Skip to content

Facet changelog

io.github.halfspacelabs/facet

5 changes recorded. MCP Harbor re-reads this listing from the official registry every six hours and asks the live server what it exposes, and keeps what changed between one look and the next.

  • server.json 2 fields changed
    description
    Ask for a model and Facet does the rest: it builds, checks and serves a model for one task. Facet's agent builds, evaluates, serves and maintains a small model for one repeated task.
    version
    1.5.0 1.5.2

  • server.json 1 field changed
    version
    1.4.1 1.5.0

  • server.json 1 field changed
    version
    1.4.0 1.4.1
  • llms.txt +17 −6

    https://facet.halfspacelabs.com/llms.txt

    − > Build a specialized model for one task, check it, and call it like any model.− Facet builds a specialized model for one narrow task, checks every change against plain-language Expectations, and serves it through an OpenAI-compatible API. Agents use it through the MCP server at https://facet.halfspacelabs.com/mcp.− - [Overview](https://facet.halfspacelabs.com/docs/index.md): Build a specialized model for one task, check it, and call it like any model.− - [Quickstart](https://facet.halfspacelabs.com/docs/quickstart.md): Make a Task, call it from your code, and ask for it to get better.− - [Concepts](https://facet.halfspacelabs.com/docs/concepts.md): Tasks, Asks, Changes, Expectations and Versions, and how they fit together.− - [Call a Task](https://facet.halfspacelabs.com/docs/call.md): Call any Task through the OpenAI-compatible API with the OpenAI SDK.+ > Facet takes a task from one plain-language ask to a live model. Its agent builds, checks and serves a model for the task you describe.+ Facet takes a task from one plain-language ask to a live model: its agent builds a model for one narrow task, runs plain-language evals on every change, and serves it through an OpenAI-compatible API. Agents use it through the MCP server at https://facet.halfspacelabs.com/mcp.+ - [Overview](https://facet.halfspacelabs.com/docs/index.md): Facet takes a task from one plain-language ask to a live model. Its agent builds, checks and serves a model for the task you describe.+ - [Quickstart](https://facet.halfspacelabs.com/docs/quickstart.md): Make your first Model, call it from your code, and ask for it to get better.+ - [Write good evals](https://facet.halfspacelabs.com/docs/evals.md): Say what a good answer does, in plain statements Facet can check on every change.+ - [Add examples](https://facet.halfspacelabs.com/docs/examples.md): Upload real inputs and answers as CSV or JSON lines, and let Facet write the rest.+ - [Make a Model better](https://facet.halfspacelabs.com/docs/improve.md): Say what should change, approve the quote, and Facet makes the fix, checks it and puts it live.+ - [Return structured output](https://facet.halfspacelabs.com/docs/structured-output.md): Get answers as plain text, as fields you name, or as JSON of any shape.+ - [Export your model](https://facet.halfspacelabs.com/docs/export.md): Download a Model's live version, its Instructions, examples and evals, and run it anywhere.+ - [Call a Model](https://facet.halfspacelabs.com/docs/call.md): Call any Model through the OpenAI-compatible API, with every parameter and header it takes.+ - [Errors](https://facet.halfspacelabs.com/docs/errors.md): Every error a Model call or the API returns, why it happens and what to do.+ - [Limits](https://facet.halfspacelabs.com/docs/limits.md): How many calls, tokens and running jobs a workspace gets, and what happens past them.+ - [Base models](https://facet.halfspacelabs.com/docs/base-models.md): The open models Facet builds every Model on, what each suits, and what calls cost.+ - [Pricing and billing](https://facet.halfspacelabs.com/docs/pricing.md): What building, improving and calling a Model costs, how quotes work, and how you're billed.+ - [Concepts](https://facet.halfspacelabs.com/docs/concepts.md): Models, Changes, evals and Versions, and how they fit together.+ - [Privacy and data](https://facet.halfspacelabs.com/docs/privacy.md): What Facet keeps, who sees your data, how hidden examples stay hidden, and how to delete.+ - [Changelog](https://facet.halfspacelabs.com/docs/changelog.md): What's new in Facet, month by month.

  • server.json 2 fields changed
    description
    Build, check and call a specialized model for one narrow task, from your agent. Ask for a model and Facet does the rest: it builds, checks and serves a model for one task.
    version
    1.0.0 1.4.0