XiaomiMiMo/MiMo-CodePublic

MiMo Code: Where Models and Agents Co-Evolve

AI summary: A sophisticated CLI AI coding assistant designed to orchestrate autonomous development and complex workflows.

Stars
13.8K
+6 today
Forks
1.5K
Watchers
73
Open issues
858
Open PRs
333
Contributors
~25
Commits
1.5K
Branches
499

TypeScriptMITCreated Jun 10, 2026Last push 3d agoLatest release v0.1.17+11 stars this week+99 this month

Quick answers

What is MiMo-Code?
A sophisticated CLI AI coding assistant designed to orchestrate autonomous development and complex workflows.
What does MiMo-Code do?
MiMo-Code is a powerful, terminal-based AI coding assistant developed by Xiaomi that deeply integrates into software development workflows. It operates through distinct agent personas—Build, Plan, and Compose—to handle tasks ranging from architectural design to autonomous, parallelized code implementation. The tool features cross-session persistent memory using SQLite, intelligent context reconstruction to manage token limits, and a robust subagent system for executing parallel research. It fundamentally shifts the interaction model from simple chat to structured, spec-driven development orchestrated directly from the command line.
Who is MiMo-Code for?
Software engineers and researchers who want a deeply integrated, autonomous CLI agent for complex, multi-step development tasks. It is designed for those who prefer to remain in the terminal while automating tedious coding workflows. The system excels at orchestrating multiple tools to accomplish intricate development tasks.
How do I get started with MiMo-Code?
npm install -g @xiaomimimo/mimo-code
How popular is MiMo-Code on GitHub?
XiaomiMiMo/MiMo-Code has 13,790 stars and 1,478 forks on GitHub, and gained 11 stars in the last 7 days.
What license does MiMo-Code use?
XiaomiMiMo/MiMo-Code is released under the MIT license.

Star history

since Jul 28, 2026
05K10KJul 2026Sep 2026Oct 2026Nov 2026
13.8K stars as of Nov 18, 2026. Measured daily since Jul 28, 2026; GitHub no longer exposes earlier star timestamps.

Update history

2 recorded
  • Nov 18, 2026New release v0.1.17 (previously v0.1.16).
  • Oct 27, 2026New release v0.1.16 (previously v0.1.15).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 0 commits2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 0 commits2026-02-28: 0 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 0 commits2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 0 commits2026-03-12: 0 commits2026-03-13: 0 commits2026-03-14: 0 commits2026-03-15: 0 commits2026-03-16: 0 commits2026-03-17: 0 commits2026-03-18: 0 commits2026-03-19: 0 commits2026-03-20: 0 commits2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 0 commits2026-03-24: 0 commits2026-03-25: 0 commits2026-03-26: 0 commits2026-03-27: 0 commits2026-03-28: 0 commits2026-03-29: 0 commits2026-03-30: 0 commits2026-03-31: 0 commits2026-04-01: 0 commits2026-04-02: 0 commits2026-04-03: 0 commits2026-04-04: 0 commits2026-04-05: 0 commits2026-04-06: 0 commits2026-04-07: 0 commits2026-04-08: 0 commits2026-04-09: 0 commits2026-04-10: 0 commits2026-04-11: 0 commits2026-04-12: 0 commits2026-04-13: 0 commits2026-04-14: 0 commits2026-04-15: 0 commits2026-04-16: 0 commits2026-04-17: 0 commits2026-04-18: 0 commits2026-04-19: 0 commits2026-04-20: 0 commits2026-04-21: 0 commits2026-04-22: 0 commits2026-04-23: 0 commits2026-04-24: 0 commits2026-04-25: 0 commits2026-04-26: 0 commits2026-04-27: 0 commits2026-04-28: 0 commits2026-04-29: 0 commits2026-04-30: 0 commits2026-05-01: 0 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 0 commits2026-05-05: 0 commits2026-05-06: 0 commits2026-05-07: 0 commits2026-05-08: 0 commits2026-05-09: 0 commits2026-05-10: 0 commits2026-05-11: 0 commits2026-05-12: 0 commits2026-05-13: 0 commits2026-05-14: 0 commits2026-05-15: 0 commits2026-05-16: 0 commits2026-05-17: 0 commits2026-05-18: 0 commits2026-05-19: 0 commits2026-05-20: 0 commits2026-05-21: 0 commits2026-05-22: 0 commits2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 0 commits2026-05-26: 0 commits2026-05-27: 0 commits2026-05-28: 0 commits2026-05-29: 0 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 0 commits2026-06-02: 0 commits2026-06-03: 0 commits2026-06-04: 0 commits2026-06-05: 0 commits2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 0 commits2026-06-09: 0 commits2026-06-10: 0 commits2026-06-11: 6 commits2026-06-12: 0 commits2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 11 commits2026-06-16: 1 commit2026-06-17: 5 commits2026-06-18: 10 commits2026-06-19: 10 commits2026-06-20: 0 commits2026-06-21: 6 commits2026-06-22: 41 commits2026-06-23: 29 commits2026-06-24: 11 commits2026-06-25: 11 commits2026-06-26: 44 commits2026-06-27: 8 commits2026-06-28: 4 commits2026-06-29: 24 commits2026-06-30: 28 commits2026-07-01: 24 commits2026-07-02: 45 commits2026-07-03: 15 commits2026-07-04: 4 commits2026-07-05: 10 commits2026-07-06: 22 commits2026-07-07: 20 commits2026-07-08: 35 commits2026-07-09: 22 commits2026-07-10: 7 commits2026-07-11: 4 commits2026-07-12: 0 commits2026-07-13: 27 commits2026-07-14: 38 commits2026-07-15: 15 commits2026-07-16: 9 commits2026-07-17: 12 commits2026-07-18: 6 commits2026-07-19: 5 commits2026-07-20: 26 commits2026-07-21: 7 commits2026-07-22: 24 commits2026-07-23: 27 commits2026-07-24: 11 commits2026-07-25: 2 commits2026-07-26: 12 commits2026-07-27: 33 commits2026-07-28: 23 commits2026-07-29: 13 commits2026-07-30: 19 commits2026-07-31: 5 commits2026-08-01: 1 commit2026-08-02: 0 commits2026-08-03: 2 commits2026-08-04: 10 commits2026-08-05: 17 commits2026-08-06: 3 commits2026-08-07: 5 commits2026-08-08: 0 commits2026-08-09: 0 commits2026-08-10: 7 commits2026-08-11: 1 commit2026-08-12: 5 commits2026-08-13: 4 commits2026-08-14: 7 commits2026-08-15: 6 commits2026-08-16: 4 commits2026-08-17: 7 commits2026-08-18: 9 commits2026-08-19: 7 commits2026-08-20: 6 commits2026-08-21: 6 commits2026-08-22: 7 commits2026-08-23: 4 commits2026-08-24: 4 commits2026-08-25: 9 commits2026-08-26: 4 commits2026-08-27: 8 commits2026-08-28: 5 commits2026-08-29: 4 commits2026-08-30: 1 commit2026-08-31: 6 commits2026-09-01: 6 commits2026-09-02: 4 commits2026-09-03: 2 commits2026-09-04: 4 commits2026-09-05: 2 commits2026-09-06: 0 commits2026-09-07: 5 commits2026-09-08: 5 commits2026-09-09: 1 commit2026-09-10: 2 commits2026-09-11: 3 commits2026-09-12: 10 commits2026-09-13: 1 commit2026-09-14: 18 commits2026-09-15: 1 commit2026-09-16: 5 commits2026-09-17: 8 commits2026-09-18: 2 commits2026-09-19: 1 commit2026-09-20: 13 commits2026-09-21: 8 commits2026-09-22: 8 commits2026-09-23: 1 commit2026-09-24: 7 commits2026-09-25: 2 commits2026-09-26: 2 commits2026-09-27: 1 commit2026-09-28: 1 commit2026-09-29: 2 commits2026-09-30: 6 commits2026-10-01: 0 commits2026-10-02: 0 commits2026-10-03: 1 commit2026-10-04: 0 commits2026-10-05: 0 commits2026-10-06: 0 commits2026-10-07: 0 commits2026-10-08: 0 commits2026-10-09: 2 commits2026-10-10: 0 commits2026-10-11: 0 commits2026-10-12: 11 commits2026-10-13: 6 commits2026-10-14: 4 commits2026-10-15: 1 commit2026-10-16: 0 commits2026-10-17: 2 commits2026-10-18: 0 commits2026-10-19: 7 commits2026-10-20: 11 commits2026-10-21: 8 commits2026-10-22: 4 commits2026-10-23: 0 commits2026-10-24: 0 commits2026-10-25: 0 commits2026-10-26: 8 commits2026-10-27: 1 commit2026-10-28: 11 commits2026-10-29: 5 commits2026-10-30: 2 commits2026-10-31: 0 commits2026-11-01: 0 commits2026-11-02: 2 commits2026-11-03: 4 commits2026-11-04: 1 commit2026-11-05: 1 commit2026-11-06: 0 commits2026-11-07: 0 commits2026-11-08: 0 commits2026-11-09: 1 commit2026-11-10: 0 commits2026-11-11: 0 commits2026-11-12: 3 commits2026-11-13: 9 commits2026-11-14: 0 commits2026-11-15: 0 commits2026-11-16: 5 commits2026-11-17: 3 commits2026-11-18: 0 commits2026-11-19: 0 commits2026-11-20: 0 commits2026-11-21: 0 commits
1,174 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Widely adopted

