The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the FRESH — Shared URL Freshness Intelligence listing page.
Know whether to fetch again.
FRESH is shared URL freshness intelligence for AI agents. Before re-fetching, re-scraping, re-rendering, or re-embedding a URL, ask whether the previously seen version is probably still fresh enough to reuse.
Production base URL: https://fresh-api-production-c783.up.railway.app
MCP endpoint: https://fresh-api-production-c783.up.railway.app/mcp
FRESH returns one of three decisions:
REUSE — cached knowledge is probably still fresh enoughREFETCH — the URL is likely stale enough to justify another retrievalUNKNOWN — evidence is insufficient; FRESH prefers uncertainty over false confidenceA local cache knows when you last fetched something. It does not know whether the outside resource changed since then, nor what other callers recently observed. FRESH builds shared, privacy-safe URL change history from timestamps, ETags, Last-Modified values, and content hashes.
POST /v1/checkPOST /v1/observeRaw page content is not required.
fresh_check — decide whether to retrieve a URL againfresh_observe — report privacy-safe freshness evidence after retrievalFRESH does not need raw page contents, cookies, target-site credentials, or customer payloads. URL keys are stored as one-way hashes with aggregate observation metadata.
A core-tool invocation is evidence of use, not automatically proof of a genuine stranger. FRESH classifies candidate activity as KNOWN_VALIDATOR, LIKELY_VALIDATOR, CONTROLLED_TEST, UNKNOWN_MACHINE, or CREDIBLE_REAL_USE. Only CREDIBLE_REAL_USE advances stranger milestones.
Our acceptance/smoke traffic uses X-Tollbooth-Internal: 1 or X-Fresh-Internal: 1 so it cannot earn stranger credit.
Every Railway deployment now performs live internal checks against the running service before /health can return 200. The gate exercises REST, UNKNOWN, REUSE, REFETCH, persistent observation reload, MCP initialize, MCP tool discovery, MCP fresh_check, and verifies that the controlled self-test does not increase the verified-stranger count.
v0.1.2 experimental production infrastructure. Priorities: conservative decisions, low latency, sub-penny economics, privacy-safe shared learning, REST + MCP, durable observations, and auditable real-use analytics.