Atlas releases a web compilation API to provide structured context for AI Agents
Understand this story
Atlas releases a web compilation service that converts public web pages into clean Markdown and a typed IR with reading order and source provenance, for use by AI Agents. The company says the service can eliminate 99% of noise, with an output of 1,639 tokens. The platform provides REST/OpenAPI, SDK, and MCP interfaces, and includes 250 initial free compute credits. The above noise-reduction ratio and token count are Atlas's claims and have not yet been independently verified.
AI overview based on source reports · Updated 8 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIShow HN: Atlas – Give Your AI Agent Better Web Context
Atlas compiles public webpages into clean Markdown and a typed, versioned intermediate representation (IR) with reading order and provenance, using a five-stage pipeline of fetch, parse, analyze, optimize and emit. It offers REST/OpenAPI endpoints for compile, scrape, map, crawl and batch, plus generated JavaScript, Python and Go clients, a dashboard, webhooks and an MCP interface for AI agents. The project claims deterministic, inspectable and idempotent outputs, with a CLI listed as planned.
Activity for this story
- Current comparable activity
- 8
- Peak comparable activity
- 10Nov 18 01:00
- 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.