Who it is forA developer scripting local model setup across machines.
The problemManual model choice does not scale across machines.
The outcomeJSON recommendations filtered by use case.
What you need first
- macOS, Windows, Linux or Docker
Steps
- Install llmfit
- Run
llmfit recommend --json - Filter by use case, for example coding, in Docker or podman
- Parse the model names with jq
Prompt for your agent
Run `llmfit recommend --json` and return the top three model names for coding on this machine.
Caveat. JSON fields can change between versions; pin a version for scripts.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for AlexsJones/llmfit and "Get model recommendations as JSON for scripts"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer