Drive Mimo logo

Drive Mimo

OrganizationPopular
XiaomiMiMo
drive-mimo

Use when developing or testing the MiMoCode repository and you need to programmatically drive another MiMoCode (mimo) process. Supports headless `mimo run` with JSON events and interactive TUI via tmux for behavior, integration, and visual regression testing. Covers an installed `mimo` binary or a dev build launched from source with `bun dev`; do not use it for ordinary MiMoCode task execution.

Overview

PublisherXiaomiMiMo
RepositoryMiMo-Code
Skill namedrive-mimo
Stars
13.6K
Forks
1.4K
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by XiaomiMiMo on GitHub. Read the source before you install it.

Installation

Install the Drive Mimo AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/XiaomiMiMo/MiMo-Code/tree/main/.agents/skills/drive-mimo
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/XiaomiMiMo/MiMo-Code.git /tmp/MiMo-Code
mkdir -p .claude/skills
cp -r /tmp/MiMo-Code/.agents/skills/drive-mimo .claude/skills/drive-mimo
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Drive Mimo in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Drive Mimo on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Drive Mimo is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Drive MiMo

Overview

Two interfaces for driving a separate mimo process:

InterfaceCommandUse when
Headlessmimo run --format jsonScripted tasks, CI, event validation
TUImimo in tmuxInteractive flow, permission dialogs, keybindings, visual regression

Core principle: Every run produces parseable evidence. No eyeballing.

Always drive an isolated instance: give each run a fresh MIMOCODE_HOME and a throwaway workspace so it never touches your own config, memory, or session DB.

Two ways to launch — orthogonal to interface

The interface (headless vs TUI, above) is what you drive. How the process is launched is a separate axis — either can be launched either way:

LauncherCommandUse when
Installed binarymimo …Testing a released/installed build
Dev (from source)bun dev …Debugging mimocode itself — runs src/index.ts directly, no build step, picks up local code changes

Everything below uses mimo for brevity. To drive a dev build instead, substitute bun dev for mimo and run from the repo root — every flag, JSON event, and tmux technique is identical. See the Dev Mode section.

Prerequisites

bash
# mimo binary must be on PATH (installed-binary launcher)
which mimo || echo "mimo not found on PATH"

# OR: dev launcher — run from the mimocode repo root, needs bun
which bun || echo "bun not found — needed for dev mode"

# tmux (for TUI interface)
which tmux || echo "tmux not found — install it for TUI mode"

Running the wait-for-text.sh helper: invoke it as ./scripts/wait-for-text.sh … from this skill's directory. The repository copy is executable and can be called directly.


Dev Mode (debugging mimocode itself)

When the goal is to debug mimocode's own code, launch from source with bun dev instead of the installed mimo binary. It runs packages/cli/src/index.ts directly — no build step — so local edits take effect on the next launch.

Key facts:

  • Run from the repo root. bun dev == bun run dev.
  • It is the dev equivalent of the mimo command: same CLI, same subcommands and flags. bun dev --help, bun dev run …, bun dev serve, etc.
  • Args pass straight through, so both interfaces work under dev:
    • Headless: bun dev run --format json --dangerously-skip-permissions …
    • TUI: bun dev <workspace> (positional workspace arg, as with mimo)
  • If MIMOCODE_HOME is not set, dev defaults it to a repo-local .dev-home dir. For an isolated driven run, set MIMOCODE_HOME=$(mktemp -d) explicitly just like with the binary.