    13,790 stars

  • Very active

    1,174 commits in 52 weeks

  • Permissive license

    MIT

  • Continuous integration

    Automated checks passing

  • Repeat trending

    5 trending appearances

What MiMo-Code does

MiMo-Code is a powerful, terminal-based AI coding assistant developed by Xiaomi that deeply integrates into software development workflows. It operates through distinct agent personas—Build, Plan, and Compose—to handle tasks ranging from architectural design to autonomous, parallelized code implementation. The tool features cross-session persistent memory using SQLite, intelligent context reconstruction to manage token limits, and a robust subagent system for executing parallel research. It fundamentally shifts the interaction model from simple chat to structured, spec-driven development orchestrated directly from the command line.

Software engineers and researchers who want a deeply integrated, autonomous CLI agent for complex, multi-step development tasks. It is designed for those who prefer to remain in the terminal while automating tedious coding workflows. The system excels at orchestrating multiple tools to accomplish intricate development tasks.

  • Specialized agent modes: Switch between Build, Plan, and Compose modes for different development phases.
  • Persistent memory: Utilizes an SQLite backend to maintain project context and task history across sessions.
  • Intelligent context management: Automatically checkpoints and reconstructs context when approaching model token limits.
  • Subagent orchestration: Spawns independent subagents to execute parallel tasks like deep research or fact-checking.
  • Deterministic workflows: Execute fixed sequences like TDD loops or adversarial fact verification automatically.

Where teams use it

Spec-driven development

Engineers use Compose mode to orchestrate the entire lifecycle from brainstorming to final implementation.

Large-scale refactoring

Leverage the Build agent to safely modify complex codebases using persistent architectural memory.

Deep multi-source research

Run the deep-research workflow to parallelize intelligence gathering across multiple subagents.

Cost-aware context management

Artificially limit model context windows to control API costs while maintaining session continuity.

Getting started: npm install -g @xiaomimimo/mimo-code

README

main branch

MiMoCode

MiMoCode

MiMo Code: Where Models and Agents Co-Evolve

中文 | English

Website | Blog


MiMoCode is a terminal-native AI coding assistant. It can read and write code, run commands, manage Git, and use a persistent memory system to keep a deep understanding of your project across sessions while continuously improving itself.

MiMoCode supports connecting to any mainstream LLM provider API.

Xiaomi MiMo Desktop

国内版下载 | Global Download

Xiaomi MiMo Desktop English interface: conversation and research report preview

Xiaomi MiMo Desktop is built for real-world work: one conversation can handle office work, design, coding, and multimodal creation, while multiple conversations can divide work and collaborate. The desktop app is powered by MiMo Code as its core engine, bringing its terminal-native intelligence to desktop workflows.

  • Smart orchestration: evaluates task type and cost, then dynamically selects models, frameworks, and tools; complex tasks can run across multiple agents in parallel.
  • Continuous iteration: drag in files in multiple formats, create PPTs, webpages, 3D assets, and apps, preview and operate on results in-session, edit selected regions precisely, and roll back versions.
  • Controlled long-task cost: routes between standard and flagship models, edits only the required regions, and supports up to 99% same-session and 95% cross-session cache hit rates.
  • Browser control: opens webpages, retrieves information, fills forms, and checks key interactions after generating webpages.
  • Computer control (international version only): reads the screen and operates mouse and keyboard across apps; Record & Replay lets you reuse recorded workflows with natural language.

Powered by the new MiMo-V2.6-Pro and MiMo-V2.6-Flash models.


