• 357 closed AI services in 21 categories: LLM APIs and gateways, embeddings, vector databases, RAG, document parsing, observability, speech, image generation, search, scraping, browser automation, sandboxes, agents and agent memory. 139 hosted model providers come from models.dev, regenerated weekly.
• 204 model retirements from OpenAI, Anthropic and Google, with dates and the vendor's replacement, checked weekly against their deprecation pages. A model counts when the code picks it (a default, a config value, a call), not when it is only listed in a menu or price table. Azure, Bedrock and Vertex have their own schedules and are not covered.
• 89 open source projects you may already run: vector databases, inference servers, gateways, RAG frameworks, document parsers, observability, evals, speech.
• Unknown candidates: API hosts and keys that look like a hosted AI service the catalog doesn't know yet. Listed for you to check, never counted.

It reads packages (Python, npm, Go, Cargo, Maven, Gradle, NuGet, RubyGems, Composer, pub, SwiftPM), imports, install commands, container images, and API hosts, model ids, env vars and SDK calls in code and config.

• Local servers behind a compatible SDK: OpenAI(base_url="http://localhost:11434/v1") is Ollama, not OpenAI.
• Comments, docs, lockfiles, node_modules and anything .gitignore excludes.
• Generic names: your perplexity.py isn't Perplexity.
• Open-weight models: gpt-oss, deepseek-v3.2 and Ollama tags aren't closed.

Secrets in the output are masked (OPENAI_API_KEY=****). Files too large to scan are listed, never skipped silently.

• Projects by GitHub stars gained in the last 90 days, from unrent's own weekly snapshots (total stars until four weeks of history exist; the report says which).
• Models by Hugging Face trending: labs' own releases under an open licence.
• Open source only: an OSI licence for code; Apache, MIT, BSD or CC-BY for weights. Archived projects are dropped, and open core is marked.

The CLI uses the rankings shipped with its release. The MCP server fetches the latest from this repo, cached for six hours (UNRENT_OFFLINE=1 turns that off). Only rankings come in; your code never goes out.

Every rule has a test that fails without it. A golden corpus of 54 real repos, labelled by hand, runs in CI: closed services precision 0.993, recall 0.957; models that stop working precision 0.939, recall 0.886.

With ripgrep installed, a 5,500-file repo scans in about 6 s.