Substitution rule: anywhere Part 1 / Part 2 / Part 3 below say mimo, replace it with bun dev (invoked from the repo root) to drive a dev build.

bash
# Headless, dev build (from repo root)
REPO=/path/to/mimocode/checkout   # your local mimocode repo root
MIMOCODE_HOME=$(mktemp -d) bun --cwd "$REPO" dev run \
  --format json --dangerously-skip-permissions --dir "$WORKSPACE" \
  < "$PROMPT" > /tmp/mimo-dev.jsonl 2>&1

# TUI, dev build in tmux (from repo root)
tmux new-session -d -s "$SESSION" -x 120 -y 30 \
  "cd $REPO && MIMOCODE_HOME=$(mktemp -d) MIMOCODE_PURE=true bun dev $WORKSPACE; sleep 999"

Part 1: Headless Mode (mimo run)

Launch

bash
PROMPT=$(mktemp -t mimo-drive.XXXXXX)
cat >"$PROMPT" <<'EOF'
Your task here.
EOF

MIMOCODE_HOME=$(mktemp -d) mimo run \
  --format json \
  --dangerously-skip-permissions \
  --dir "$WORKSPACE" \
  < "$PROMPT" > /tmp/mimo-out.jsonl 2>&1

EXIT=$?

Key flags

FlagPurpose
--format jsonStructured JSONL events to stdout
--dangerously-skip-permissionsAuto-approve all permissions
--model provider/modelOverride model
--agent composeUse compose agent
--session SIDContinue existing session
--continueContinue last session
--file pathAttach file to message
--dir pathWorking directory

JSON event types

--format json writes one JSON object per line. Every event has the shape {"type": ..., "timestamp": <ms>, "sessionID": "ses_...", ...payload} — the sessionID is a field on each event, not a standalone event. The payload for most events is nested under part.

Emitted event types (from the run event stream):

{"type":"step_start","timestamp":...,"sessionID":"ses_abc","part":{...}}
{"type":"text","timestamp":...,"sessionID":"ses_abc","part":{"type":"text","text":"I'll create the file...","time":{...}}}
{"type":"reasoning","timestamp":...,"sessionID":"ses_abc","part":{"type":"reasoning","text":"The user wants..."}}
{"type":"tool_use","timestamp":...,"sessionID":"ses_abc","part":{"type":"tool","tool":"write","state":{"status":"completed",...}}}
{"type":"step_finish","timestamp":...,"sessionID":"ses_abc","part":{...}}
{"type":"error","timestamp":...,"sessionID":"ses_abc","error":{...}}

Notes that matter for parsing:

  • No session.id, no tool_result, no session.status event. A tool_use is emitted once per tool part when it reaches completed or error — the result/output is inside part.state, there is no separate result event.
  • tool_use identifies the tool via part.tool (a bare string, e.g. "tool":"write") — there is no .tool.name and no top-level .name.
  • text / reasoning text lives at part.text, not top-level .text.
  • reasoning is only emitted when --thinking is passed. Without it, no reasoning events appear.
  • Completion is not a stream event. The process finishes when the run completes; the reliable completion signal is process exit (exit code 0), not any line in the JSONL.

Validation patterns

bash
# Completion — the real signal is the exit code, not a stream event
[ $EXIT -eq 0 ] || echo "FAIL: exit $EXIT"

# No errors
grep -q '"type":"error"' /tmp/mimo-out.jsonl && echo "FAIL: errors found"

# A specific tool was used (match part.tool, the bare string)
grep -q '"tool":"write"' /tmp/mimo-out.jsonl || echo "FAIL: write tool not called"

# Text output contains expected string (text is at .part.text)
grep '"type":"text"' /tmp/mimo-out.jsonl | jq -r '.part.text' | grep -q "expected"

# Robust tool check via jq (works regardless of key ordering)
jq -e 'select(.type=="tool_use") | .part.tool=="write"' /tmp/mimo-out.jsonl >/dev/null \
  || echo "FAIL: write tool not called"

Timeout

bash
timeout 120 mimo run --format json --dangerously-skip-permissions < "$PROMPT"
[ $? -eq 124 ] && echo "FAIL: timed out"

Part 2: TUI Mode (tmux)

Isolation variables

VariablePurpose
MIMOCODE_HOMERequired. Fresh mktemp -d per run. Sandboxes DB, config, cache.
MIMOCODE_PURE=trueDisable external plugins.
MIMOCODE_DISABLE_GIT=trueSkip git ops if workspace isn't a real repo.