Quick Start

# One-line install (macOS / Linux)
curl -fsSL https://mimo.xiaomi.com/install | bash

# One-line install (Windows PowerShell)
powershell -ep Bypass -c "irm https://mimo.xiaomi.com/install.ps1 | iex"

# Run
mimo

The first launch guides you through configuration automatically. Supported options:

  • Xiaomi MiMo Platform — OAuth login
  • Codex (ChatGPT Pro/Plus) — OpenAI OAuth login
  • Import from Claude Code — migrate existing authentication in one step
  • Provider list — connect catalog providers by API key, or OAuth where supported (e.g. xAI/Grok)
  • Custom Provider — add any OpenAI-compatible API in the TUI
WSL: clipboard issues

If you encounter garbled text when copying on WSL, install xsel:

sudo apt install xsel
macOS: rendering issues in the default terminal

MiMoCode does not support the built-in macOS Terminal (Terminal.app). If the interface is misaligned, flickers, or has other rendering issues, use iTerm2 or the VS Code integrated terminal instead:

brew install --cask iterm2
TUI lag and visual animation issues

If the TUI lags when run directly over SSH, render it locally and run only the MiMoCode server on the remote host. Start the server from the remote project directory:

# Remote host
mimo serve --port 4096

# Local host: create the SSH port forward
ssh -N -L 4096:127.0.0.1:4096 user@remote-host

# Local host: connect from another terminal
mimo attach http://127.0.0.1:4096

If decorative animation is causing the lag, run /vivid, or configure Vivid visuals in the ctrl+p command palette, to switch between Vivid and Minimal visuals as needed.

Windows: garbled CJK (Chinese/Japanese/Korean) output in the shell

On Windows with a non-UTF-8 system locale (e.g. zh-CN, whose active code page is 936/GBK), command output containing CJK characters may appear garbled (mojibake). MiMoCode forces UTF-8 output for spawned PowerShell/cmd subprocesses. If you still encounter garbled output in cases this does not yet cover, enable Windows' system-wide UTF-8 support:

Settings → Time & language → Language & region → Administrative language settings → Change system locale → check "Beta: Use Unicode UTF-8 for worldwide language support" → reboot.

This switches the active code page (ACP) to UTF-8 (65001) for all programs, so subprocesses no longer inherit the legacy code page. Note it is a system-wide Beta toggle and may cause some older non-Unicode programs to display incorrectly, so treat it as a workaround.

How to set up web search

To let the agent search the web, either set MIMOCODE_ENABLE_EXA=1 to enable the built-in websearch and codesearch tools (backed by Exa; for higher rate limits set EXA_API_KEY, created at https://dashboard.exa.ai/api-keys), or add a search MCP server under mcp in your config. Keys can come from environment variables through {env:VAR}:

{
  "mcp": {
    // Exa (key optional: create one at https://dashboard.exa.ai/api-keys and append ?exaApiKey=<key> to the URL)
    "exa": { "type": "remote", "url": "https://mcp.exa.ai/mcp" },
    // Tavily (API key from https://app.tavily.com)
    "tavily": {
      "type": "remote",
      "url": "https://mcp.tavily.com/mcp/",
      "headers": { "Authorization": "Bearer {env:TAVILY_API_KEY}" }
    },
    // Volcengine Doubao Search (needs uv with Python 3.12/3.13;
    // key from https://console.volcengine.com/search-infinity/api-key)
    "doubao-search": {
      "type": "local",
      "command": ["uvx", "--from", "mcp-server-askecho-search-infinity>=0.2.0", "mcp-server-askecho-search-infinity"],
      "environment": { "ASK_ECHO_SEARCH_INFINITY_API_KEY": "{env:ASK_ECHO_SEARCH_INFINITY_API_KEY}" }
    }
  }
}

Run mimo mcp to check that the server connects.


MiMo Ecosystem

Beyond MiMoCode, Xiaomi MiMo models also work in other agents and coding tools like Cursor, Cline, and Zed.

awesome-mimo-agent collects setup guides for using MiMo in those tools — worth a look if you want to try MiMo elsewhere. Contributions welcome: open a PR to add your own setup.


Core Features

Multiple Agents

Agent Description
build Default. Full tool permissions for development
plan Read-only analysis mode for code exploration and solution design

Press Tab to switch between primary agents. Build and Plan can switch at any time; other custom or special modes lock once the first message is sent.

Persistent Memory

Cross-session memory powered by SQLite FTS5 full-text search:

  • Project memory (MEMORY.md) — persistent project knowledge, rules, and architecture decisions
  • Session checkpoint (checkpoint.md) — structured state snapshots maintained automatically by the checkpoint-writer subagent
  • Scratch notes (notes.md) — temporary note area for agents
  • Task progress (tasks/<id>/progress.md) — per-task logs

Memory is injected automatically when a session resumes, so the agent does not need to relearn project context.

Intelligent Context Management

  • Automatic checkpoints — decides when to save session state based on the model context window
  • Context reconstruction — when context approaches the limit, rebuilds it from the latest checkpoint, project memory, task progress, and retained recent messages so the agent can continue the current task
  • Budgeted injection — uses a token budget to control how much checkpoint, memory, and notes content enters context, with importance ranking
  • Adjustable compaction point — /context-limit (or compaction.max_context) makes a model compact earlier than its own window, per model
Compacting earlier than the model window (/context-limit)

Compaction normally fires just below the model's context window. Run /context-limit to pick a smaller working budget for the current model — 200K / 300K / 500K / 1M or a custom value — stored per model as compaction.max_context:

{
  "compaction": {
    "max_context": {
      "openai/gpt-5.6": "272K", // token count, "300K", "1M", or "50%" of the window
      "anthropic/*": "300K" // wildcards allowed, longest pattern wins
    }
  }
}

The value is always clamped to what the provider actually accepts, so it can only lower the compaction point, never raise it. 0 restores the model's own window.

Why you might want it:

  • Cost tiers. OpenAI prices GPT-5.6 prompts above 272K input at 2x input and 1.5x output for the whole request.
  • The advertised window is not always what you get. The same model can have a different usable window depending on how you reach it — a ChatGPT/Codex subscription, a direct API key, or a reseller such as OpenRouter — so a catalog figure of 1M does not mean your route serves 1M.
  • Quality and latency. Very long contexts are slower and, past a point, not better.

mimo models <provider> prints, per model, the window MiMoCode resolved and the token count where it will compact. The prompt footer uses that same number as its denominator (33.0K/260K↓ (13%) — the ↓ means a budget is in force), and /status breaks it down.

