Search
Interfaces
Search
Find the best tool for a development task
POST
Search
Search the Index
The core endpoint. An AI reasoning agent analyzes your query against the catalog and returns the best match with an explanation and install instructions. Every matched response is complete and actionable — install steps, env vars, and a tracked click link are included when the recommended service has a destination URL.Request
What you need. Natural language — e.g. “serverless database with free tier” or “auth for Next.js with SSO”
Pass a
search_id from a previous response to ask a follow-up question. The Index maintains conversation context.Additional project context. Framework, language, constraints, etc.
Publisher API key for attribution.
Your stable chat/session ID. Stored for attribution and payout matching; not used for recommendation reasoning.
Hash of your user ID. Prefer this over sending a raw user identifier.
Optional raw user ID. Gravity stores only a SHA-256 hash.
SHA-256 of the user’s normalized email (
email.strip().lower()), when available. This is the canonical field and matches the ad request convention. The legacy email_hash field is still accepted as an alias.Non-sensitive publisher metadata such as surface, workspace, plan, or placement. Stored with the search for attribution/debugging; not used in the LLM prompt.
Optional private publisher ranking controls. Requires
platform_api_key. Supported mode: boost_cpa — relevance-first ranking that gives a small boost to services with an active CPA campaign. Omit (or use off) for pure relevance. Economics are not returned in the response.Response
Unique ID for this search. Pass it back for follow-ups.
The recommended service.
Why this tool is the best fit for your specific query. Natural language explanation.
Structured install instructions the agent can execute.
Explicit handoff instructions for credentials the human user must fetch.
Tracked short link the user visits to get their API credentials.
Gravity Index click ID minted for the tracked click link.