Launch TUI in tmux

bash
# Create isolated environment
MHOME=$(mktemp -d)
WORKSPACE=$(mktemp -d)
SESSION="mimo-drive-$$"

# Launch mimo TUI in tmux (workspace is a positional arg, NOT --dir)
tmux new-session -d -s "$SESSION" -x 120 -y 30 \
  "MIMOCODE_HOME=$MHOME MIMOCODE_PURE=true mimo $WORKSPACE; sleep 999"

# Wait for the TUI to render its input prompt
bash scripts/wait-for-text.sh -t "$SESSION:0.0" -p "$PROMPT_RE" -T 15

Where PROMPT_RE is a language-neutral pattern for the input prompt. The prompt placeholder is localized, so match on the stable markers rather than a localized string:

bash
# Matches the prompt line regardless of UI language:
#   the ">" input caret, the "Ask" English placeholder, or a "/" command hint
PROMPT_RE='>|Ask|/[a-z]'

If a run's UI language is known and fixed, you may match its literal placeholder instead — but prefer the neutral pattern for portability.

Send input

bash
# Type a message (literal text, then Enter)
tmux send-keys -t "$SESSION:0.0" -l -- "Create a file called hello.txt with content 'world'"
tmux send-keys -t "$SESSION:0.0" Enter

# Special keys
tmux send-keys -t "$SESSION:0.0" C-c          # Cancel
tmux send-keys -t "$SESSION:0.0" C-d          # EOF
tmux send-keys -t "$SESSION:0.0" Escape       # Escape
tmux send-keys -t "$SESSION:0.0" Tab          # Tab completion
tmux send-keys -t "$SESSION:0.0" Up           # History up
tmux send-keys -t "$SESSION:0.0" Down         # History down
tmux send-keys -t "$SESSION:0.0" Enter        # Submit

Capture output

bash
# Current screen
tmux capture-pane -t "$SESSION:0.0" -p

# Full scrollback
tmux capture-pane -t "$SESSION:0.0" -p -S -

# Last 50 lines
tmux capture-pane -t "$SESSION:0.0" -p -S -50

Wait for state changes

bash
# Wait for agent to start processing
bash scripts/wait-for-text.sh -t "$SESSION:0.0" -p "thinking\|reading\|writing" -T 30

# Wait for tool permission prompt
bash scripts/wait-for-text.sh -t "$SESSION:0.0" -p "Allow\|Deny\|permission\|approve" -T 30

# Wait for completion
bash scripts/wait-for-text.sh -t "$SESSION:0.0" -p "completed\|done\|finished\|idle" -T 120

# Wait for error
bash scripts/wait-for-text.sh -t "$SESSION:0.0" -p "error\|failed\|Error" -T 30

# Custom regex
bash scripts/wait-for-text.sh -t "$SESSION:0.0" -p "hello\.txt.*world" -T 30

Handle permission dialogs

bash
# Wait for permission prompt, then approve
bash scripts/wait-for-text.sh -t "$SESSION:0.0" -p "Allow\|approve" -T 30
tmux send-keys -t "$SESSION:0.0" -l -- "y"
tmux send-keys -t "$SESSION:0.0" Enter

# Or deny
tmux send-keys -t "$SESSION:0.0" -l -- "n"
tmux send-keys -t "$SESSION:0.0" Enter

Multi-turn interaction

bash
# Turn 1: send initial message
tmux send-keys -t "$SESSION:0.0" -l -- "Create a TypeScript file that adds two numbers"
tmux send-keys -t "$SESSION:0.0" Enter
bash scripts/wait-for-text.sh -t "$SESSION:0.0" -p "completed\|done" -T 120

# Turn 2: follow-up
tmux send-keys -t "$SESSION:0.0" -l -- "Now add a test for it"
tmux send-keys -t "$SESSION:0.0" Enter
bash scripts/wait-for-text.sh -t "$SESSION:0.0" -p "completed\|done" -T 120