Task Tracking

A tree-shaped task system (T1, T1.1, T1.2, …) that integrates automatically with the checkpoint system, so task progress is preserved when sessions resume.

Subagent System

The primary agent can create subagents on demand. Subagents share the current session context and can work in parallel, with lifecycle tracking, cancellation, and background execution.

Goal / Stop Condition

The /goal command sets a stopping condition for a session. When the agent tries to stop, an independent judge model evaluates the conversation to decide whether the condition is truly satisfied — preventing premature "optimistic stops" during autonomous work.

Compose Mode

Use the /compose-next skill to run an end-to-end feature delivery loop: a single self-contained contract covering grill → workspace → spec → implement → verify → review → finalize → finish, with feature documents at docs/compose/spec/<feature>.md under the workspace root. Do not combine it with plan mode.

Workflows

Workflows are deterministic JavaScript scripts that orchestrate multiple agents in a sandboxed runtime. Unlike agent conversations, workflows encode fixed phase sequences with bounded retries and automatic parallelization — fire-and-forget execution with no user interaction required.

MiMoCode ships with three built-in workflows:

Workflow Phases Description
deep-research Brief → Plan → Research → Reflect → Write → Review Multi-source deep research report generator. Plans independent research angles, runs parallel sub-agents to collect cited findings, reflects on gaps, writes a single coherent Markdown report, then cold-reviews citations. Convergent: resumable via file checkpoints.
fact-check Plan → Search → Extract → Group → Crosscheck → Report Adversarial fact verification. Runs parallel web searches, extracts checkable facts, groups duplicates, then cross-checks each with a 3-juror adversarial vote. Best for precise claims ("Is X true?").
research-experiment Baseline → Loop → Audit → Report Autonomous optimization loop for a mechanically verifiable metric. Establishes a baseline, iterates through hypothesize → implement → evaluate → keep/revert, audits for metric gaming, and produces a reproducible result log. Requires a fixed-budget evaluation command and an explicit editable-file scope.

Custom workflows: Place a .js file in .mimocode/workflows/ or .claude/workflows/ to define your own, or override a built-in by using the same name.

Builtin Skills

Skills are reusable instruction sets that teach agents how to handle specific tasks (e.g. generating PDFs, writing academic papers, searching arXiv). For a new task, MiMoCode searches available skills by exact name, localized alias, and BM25 relevance. High-confidence matches are loaded automatically; uncertain matches are ranked for the agent to assess. In the TUI, type / to browse the autocomplete list or invoke a skill directly with /<skill-name> — mentioning two or more skills in a single message auto-loads them and injects a multi-skill orchestration plan.

MiMoCode bundles the following builtin skills, enabled by default (set MIMOCODE_DISABLE_BUILTIN_SKILLS=true to turn them all off):

Development & delivery

Skill Description
compose-next Spec→ship feature delivery orchestration — clarify, spec, implement, verify, review, finish
modern-python-toolchain Set up modern Python projects with uv, Ruff, and Pyright
playwright Automate a real browser from the terminal — navigation, form filling, snapshots, screenshots, data extraction, and UI-flow debugging

Research & learning

Skill Description
deep-research Produce cited, multi-source research reports with parallel subagents and built-in web tools
super-research Run long-horizon, auditable research, experiments, benchmarks, diagnostics, reproductions, and citation checks
arxiv Search, read, cite, and analyze arXiv papers
research-paper-writing Write and polish academic papers (ML/CV/NLP style)
learn-everything Turn documents, URLs, or topics into adaptive courses with exercises, feedback, and progress tracking

Documents & media (can be turned off together with MIMOCODE_DISABLE_OFFICIAL_SKILLS)

Skill Description
docx-official Produce, read, and transform Word (.docx) files
pdf-official Produce, read, fill, and transform PDF files
pptx-official Author and manipulate PowerPoint (.pptx) decks
xlsx-official Build, clean, and transform spreadsheets (.xlsx/.csv)
html-to-video-pipeline HTML-to-MP4 rendering via headless browser + ffmpeg

Business & design

Skill Description
data-analytics Analyze product and business data through reusable workflows for data quality, KPIs, dashboards, reports, notebooks, and market sizing
product-design Explore, audit, implement, and QA product and UX designs through focused workflows
sales Support sales research, meeting preparation, account prioritization, deal strategy, forecasting, and CRM workflows

MiMoCode itself

Skill Description
mimocode-docs Self-documenting reference for MiMoCode features, commands, providers, and configuration
skill-creator Interactive guide for creating and improving agent skills
loop Schedule recurring prompts on a fixed cadence
memory-search Query the session trajectory database with SQL when the built-in memory and history tools are not enough

Some skills require task-specific tools described in their instructions.

Agent-CLI skills (off by default): claude-code, codex, and grok-build drive the Claude Code, Codex, and Grok Build CLIs from the terminal. They are bundled but not loaded unless you set MIMOCODE_ENABLE_AGENT_CLI_SKILLS=true.

Overriding a builtin skill: Create a skill with the same name under the project (.mimocode/skills/<name>/SKILL.md) or personal (for example ~/.config/mimocode/skills/<name>/SKILL.md) MiMoCode skills directory. Open-standard .agents/skills/ in the project and ~/.agents/skills/ are compatible discovery roots. User skills discovered later in the scan order override builtins with the same name.

Configuring skills via environment variables
Variable Effect
MIMOCODE_DISABLE_BUILTIN_SKILLS=true Disable all builtin skills
MIMOCODE_DISABLE_OFFICIAL_SKILLS=true Disable only the office/media skills: docx-official, pdf-official, pptx-official, xlsx-official, html-to-video-pipeline
MIMOCODE_ENABLE_AGENT_CLI_SKILLS=true Opt in the agent-CLI skills claude-code, codex, and grok-build (default: off)
MIMOCODE_DISABLE_SLASH_SKILLS=true Hide skills from TUI / autocomplete without disabling them

External skill roots (default surface is .mimocode + open-standard .agents):

Env Default Effect
MIMOCODE_DISABLE_AGENTS_SKILLS=true unset = on Turn off ~/.agents/skills and project .agents/skills
MIMOCODE_ENABLE_CLAUDE_CODE_SKILLS=true unset = off Opt in .claude/skills
MIMOCODE_ENABLE_CODEX_SKILLS=true unset = off Opt in .codex/skills (user skills only; Codex skills/.system is never loaded)
MIMOCODE_ENABLE_OPENCODE_SKILLS=true unset = off Opt in .opencode/skills

External scans never match dotted path segments under skills/.

