026
OpenAI’s Approach to Frontier Risk
Uncategorized • 2/27/2026
Taking a responsible path to AGI
Industry • 2/27/2026