#open-source

We built a playable simulation of a different AI future: cheap, open intelligence lets everyone chase a question, and a shared Commons checks what holds up and shares credit with the people behind it.

Explorers find things. Makers build the tools. Verifiers test the claims. Try changing the incentives and watch the system behave differently. It is a synthetic thought experiment with fictional people and imaginary credits, not a live research network.

Play: drop4u.pages.dev/projects/discovery-commons/
49-second explainer: x.com/jayuhdinger/status/2113984643481653499

GitHub - veiovi/discovery-commons: Everyone gets a lab. A playable simulation: Explorers, Makers and Verifiers feed one shared Commons that checks what's real and rewards everyone who moved it forward

One API call creates an agent, and Omnara gives it sandboxes, secrets, permissions and the usual harness tools, on the model you pick and on your own servers if you like. The design is the interesting part: every step an agent takes is appended to a log in Postgres and any free worker can run the next one, so an agent outlives crashes and redeploys and holds no worker while it waits. Apache 2.0, with a hosted version as well.

Made by the Omnara team. Kartik from Omnara posted it to Hacker News: news.ycombinator.com/item?id=50183892

GitHub - omnara-ai/omnara: The open-source managed agent platform. A self-hostable alternative to Claude Managed Agents and OpenAI's Agents API.

Hallmark is a skill for Claude Code, Codex, Cursor and OpenCode. It picks three themes from a catalog of forty-eight, builds the page around what the visitor came to do, then checks the result in a real browser for the tells of machine-made pages: an eyebrow above every heading, tracked-capital labels, one coloured word in a headline. Open source under MIT.

Made by Nutlope and Together AI, not me.

GitHub - Nutlope/hallmark: Anti-AI-slop design skill for Claude Code, Cursor, and Codex.