MIMOCODE_DISABLE_BUILTIN_SKILLS and MIMOCODE_DISABLE_OFFICIAL_SKILLS remove the corresponding skills from the agent's available skill list entirely — they will not appear in context and cannot be invoked. MIMOCODE_DISABLE_SLASH_SKILLS affects only TUI autocomplete; the skills remain available to agents.

Voice Input

Real-time streaming voice input powered by TenVAD and MiMo ASR. Activate with /voice, then speak — audio is segmented by pauses and transcribed incrementally into the input. Available for MiMo logged-in users. Requires sox (brew install sox on macOS, other platforms similar).

WSLg audio setup
sudo apt install -y sox pulseaudio libasound2-plugins
export PULSE_SERVER=unix:/mnt/wslg/PulseServer
SSH remote audio (Mac → remote host)
# Mac (local)
brew install pulseaudio
pulseaudio --load="module-native-protocol-tcp auth-ip-acl=127.0.0.1" --exit-idle-time=-1 --daemonize
# Add to ~/.ssh/config: RemoteForward 4713 127.0.0.1:4713

# Remote host
apt install -y pulseaudio pulseaudio-utils sox
export PULSE_SERVER=tcp:127.0.0.1:4713
# Verify: pactl info
Non-MiMo voice providers (OpenRouter, internal API, etc.)

Voice input can route through other OpenAI-compatible providers via the voice config field. The ASR model (mimo-v2.5-asr) is only available on MiMo's platform; voice control mode (mimo-v2.6-flash) is available on OpenRouter and compatible relay platforms.

OpenRouter (voice control only):

Use /connect to sign in to OpenRouter, then add to your config:

{
  "voice": {
    "control_model": "openrouter/xiaomi/mimo-v2.6-flash"
  }
}

Internal / self-hosted relay (both ASR and voice control):

{
  "provider": {
    "internal": {
      "options": {
        "baseURL": "https://your-api-gateway.example.com/v1",
        "apiKey": "sk-..."
      },
      "models": {
        "xiaomi/mimo-v2.5-asr": { "name": "MiMo-V2.5-ASR" },
        "xiaomi/mimo-v2.6-flash": { "name": "MiMo-V2.6-Flash" }
      }
    }
  },
  "voice": {
    "asr_model": "internal/xiaomi/mimo-v2.5-asr",
    "control_model": "internal/xiaomi/mimo-v2.6-flash"
  }
}

Custom providers must register at least one model in their models field to be recognized. The model names in voice.*_model are sent directly to the API — they don't need to match the registered model keys exactly.

Note: Models registered under a custom provider will appear in the model selection list. Don't use ASR-only models (e.g. mimo-v2.5-asr) as your primary coding model.

Dream & Distill

  • /dream — scans recent session traces, extracts persistent knowledge into project memory, and removes outdated entries
  • /distill — discovers repeated manual workflows in recent work and packages high-confidence candidates into reusable skills, subagents, or commands

Configuration

MiMoCode uses JSON/JSONC config files with published JSON Schemas for autocompletion and validation.

File Locations

File Project-level Global
Main config .mimocode/mimocode.jsonc (also .json) ~/.config/mimocode/mimocode.jsonc (also .json)
TUI config .mimocode/tui.json ~/.config/mimocode/tui.json
Auth credentials — ~/.local/share/mimocode/auth.json

On Windows, XDG paths fall under %LOCALAPPDATA%\mimocode\. You can override all paths with MIMOCODE_HOME.

JSON Schemas

MiMoCode auto-injects a $schema field when it first loads your config, so your editor gets completions and validation out of the box:

Config Schema URL
mimocode.jsonc / mimocode.json https://mimo.xiaomi.com/mimocode/config.json
tui.json https://mimo.xiaomi.com/mimocode/tui.json
VS Code / Cursor: trust the schema domain

Add to your settings.json so the editor can download schemas for autocompletion:

{
  "json.schemaDownload.trustedDomains": {
    "https://mimo.xiaomi.com/": true
  }
}
Data directories

Beyond config files, MiMoCode stores runtime data under XDG paths (or $MIMOCODE_HOME):

Directory Default (Linux) Contents
data ~/.local/share/mimocode/ SQLite database, auth credentials (auth.json), memory, logs
state ~/.local/state/mimocode/ TUI preferences (kv.json), recent models (model.json)
cache ~/.cache/mimocode/ Language servers, cached model catalog, skills

To remove stored credentials, delete auth.json from the data directory. On macOS, XDG data defaults to ~/Library/Application Support/mimocode/.

Custom OpenAI-Compatible Endpoints

If your provider is not in the built-in model catalog, configure it directly with its base URL, API key, and model ID:

{
  "$schema": "https://mimo.xiaomi.com/mimocode/config.json",
  "model": "custom/MODEL_NAME",
  "provider": {
    "custom": {
      "name": "Custom",
      "npm": "@ai-sdk/openai-compatible",
      "only_configured_models": true,
      "models": {
        "MODEL_NAME": {
          "name": "MODEL_NAME"
        }
      },
      "options": {
        "baseURL": "BASE_URL",
        "apiKey": "API_KEY"
      }
    }
  }
}
  • Use the exact keys baseURL and apiKey.
  • Preserve the base URL and model ID exactly as supplied. MiMoCode does not require a known provider and you should not add or remove /v1 unless the endpoint requires it.
  • The key under models is the upstream model ID. Model IDs containing / are supported because only the first / in model separates the provider ID from the model ID.
  • Replace custom with another unused lowercase provider ID if needed, and use the same ID in the top-level model value.
  • @ai-sdk/openai-compatible is for OpenAI-compatible APIs. Services using a different wire protocol require their provider-specific adapter.

Put user-wide settings in ~/.config/mimocode/mimocode.jsonc (or mimocode.json in the same directory), or project-only settings in .mimocode/mimocode.jsonc (or .json), and merge them with any existing configuration. Because apiKey is stored as plaintext, keep the file readable only by your user and never commit it. Run mimo models or use the TUI model picker to verify the configured model.

To declare which input modalities a custom model supports (image, audio, video, PDF), run /modalities in the TUI — a multi-select dialog that persists the setting to config without hand-editing.

Key Options

  • Provider and model selection
  • Agent permissions and custom agents
  • Checkpoint and memory behavior
  • MCP server connections
  • Keybindings and theme

Max Mode (parallel best-of-N reasoning with judge selection) can be enabled via experimental.maxMode in the config.