# Verify result
tmux capture-pane -t "$SESSION:0.0" -p -S - | grep -i "pass\|fail"

Cleanup

bash
tmux kill-session -t "$SESSION" 2>/dev/null
rm -rf "$MHOME" "$WORKSPACE"

Part 3: Scenarios

S1: Smoke (headless)

bash
test_smoke() {
  local P=$(mktemp) MHOME=$(mktemp -d)
  echo "Say hello" > "$P"
  MIMOCODE_HOME=$MHOME mimo run --format json --dangerously-skip-permissions \
    < "$P" > /tmp/s1.jsonl 2>&1
  local E=$?
  rm -rf "$MHOME" "$P"
  [ $E -eq 0 ] && grep -q '"type":"text"' /tmp/s1.jsonl && echo "PASS" || echo "FAIL"
}

S2: Tool use (headless)

bash
test_tool_use() {
  local P=$(mktemp) MHOME=$(mktemp -d) WS=$(mktemp -d)
  echo 'Create file test.txt with content "hello"' > "$P"
  MIMOCODE_HOME=$MHOME mimo run --format json --dangerously-skip-permissions --dir "$WS" \
    < "$P" > /tmp/s2.jsonl 2>&1
  local E=$?
  local OK=true
  [ $E -ne 0 ] && OK=false
  ! grep -q '"tool":"write"' /tmp/s2.jsonl && OK=false
  [ ! -f "$WS/test.txt" ] && OK=false
  rm -rf "$MHOME" "$WS" "$P"
  $OK && echo "PASS" || echo "FAIL"
}

S3: TUI interactive flow

bash
test_tui_interactive() {
  local MHOME=$(mktemp -d) WS=$(mktemp -d) SID="mimo-s3-$$"
  local PROMPT_RE='>|Ask|/[a-z]'
  tmux new-session -d -s "$SID" -x 120 -y 30 "MIMOCODE_HOME=$MHOME MIMOCODE_PURE=true mimo $WS; sleep 999"

  # Wait for prompt
  bash scripts/wait-for-text.sh -t "$SID:0.0" -p "$PROMPT_RE" -T 15 || { echo "FAIL: no prompt"; tmux kill-session -t $SID; return 1; }

  # Send task
  tmux send-keys -t "$SID:0.0" -l -- "Create hello.txt with content 'world'"
  tmux send-keys -t "$SID:0.0" Enter

  # Wait for completion (agent shows elapsed time like "· 9.8s")
  bash scripts/wait-for-text.sh -t "$SID:0.0" -p "· [0-9]" -T 120 || { echo "FAIL: no completion"; tmux kill-session -t $SID; return 1; }

  # Verify file
  [ -f "$WS/hello.txt" ] && echo "PASS" || echo "FAIL"
  tmux kill-session -t "$SID" 2>/dev/null
  rm -rf "$MHOME" "$WS"
}

S4: TUI permission handling

bash
test_tui_permission() {
  local MHOME=$(mktemp -d) WS=$(mktemp -d) SID="mimo-s4-$$"
  local PROMPT_RE='>|Ask|/[a-z]'
  tmux new-session -d -s "$SID" -x 120 -y 30 "MIMOCODE_HOME=$MHOME MIMOCODE_PURE=true mimo $WS; sleep 999"

  bash scripts/wait-for-text.sh -t "$SID:0.0" -p "$PROMPT_RE" -T 15

  # Ask for something that needs permission (no --dangerously-skip-permissions in TUI)
  tmux send-keys -t "$SID:0.0" -l -- "Run the command: echo hello"
  tmux send-keys -t "$SID:0.0" Enter

  # Wait for permission prompt
  bash scripts/wait-for-text.sh -t "$SID:0.0" -p "Allow\|approve\|permission\|y/n" -T 30 || { echo "FAIL: no permission prompt"; tmux kill-session -t $SID; return 1; }

