Mimir

AI accounts

Mimir has no model of its own. Each bot uses an AI account you choose, on the bot's page.

Account How Mimir uses it Cost
Claude Runs the official claude CLI (claude -p) with your signed-in subscription Your plan
ChatGPT Sign in with ChatGPT in Mimir; bots call OpenAI's API on your Plus or Pro plan. Nothing to install Your plan
Codex CLI Runs the official codex CLI (codex exec) with your ChatGPT login Your plan
Grok Runs Grok Build (grok -p) on your X Subscription plan (or an older SuperGrok or X Premium+ plan) Your plan
OpenRouter One key for hundreds of models (only ones that can use tools are offered) What OpenRouter charges
xAI API A per-token key from console.x.ai Per token
Local model Ollama (localhost:11434) or LM Studio (localhost:1234); nothing leaves your computer Free
OpenAI-compatible OpenAI or any compatible service, with a key and base URL Per token

Web search. Bots on Claude search the web on their own (Claude's built-in search). For bots on any other account, set up Brave Search or your own SearXNG once in Settings → Web search, and every bot can search (how).

Signing in #

A fallback for usage limits #

A bot's page can name a second account for its routines while its own is at a usage limit, until the limit resets (how it works). It's another kind of account, not a second login of the same kind: Mimir uses one Claude, ChatGPT or Grok sign-in for all bots.

On The X Subscription, Grok's allowance is one weekly pool shared by everything on that plan: the Grok apps, Grok Bot and Cursor. Coding in Cursor or chatting in Grok uses up the same allowance your bots run on, so a fallback account is worth setting for Grok bots.

How tools reach the model #

The CLIs (Claude, Codex, Grok) start Mimir as an MCP server for each run, so the model sees Mimir's tools (memory, routines, web pages, meetings…) the same way it sees any tool. API accounts get the same tools as function-calling definitions. Either way, every call passes through Mimir's rules (see Tools, approvals and safety).

Local models #

The app finds a running Ollama or LM Studio and lists its models. Models that can't use tools are flagged: they can chat but can't remember things or run routines. Ollama's default 4k-token context drops older messages in a long conversation (instructions and memory are kept); start it with OLLAMA_CONTEXT_LENGTH=16384 for more.

What a run costs #

The run log shows each reply's model, tokens and cost. For Claude it's the API list-price equivalent that claude -p reports (subscriptions aren't billed per token); OpenRouter runs show what OpenRouter charged; other key and local runs show tokens only.