Quickstart
Compare tradeoffs, transfer concepts, or fetch curated MIT JSON — same records for you and your agents. Start
with the 140-language reference (deepest layer), hand-curated tools (14) and stacks (7),
preview registry snapshots, or the experimental Advisor — whichever path matches your question.
Curation pipeline notes (including data sources in §1.5) are in the repo under docs/PROCESS_LAYER.md.
1. Language reference (core)
- Open Catalogue (languages layer is the default).
- Use Compare or Transfer for two-language tradeoffs.
- Fetch
/api/languages.jsonfor agents and tools.
2. Experimental Advisor
Advisor (experimental) — drafts a language-oriented Decision Brief from one prompt. Verify against official docs.
- Open Advisor.
- Describe what you are building or deciding.
- Read the Decision Brief draft; copy the structured handoff if you work with agents.
Compare — language compare is deepest; other layers show metadata previews.
- Open Compare.
- Select two entries and scroll the dimensions.
Public example: Go vs TypeScript for background workers
Try this real prompt in Advisor:
We need background workers for webhooks, retries, and queue processing. Small team. Strong TypeScript experience. Should we stay on TypeScript or move the worker layer to Go?
A good Decision Brief should give you:
- a default recommendation tied to the current team and workload,
- viable alternatives and the trigger for choosing them,
- an avoid/defer list so complexity is not mistaken for maturity,
- evidence links into language records, compare view, and proof status,
- a copyable Markdown brief plus a separate agent handoff.
Want the side-by-side language lens after the brief? Open Compare: TypeScript vs Go.
3. Open JSON or integrate an agent
- Read For agents for MCP tools, HTTP routes, and static JSON entrypoints.
- Fetch
/api/agent-entrypoints.jsonfirst — it lists the recommended URLs for your deployment. -
For catalogue data on the same origin:
/api/languages.json; registry indexes under/api/model-registry/,/api/agent-registry/,/api/company-registry/, and/api/benchmark-registry/. -
Human-readable pages: languages at
/language?lang=<id>; models, agents, companies, and benchmarks at/entity-detail?layer=…&id=…(links from the catalogue).
More help
- First-use guide (catalogue UI walkthrough)
- FAQ
- Troubleshooting
- Use cases
- llms.txt (agent-oriented index)