Allowing the system temp directory (/tmp)

By default, reading or writing files outside the project working directory triggers an external_directory permission prompt — including the system temp directory. This is intentional: MiMoCode does not silently widen permissions, so you stay in control of what the model can touch outside your project.

The temp directory comes up often because most models reach for it as scratch space (e.g. a quick script, a throwaway data file). If you trust your environment and would rather not be prompted each time, you can opt in by allowing it in your config:

{
  "$schema": "https://mimo.xiaomi.com/mimocode/config.json",
  "permission": {
    "external_directory": {
      "/tmp/**": "allow"
    }
  }
}

This setting has known risks — use it at your own risk. The temp directory is world-writable and shared with every other process and user on the machine. Auto-allowing it means the model can read and write there without confirmation, which widens your exposure to predictable temp-path / symlink tricks (e.g. another process pre-creating /tmp/foo as a symlink to a sensitive file). For that reason it is only recommended for single-user, controlled environments or inside a container. Keep the allowlist as narrow as possible.

Skipping permission prompts (--dangerously-skip-permissions)

For trusted, disposable environments (containers, sandboxes, CI) you can auto-approve everything the agent does instead of confirming each action:

# TUI — prompts once for an explicit confirmation on startup
mimo --dangerously-skip-permissions

# Headless
mimo run --dangerously-skip-permissions "your prompt"

# Or via environment variable (any surface)
MIMOCODE_DANGEROUSLY_SKIP_PERMISSIONS=1 mimo

This injects an allow-all base underneath your config, so a tool with no rule auto-approves — but any explicit rule you wrote still wins (the last matching rule wins, and your rules sit after the injected *). A deny still blocks; note that a leftover ask rule also still prompts, and a top-level "*": "ask" makes the flag a no-op. In the TUI it shows a red warning and requires you to accept the risk before it takes effect (the prompt is skipped when there is no TTY, so in CI it activates with no confirmation).

This is dangerous. With permissions bypassed, a malicious prompt, file, or plugin can run arbitrary shell commands and read, modify, or exfiltrate your data without any confirmation. Only use it where you fully trust the workspace.

For a lighter-weight option, the /skip-permissions command toggles auto-allow at runtime inside the TUI: deny rules still block, and forced-ask operations (e.g. destructive bash) auto-reject after 60 seconds with feedback the model can act on instead of hanging.


Development

bun ci                   # Install dependencies (= bun install --frozen-lockfile)
bun run dev              # Run in development mode
bun run typecheck          # Type check

Relationship to OpenCode

MiMoCode is built as a fork of OpenCode. It keeps all core OpenCode capabilities (multiple providers, TUI, LSP, MCP, plugins) and adds persistent memory, intelligent context management, subagent orchestration, goal-driven autonomous loops, compose-next end-to-end delivery, Dynamic Workflows, and self-improvement via dream/distill.


Community

Scan the QR code to join the community group chat:

Community group chat QR code 1    Community group chat QR code 2


License

Source code is licensed under the MIT License.

Use of MiMoCode is also subject to the Use Restrictions. Use of Xiaomi MiMo-hosted services is subject to the MiMo Terms of Service. Use of the MiMo name, logo, and trademarks is subject to the MiMo Trademark Policy.

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

4 total
  1. v0.1.17v0.1.17Nov 13, 20261.3K downloads

    ## 简介 本版本移除了一些过时的策略,减少针对特定模型的行为改变:上下文与输出上限、推理档位改从 models.dev 和用户配置读取,不再按模型名推断,也不再默认发送 temperature / top_p;`/variants` 可在配置中直接按档位名启用,子 agent 继承父会话的档位;GPT 模型也不再自动开启 Codex 风格的提示词和工具集,所有模型默认使用同一套(需要时可设置 `MIMOCODE_CODEX_MODE=true`)。 此外,内置联网搜索改为通过 `MIMOCODE_ENABLE_EXA=1` 启用(也可接入搜索 MCP);小米 API key 与 Token Plan key 可同时登录;记忆搜索支持中文子串召回;并修复了额度耗尽仍重试、压缩失败残留等稳定性问题。 ## Highlights This release removes some outdated policies and reduces model-specific behavior changes: context/output limits and reasoning levels now come from models.dev and your config rather than model-name heuristics, and temperature/top_p are no longer sent by default; reasoning levels for `/variants` can be enabled by name in config, and subagents inherit the parent session's level; GPT models also no longer switch to a Codex-like prompt and toolset automatically — every model uses the same defaults (set `MIMOCODE_CODEX_MODE=true` to opt in). Also: built-in web search is now opt-in via `MIMOCODE_ENABLE_EXA=1` (or add a search MCP server), Xiaomi API and Token Plan keys can be signed in together, memory search recalls Chinese substrings, and reliability fixes cover retries on exhausted quota and leftovers from failed compact

  2. v0.1.16v0.1.16Oct 26, 20263.6K downloads

    ## Upgrade notes **中文** 本版本移除 legacy Compose:`compose` 主智能体、内置 workflow 及全部 `compose:*` 技能不再提供,复杂任务请改用 build 模式下的 `/compose-next`(clarify → spec → implement → verify → review → finish)。MCP 工具默认懒加载,按需发现并在就绪后调用。`npm i @mimo-ai/cli` 目前仅包含启动器,完整体验建议使用原生安装脚本。实验性 Orchestrator 模式已移除;Claude 会话导入与 agent-CLI 技能(claude-code / codex / grok-build)需通过环境变量显式启用。 **English** Legacy Compose is retired in this release. The old `compose` agent, its built-in workflow, and the whole `compose:*` skill set are gone — for non-trivial work, switch to `/compose-next` on the build agent (clarify → spec → implement → verify → review → finish). On the MCP side, tools now load lazily instead of dumping the full catalog up front; they are discovered on demand and become callable once ready. Install-wise, `npm i @mimo-ai/cli` is only a thin launcher now, so the native installer remains the recommended path. Also worth knowing: the experimental Orchestrator mode is gone, and both Claude Code session import and the agent-CLI skills (claude-code / codex / grok-build) are opt-in via env flags. --- ## What's Changed * fix(mcp): support explicit user confirmation for recording by @wqymi in https://github.com/Xiaom

