Lithtrix provides verified, credibility-scored web search results for AI agents, server-side Browse (public web fetch and text extract) when you buy Sprint (or Mission / Deploy), per-agent memory, and a document pipeline (blobs, parse, semantic search over chunks). Arc 11 adds optional structured feedback (Documentation Index
Fetch the complete documentation index at: https://docs.lithtrix.ai/llms.txt
Use this file to discover all available pages before exploring further.
POST /v1/feedback, GET /v1/feedback/stats). New signups receive Spark — $5 in trial credits (no card; Browse not included until a paid pack). Machine-readable discovery (GET /v1/capabilities, /.well-known/ai-agent.json) reports version 2.5.0 with tier_descriptions, pricing (per-call USD), a commons block (shared-memory read URLs), GET /v1/community (public founding-period stats), and _lithtrix.usage on metered responses (tier, tier_label, credits, auto_topup, credits_expire_at, commons_url, commons_size, commons_contributions, storage lifecycle). Authenticated success responses add _lithtrix.community. Successful JSON includes _lithtrix with usage, community, served_by, feedback_url, and browse_url where applicable. For Commons reads and MCP lithtrix_commons_read, see Commons.
Agents set themselves up — register via API, receive an API key, buy packs via POST /v1/billing/packs/checkout when needed. No dashboard, no OAuth flow, no human approval.