xiaomimimo/mimo-code

MiMo Code: Where Models and Agents Co-Evolve

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 55 minutes ago
Added to GitGenius on September 1st, 2026
Created on June 10th, 2026
Open Issues & Pull Requests: 983 (+0)
GitHub issues: Enabled
Number of forks: 1,337
Total Stargazers: 12,959 (+0)
Total Subscribers: 73 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 1.9 hours
Mean response time: 2.1 days
90th percentile: 4.3 days
Tracked items: 524

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Almost all tracked open issues have seen activity in the last three months. Only 7% of issues opened in the past year have been closed. Three people close 61% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 710
New in 7 days: 18
Closed in 7 days: 2
Avg open age: 64 days
Stale 30+ days: 628
Stale 90+ days: 0

Recent activity

Opened in 7 days: 16
Closed in 7 days: 2
Comments in 7 days: 8
Events in 7 days: 21

Top labels

  • bug (475)
  • question (112)

Detailed Description

MiMoCode is a terminal-native AI coding assistant that reads and writes code, runs commands, manages Git, and maintains persistent memory across sessions.

The tool addresses the challenge of maintaining project context during extended development work. It solves this by combining an AI agent interface with a persistent memory system that accumulates understanding of your codebase over time. The agent can execute terminal commands, interact with Git repositories, and leverage any mainstream LLM provider API, allowing it to take actions directly within your development environment rather than simply offering suggestions.

Developers should choose this tool if they work primarily in terminal environments and want an AI assistant that understands their specific project deeply across multiple sessions. It suits projects where maintaining continuity of context matters—where the assistant benefits from remembering previous decisions and code patterns. The tool supports flexible LLM provider selection, including Xiaomi's MiMo Platform, OpenAI, xAI/Grok, and custom OpenAI-compatible APIs. Users can migrate existing authentication from Claude Code in a single step. The README notes that MiMoCode works within the broader MiMo ecosystem, which also integrates with other coding tools like Cursor, Cline, and Zed.

The project maintains active development with regular updates addressing platform-specific issues. The maintainers respond to user friction points across different operating systems, including clipboard handling on WSL, rendering compatibility with macOS terminals, SSH performance optimization, and character encoding problems on Windows. The codebase is written in TypeScript and includes a command palette interface for runtime configuration adjustments, suggesting ongoing refinement of the user experience based on practical usage patterns.