  3. v0.1.15v0.1.15Sep 22, 20269.6K downloads

    Today Xiaomi released and open-sourced MiMo-V2.6 — the flagship multimodal model Pro, the efficient reasoning model Flash, and the ultra-fast model Pro-UltraSpeed. MiMoCode 0.1.15 follows with a number of improvements to everyday agent runs. Within a single agent step, model-emitted tool calls now go through a sequencing gate: only pure read/search tools overlap, everything else runs one after another; if a side-effecting call fails, later calls that could be affected are safely skipped. There is also a flood guard on tool calls — when a single response emits too many calls, the excess are held back instead of being executed, as a safeguard against over-aggressive batching. Session resume is also more dependable — recoverable provider errors back off and retry, and an interrupted session can pick up from the right recovery target, with idle subagents resumed alongside the main turn. On the input side, the Read tool can read images, audio, and video files, so multimodal agents can work with a wider range of material. --- 小米今日正式发布并开源 MiMo-V2.6 系列,包含全模态旗舰模型 Pro、高效推理模型 Flash 与超高速模型 Pro-UltraSpeed。MiMoCode 0.1.15 同步带来多项改进,覆盖智能体的日常运行。在同一次执行中,模型发出的多个工具调用会进入串行门禁:只读、检索类的工具仍可并行,其余调用依次执行;若带

  4. v0.1.14v0.1.14Sep 23, 20261.4K downloads

    ## What's Changed * fix(skill): replace broken skill-tools filtering with glob prefix matching by @MiMoHardFather in https://github.com/XiaomiMiMo/MiMo-Code/pull/2166 * fix: remove skill search reminders and related infrastructure by @MiMoHardFather in https://github.com/XiaomiMiMo/MiMo-Code/pull/2168 * fix(gpt): align Codex prompt and shell tool exposure by @MiMoHardFather in https://github.com/XiaomiMiMo/MiMo-Code/pull/2176 * fix(gpt): correct Tengu AgentToolHook wrapper script alias by @MiMoHardFather in https://github.com/XiaomiMiMo/MiMo-Code/pull/2177 * feat: compact GPT tool surface with hidden tool registration by @MiMoHardFather in https://github.com/XiaomiMiMo/MiMo-Code/pull/2179 * fix(gpt): update reasoning format instruction to accept both We need and Need by @MiMoHardFather in https://github.com/XiaomiMiMo/MiMo-Code/pull/2178 * feat(tool-script): add exec_command parameter schema with yield_time_ms and workdir by @MiMoHardFather in https://github.com/XiaomiMiMo/MiMo-Code/pull/2180 * fix(provider): use 128K output defaults for large models by @MiMoHardFather in https://github.com/XiaomiMiMo/MiMo-Code/pull/2181 * fix(provider): align large-model output and compaction rese

Code frequency

additions and deletions
+1M-1MWeek of 2026-06-07: +639,518 linesWeek of 2026-06-07: -6 linesWeek of 2026-06-14: +227,389 linesWeek of 2026-06-14: -3,335 linesWeek of 2026-06-21: +15,097 linesWeek of 2026-06-21: -8,531 linesWeek of 2026-06-28: +27,579 linesWeek of 2026-06-28: -1,421 linesWeek of 2026-07-05: +38,261 linesWeek of 2026-07-05: -16,521 linesWeek of 2026-07-12: +32,616 linesWeek of 2026-07-12: -3,527 linesWeek of 2026-07-19: +11,653 linesWeek of 2026-07-19: -4,330 linesWeek of 2026-07-26: +23,791 linesWeek of 2026-07-26: -4,269 linesWeek of 2026-08-02: +5,782 linesWeek of 2026-08-02: -1,073 linesWeek of 2026-08-09: +2,795 linesWeek of 2026-08-09: -1,555 linesWeek of 2026-08-16: +15,381 linesWeek of 2026-08-16: -4,249 linesWeek of 2026-08-23: +13,582 linesWeek of 2026-08-23: -2,592 linesWeek of 2026-08-30: +3,952 linesWeek of 2026-08-30: -1,334 linesWeek of 2026-09-06: +10,898 linesWeek of 2026-09-06: -5,108 linesWeek of 2026-09-13: +13,536 linesWeek of 2026-09-13: -5,983 linesWeek of 2026-09-20: +22,653 linesWeek of 2026-09-20: -21,561 linesWeek of 2026-09-27: +463,779 linesWeek of 2026-09-27: -1,005,358 linesWeek of 2026-10-04: +13 linesWeek of 2026-10-04: -9 linesWeek of 2026-10-11: +9,665 linesWeek of 2026-10-11: -10,733 linesWeek of 2026-10-18: +24,850 linesWeek of 2026-10-18: -8,718 linesWeek of 2026-10-25: +3,513 linesWeek of 2026-10-25: -823 linesWeek of 2026-11-01: +2,807 linesWeek of 2026-11-01: -2,677 linesWeek of 2026-11-08: +2,299 linesWeek of 2026-11-08: -4,110 linesWeek of 2026-11-15: +1,997 linesWeek of 2026-11-15: -145 linesJun 7, 2026Nov 15, 2026
+1.6M lines added, -1.1M removed over the last year.

