Docs

How the pieces of Bring Your LM work — what each capability does, when to reach for it, and what it does not do yet.

• Providers — bring your own LLM

  Shipped

  The kinds of model backend you can point an agent at, what each one needs from you, and how much it can tell you about a model.

• On-device models — run fully offline

  Shipped

  The embedded llama.cpp provider runs your own GGUF model files in-process — no server, no URL, no API key — with a compute backend you pick per device, and vision support.

• Agents — the thing you build

  Shipped

  What an agent is: a provider, a model, a system prompt, the sampling and reasoning controls a model supports, and the tools it can call.

• Tools — giving an agent more than the model knows

  Shipped

  The kinds of tool an agent can call mid-conversation, which ones you configure, and how an agent can even build its own tools and manage other agents.

• Workspaces — keep your work in scopes

  Shipped

  Group your agents, tools and conversations into named workspaces, each with its own defaults, default agent, and overrides for titles, compaction, and the conversation loop.

• Conversations — how a turn runs

  Shipped

  What happens when you send a message: streaming, mid-turn tool calls, a durable cancel, attachments, search, and reading the metrics behind each reply.

• Attachments — images and files in a message

  Shipped

  Attach an image or a text file to a message when the model can read it: what's supported, how the app gates the button on the model's own capabilities, and where the bytes go.

• Context management — what the model still sees

  Shipped

  Long conversations no longer silently drop their oldest messages. Choose how much history the model keeps and how to represent what falls out — globally, per workspace, or per agent.

• Background turns — replies that keep running

  Shipped

  An assistant reply is a durable background job: leave the chat or the whole app and it keeps generating, notifies you when it's ready, and shows up on the Jobs page.

• Local-first & private by design

  Shipped

  Where your data lives (on your device), how secrets are kept out of it, and what does — and doesn't — leave when you turn on sync.

• Sync — your data across your devices

  Shipped

  How Bring Your LM replicates to a Couchbase Edge Server you run, what travels and what stays on the device, why secrets don't ride along by default, what the status icon means, and how to stand a server up.

• Running a Couchbase Edge Server

  Shipped

  A copy-and-run example — a Dockerfile, a docker run command, and the config and users files — for the server Bring Your LM syncs against.

• Spell checking — catch typos while you write

  Shipped

  Misspelled words are underlined in every prompt field, with replacements a tap away. You choose the dictionaries; you bring them.