the provider catalog

LocalAI

{"meta":{"title":"LocalAI · a self-hosted endpoint for Nika workflows","angle":"A self-hosted server that speaks the familiar API shape, with a model gallery and a web UI: one shared endpoint instead of per-laptop runtimes.","pick":"when a team wants one local endpoint they administer together.","note":"Open source (MIT), community-led.","setup":[{"text":"Run the container","code":"docker run -p 8080:8080 --name local-ai -ti localai/localai:latest"},{"text":"Pick models from its gallery. No key."}]},"usage":{"id":"localai","yaml":"nika: v1\nworkflow:\n  id: self-hosted-triage\n  description: \"your own server, the familiar API shape — LocalAI on localhost:8080\"\n\ntasks:\n  triage:\n    infer:\n      model: localai/default\n      max_tokens: 120\n      prompt: |\n        Three support lines arrive. Order them most urgent first:\n        payment page 500s, typo in footer, password reset loops.\n\noutputs:\n  order: ${{ tasks.triage.output }}\n","file":"localai.nika.yaml"},"audit":{"clean":true,"models_resolve":true,"tasks":1,"waves":1,"cost_ceiling_usd":null,"cost_floor_usd":0,"pricing":[{"model":"localai/default","input_per_million":null,"output_per_million":null}],"pricing_as_of":"2026-07-07"}}

[{"slug":"default","id":"default","aliases":["default"]}]

A self-hosted server that speaks the familiar API shape, with a model gallery and a web UI: one shared endpoint instead of per-laptop runtimes. One provider/model line moves a workflow here or away again: the same file runs on every provider the catalog names, and swapping is a one-word diff. Machines read the catalog; the binary answers nika catalog.

1pinned modelaliases pin exact upstream ids
localfamilythe sovereign default: your hardware, no key
no keynothing to leakthe sovereign path
openai-chatwire dialectthe adapter speaks it

the wire

local · the sovereign default: your hardware, no key

A workflow names this provider in the model line (model: localai/default), and the engine speaks openai-chat on the wire. No key exists on this path: nothing to rotate, nothing to leak.

default: default
dialect: openai-chat
tags: local · open-source

the models

1 pin

Aliases are what the file may write; the engine pins each one to an exact upstream id, so a run stays reproducible after a vendor rotates names.

defaultdefaultctx 128k · vision

in the released catalog

1 room

The wire models this provider serves in the released binary's catalog · each one is a room with its seats, exact prices and measured energy.

defaultas default

the whole register: /catalog/models · what the released binary knows, vendored at the engine pin.

in a real file

a complete workflow · shown whole

localai.nika.yaml

1nika: v12workflow:3  id: self-hosted-triage4  description: "your own server, the familiar API shape — LocalAI on localhost:8080"56tasks:7  triage:8    ◇infer:9      model: localai/default10      max_tokens: 12011      prompt: |12        Three support lines arrive. Order them most urgent first:13        payment page 500s, typo in footer, password reset loops.1415outputs:16  order: ${{ tasks.triage.output }}17

check-green against the released engine · 1 task · 1 wave · no closed ceiling: an unpriced model is unpriced, never free · the drift gate re-proves this copy on every test run · open it in the playground →

get set up

1Run the container docker run -p 8080:8080 --name local-ai -ti localai/localai:latest
2Pick models from its gallery. No key.

Pick it for when a team wants one local endpoint they administer together. Open source (MIT), community-led. Then prove the seat: nika doctor names every provider this binary can reach.

swap it

4 more local seats

Moving off LocalAI is editing one line. The rest of the file (tasks, permits, outputs, the trace) does not change. The register orders the catalog local first; beyond it the engine embeds 21 more OpenAI-compatible endpoints.

model: localai/default model: mistral/mistral-large-latestthe whole migration · nothing else moves

cross-references

the words that meet it

[]

where it lives

Try it in the playground, or install and go local first. Read the spec →