LibreChat

LibreChat. Docs checked 2026-10-12.

Multi-provider chat UI. Custom OpenAI-compatible endpoints live in librechat.yaml.

What it’s for

One UI for local /v1 and cloud providers.

Local endpoint

llama-server base: http://127.0.0.1:8080/v1
Strata base: http://127.0.0.1:8083/v1
Model name: endpoints.custom[].models.default
API key: '${LLAMA_KEY}' in yaml, real value in .env (placeholder locally)

Tool calling

Product has tools/agents; whether they fire against llama-server tool-calling is not documented here.

Long context

Server -c.

ROCm / Radeon gotchas

Docker needs host.docker.internal. You own the GPU process.

Hybrid local + cloud

Yes — that is the product.

This is the same question as the calculator’sfully localversushybridtoggle. This page does not quote cloud prices.

Official links

Sources

Copy-paste

More on the connect page. Prove http://127.0.0.1:8080/v1/models first.

LibreChat → llama-server :8080librechat.yaml

# librechat.yaml — endpoints.custom
endpoints:
  custom:
    - name: "llama-server"
      apiKey: "${LLAMA_KEY}"
      baseURL: "http://127.0.0.1:8080/v1"
      models:
        default: ["qwen"]
        fetch: false
# Put LLAMA_KEY=local-not-a-secret in .env (placeholder locally).
# Docker: host.docker.internal, not 127.0.0.1.

Exact llama-server flags for our daily driver stay TODO in stacks.yaml. This is the port only.

LibreChat → Strata :8083librechat.yaml

# librechat.yaml — endpoints.custom
endpoints:
  custom:
    - name: "Strata"
      apiKey: "${LLAMA_KEY}"
      baseURL: "http://127.0.0.1:8083/v1"
      models:
        default: ["qwen"]
        fetch: false
# Put LLAMA_KEY=local-not-a-secret in .env (placeholder locally).
# Docker: host.docker.internal, not 127.0.0.1.

Exact Strata flags for our rig stay TODO in stacks.yaml. This is the port only.