  # Approve
  tmux send-keys -t "$SID:0.0" -l -- "y"
  tmux send-keys -t "$SID:0.0" Enter

  # Wait for completion
  bash scripts/wait-for-text.sh -t "$SID:0.0" -p "· [0-9]" -T 60

  tmux capture-pane -t "$SID:0.0" -p | grep -q "hello" && echo "PASS" || echo "FAIL"
  tmux kill-session -t "$SID" 2>/dev/null
  rm -rf "$MHOME" "$WS"
}

S5: TUI keybindings

bash
test_tui_keybindings() {
  local MHOME=$(mktemp -d) WS=$(mktemp -d) SID="mimo-s5-$$"
  local PROMPT_RE='>|Ask|/[a-z]'
  tmux new-session -d -s "$SID" -x 120 -y 30 "MIMOCODE_HOME=$MHOME MIMOCODE_PURE=true mimo $WS; sleep 999"

  bash scripts/wait-for-text.sh -t "$SID:0.0" -p "$PROMPT_RE" -T 15

  # Test Ctrl+C cancels input
  tmux send-keys -t "$SID:0.0" -l -- "some partial input"
  tmux send-keys -t "$SID:0.0" C-c

  # Screen should still show prompt (not exit)
  sleep 1
  tmux capture-pane -t "$SID:0.0" -p | grep -qE "$PROMPT_RE" && echo "PASS: Ctrl+C didn't exit" || echo "FAIL: Ctrl+C exited"

  # Test Escape
  tmux send-keys -t "$SID:0.0" Escape
  sleep 0.5

  tmux kill-session -t "$SID" 2>/dev/null
  rm -rf "$MHOME" "$WS"
}

Batch Runner

bash
run_all() {
  local PASS=0 FAIL=0 RESULTS=()
  for fn in test_smoke test_tool_use test_tui_interactive test_tui_permission test_tui_keybindings; do
    echo "--- $fn ---"
    if $fn 2>/dev/null; then PASS=$((PASS+1)); else FAIL=$((FAIL+1)); RESULTS+=("$fn: FAIL"); fi
  done
  echo "=== $PASS passed, $FAIL failed ==="
  [ ${#RESULTS[@]} -gt 0 ] && printf '  %s\n' "${RESULTS[@]}"
  [ $FAIL -eq 0 ]
}

Quick Reference

TaskCommand
Headless runMIMOCODE_HOME=$(mktemp -d) mimo run --format json --dangerously-skip-permissions "prompt"
TUI launchtmux new-session -d -s test -x 120 -y 30 "MIMOCODE_HOME=$(mktemp -d) mimo $WORKSPACE; sleep 999"
Send texttmux send-keys -t test:0.0 -l -- "text" && tmux send-keys -t test:0.0 Enter
Capture screentmux capture-pane -t test:0.0 -p -S -
Wait for textbash scripts/wait-for-text.sh -t test:0.0 -p "pattern" -T 30
Send Ctrl+Ctmux send-keys -t test:0.0 C-c
Approve permissiontmux send-keys -t test:0.0 -l -- "y" && tmux send-keys -t test:0.0 Enter
Cleanuptmux kill-session -t test && rm -rf $MHOME

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Drive Mimo AI skill do?

Use when developing or testing the MiMoCode repository and you need to programmatically drive another MiMoCode (mimo) process. Supports headless `mimo run` with JSON events and interactive TUI via tmux for behavior, integration, and visual regression testing. Covers an installed `mimo` binary or a dev build launched from source with `bun dev`; do not use it for ordinary MiMoCode task execution.

Why use Drive Mimo on TypingMind?

Because you install it once and use it with any model. Drive Mimo is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Drive Mimo in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/XiaomiMiMo/MiMo-Code/tree/main/.agents/skills/drive-mimo. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Drive Mimo?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Drive Mimo?

As many as you like. As long as a model supports skills, you can use Drive Mimo with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Drive Mimo AI skill free?

Yes. It is published on GitHub by XiaomiMiMo under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