oss-search

Find open-source repositories by topic, name, or description. Returns a ranked shortlist with pre-computed fitness evidence (stars, license class, last release, archived flag, one-line what-it-is, one-line the-catch) — not a link dump. Lead with this for 'is there a tool for X' questions; use oss_search_code when the capability is an implementation detail no README advertises.

Find repos by distinctive code idioms, not marketing. Fires 2-5 orthogonal literal or /regex/ probes, aggregates hits PER REPO, and ranks by probe breadth (repos hitting several independent idioms outrank any star count). Use for: implementations of an API idiom, error string, or config key; finding peers of a known-good repo (steal its identifiers as probes). Do NOT use to test whether a category exists — probing your own idioms finds only clones; lead with oss_search_repos instead.

Pre-digested brief for ONE known repo: metadata, computed health verdicts, license compatibility class, README digest (<=1200 chars), top-level architecture from the file tree, release cadence, runtime-support evidence. Use instead of 5+ raw metadata calls; use oss_fetch_docs / oss_fetch_file to drill in.

Whole-repo file list in ONE call, path-filtered. ALWAYS call this before fetching any file whose path you are guessing — a 404 from a guessed path proves nothing. Response declares the total file count and returns up to `limit` paths with truncated/has_more set beyond.

Read one file's exact contents — byte-exact, never via a summarizer for opaque tokens, paths, or config keys. Prefer a line_range to keep payloads small; large files return the range plus total_lines.

Fetch a project's docs the reliable way: resolve llms.txt / llms-full.txt aggregates, then return search hits WITH their 'Source: <url>' breadcrumbs so each hit maps back to its page. Falls back to raw docs/*.md and flags redirect-stub pages. One aggregate fetch replaces a dozen lossy page fetches.

Returns the probe-writing and query-syntax playbook on demand: good vs bad probes, the backend regex support matrix, rate-limit traps, license-class meanings, and which tool answers which question (discovery vs vetting vs drill-down). Call once when unsure which oss_ tool to use.

Takes no parameters.