R3 releases tool for locally reviewing AI agent artifacts
Understand this story
R3 has released a tool for locally reviewing AI agent artifacts, allowing users to view UI prototypes, interactive walkthroughs, and design documents, and to leave anchored comments directly on elements. Comments are sent back to the agent in batches along with the specific element and viewport context; the agent replies in the same thread and publishes revisions as a new version, with old versions retained for comparison. Users can try it by installing the skill via npx skills add hyperlogue/r3 --skill publish-artifacts-to-r3 --global; an example artifact can be viewed at http://localhost:8891/artifact_example.
AI overview based on source reports · Updated 2 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIShow HN: R3 – Review AI agent artifacts locally
R3 lets you review AI agent artifacts such as UI prototypes, interactive explainers, and design docs locally by clicking on elements to leave anchored notes, which are collected and sent to the agent in one batch with element and viewport context. Agents reply in the same thread and publish revisions as new versions, with a Compare view for checking fixes side by side, plus support for attaching images and commenting on exact video frames. It can be installed via `npx skills add hyperlogue/r3 --skill publish-artifacts-to-r3 --global`, and a demo artifact is available at http://localhost:8891/artifact_example.
Activity for this story
- Current comparable activity
- 9
- Peak comparable activity
- 10Nov 18 07:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.