Commits per week

last 52 weeks
1500Week of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 0 commitsWeek of 2026-02-22: 0 commitsWeek of 2026-03-01: 0 commitsWeek of 2026-03-08: 0 commitsWeek of 2026-03-15: 0 commitsWeek of 2026-03-22: 0 commitsWeek of 2026-03-29: 0 commitsWeek of 2026-04-05: 0 commitsWeek of 2026-04-12: 0 commitsWeek of 2026-04-19: 0 commitsWeek of 2026-04-26: 0 commitsWeek of 2026-05-03: 0 commitsWeek of 2026-05-10: 0 commitsWeek of 2026-05-17: 0 commitsWeek of 2026-05-24: 0 commitsWeek of 2026-05-31: 0 commitsWeek of 2026-06-07: 6 commitsWeek of 2026-06-14: 37 commitsWeek of 2026-06-21: 150 commitsWeek of 2026-06-28: 144 commitsWeek of 2026-07-05: 120 commitsWeek of 2026-07-12: 107 commitsWeek of 2026-07-19: 102 commitsWeek of 2026-07-26: 106 commitsWeek of 2026-08-02: 37 commitsWeek of 2026-08-09: 30 commitsWeek of 2026-08-16: 46 commitsWeek of 2026-08-23: 38 commitsWeek of 2026-08-30: 25 commitsWeek of 2026-09-06: 26 commitsWeek of 2026-09-13: 36 commitsWeek of 2026-09-20: 41 commitsWeek of 2026-09-27: 11 commitsWeek of 2026-10-04: 2 commitsWeek of 2026-10-11: 24 commitsWeek of 2026-10-18: 30 commitsWeek of 2026-10-25: 27 commitsWeek of 2026-11-01: 8 commitsWeek of 2026-11-08: 13 commitsWeek of 2026-11-15: 8 commitsNov 23, 2025Nov 15, 2026
1.2K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 3 commitsSun 1:00 — 5 commitsSun 2:00 — 3 commitsSun 3:00 — 0 commitsSun 4:00 — 0 commitsSun 5:00 — 1 commitsSun 6:00 — 0 commitsSun 7:00 — 1 commitsSun 8:00 — 0 commitsSun 9:00 — 0 commitsSun 10:00 — 6 commitsSun 11:00 — 3 commitsSun 12:00 — 4 commitsSun 13:00 — 3 commitsSun 14:00 — 3 commitsSun 15:00 — 8 commitsSun 16:00 — 3 commitsSun 17:00 — 1 commitsSun 18:00 — 1 commitsSun 19:00 — 1 commitsSun 20:00 — 2 commitsSun 21:00 — 6 commitsSun 22:00 — 3 commitsSun 23:00 — 4 commitsMon 0:00 — 0 commitsMon 1:00 — 1 commitsMon 2:00 — 0 commitsMon 3:00 — 0 commitsMon 4:00 — 0 commitsMon 5:00 — 0 commitsMon 6:00 — 0 commitsMon 7:00 — 0 commitsMon 8:00 — 1 commitsMon 9:00 — 1 commitsMon 10:00 — 0 commitsMon 11:00 — 2 commitsMon 12:00 — 10 commitsMon 13:00 — 11 commitsMon 14:00 — 11 commitsMon 15:00 — 28 commitsMon 16:00 — 25 commitsMon 17:00 — 40 commitsMon 18:00 — 29 commitsMon 19:00 — 16 commitsMon 20:00 — 13 commitsMon 21:00 — 26 commitsMon 22:00 — 32 commitsMon 23:00 — 30 commitsTue 0:00 — 12 commitsTue 1:00 — 9 commitsTue 2:00 — 1 commitsTue 3:00 — 2 commitsTue 4:00 — 1 commitsTue 5:00 — 0 commitsTue 6:00 — 0 commitsTue 7:00 — 1 commitsTue 8:00 — 0 commitsTue 9:00 — 0 commitsTue 10:00 — 1 commitsTue 11:00 — 8 commitsTue 12:00 — 7 commitsTue 13:00 — 8 commitsTue 14:00 — 21 commitsTue 15:00 — 17 commitsTue 16:00 — 19 commitsTue 17:00 — 7 commitsTue 18:00 — 14 commitsTue 19:00 — 13 commitsTue 20:00 — 19 commitsTue 21:00 — 26 commitsTue 22:00 — 25 commitsTue 23:00 — 11 commitsWed 0:00 — 3 commitsWed 1:00 — 0 commitsWed 2:00 — 1 commitsWed 3:00 — 0 commitsWed 4:00 — 1 commitsWed 5:00 — 0 commitsWed 6:00 — 0 commitsWed 7:00 — 0 commitsWed 8:00 — 0 commitsWed 9:00 — 1 commitsWed 10:00 — 0 commitsWed 11:00 — 1 commitsWed 12:00 — 10 commitsWed 13:00 — 8 commitsWed 14:00 — 17 commitsWed 15:00 — 18 commitsWed 16:00 — 20 commitsWed 17:00 — 28 commitsWed 18:00 — 10 commitsWed 19:00 — 13 commitsWed 20:00 — 23 commitsWed 21:00 — 12 commitsWed 22:00 — 20 commitsWed 23:00 — 15 commitsThu 0:00 — 9 commitsThu 1:00 — 12 commitsThu 2:00 — 4 commitsThu 3:00 — 1 commitsThu 4:00 — 1 commitsThu 5:00 — 1 commitsThu 6:00 — 1 commitsThu 7:00 — 2 commitsThu 8:00 — 2 commitsThu 9:00 — 4 commitsThu 10:00 — 3 commitsThu 11:00 — 3 commitsThu 12:00 — 6 commitsThu 13:00 — 8 commitsThu 14:00 — 15 commitsThu 15:00 — 7 commitsThu 16:00 — 13 commitsThu 17:00 — 8 commitsThu 18:00 — 12 commitsThu 19:00 — 9 commitsThu 20:00 — 26 commitsThu 21:00 — 26 commitsThu 22:00 — 17 commitsThu 23:00 — 13 commitsFri 0:00 — 19 commitsFri 1:00 — 11 commitsFri 2:00 — 6 commitsFri 3:00 — 3 commitsFri 4:00 — 1 commitsFri 5:00 — 1 commitsFri 6:00 — 0 commitsFri 7:00 — 0 commitsFri 8:00 — 0 commitsFri 9:00 — 1 commitsFri 10:00 — 1 commitsFri 11:00 — 2 commitsFri 12:00 — 6 commitsFri 13:00 — 5 commitsFri 14:00 — 12 commitsFri 15:00 — 8 commitsFri 16:00 — 11 commitsFri 17:00 — 14 commitsFri 18:00 — 9 commitsFri 19:00 — 7 commitsFri 20:00 — 6 commitsFri 21:00 — 12 commitsFri 22:00 — 10 commitsFri 23:00 — 6 commitsSat 0:00 — 7 commitsSat 1:00 — 3 commitsSat 2:00 — 1 commitsSat 3:00 — 1 commitsSat 4:00 — 2 commitsSat 5:00 — 0 commitsSat 6:00 — 0 commitsSat 7:00 — 0 commitsSat 8:00 — 3 commitsSat 9:00 — 1 commitsSat 10:00 — 1 commitsSat 11:00 — 4 commitsSat 12:00 — 2 commitsSat 13:00 — 6 commitsSat 14:00 — 4 commitsSat 15:00 — 6 commitsSat 16:00 — 3 commitsSat 17:00 — 2 commitsSat 18:00 — 0 commitsSat 19:00 — 3 commitsSat 20:00 — 3 commitsSat 21:00 — 6 commitsSat 22:00 — 0 commitsSat 23:00 — 2 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Jun 15, 2026daily#21+19
Jun 14, 2026daily#22+33
Jun 13, 2026daily#4+72
Jun 12, 2026daily#2+76
Jun 11, 2026daily#1+113
  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • freeCodeCamp/freeCodeCamp

    freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

    459.4K stars · TypeScript

  • openclaw/openclaw

    The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

    394.9K stars · TypeScript

  • obra/superpowers

    An agentic skills framework & software development methodology that works.

    322.9K stars · Shell

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    307.9K stars · JavaScript

  • NousResearch/hermes-agent

    The agent that grows with you

    265K stars · Python