# xiaomimimo/mimo-code

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/xiaomimimo-mimo-code).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

13,767 stars · 1,473 forks · TypeScript · MIT

## Links

- GitHub: https://github.com/XiaomiMiMo/MiMo-Code
- Homepage: https://mimo.xiaomi.com/mimocode
- awesome-repositories: https://awesome-repositories.com/repository/xiaomimimo-mimo-code.md

## Topics

`ai` `ai-agents` `cli` `mimo` `mimo-code`

## Description

MiMo-Code is a terminal-based AI coding assistant that reads and edits project files, runs shell commands, manages version control, and delegates work to LLM-powered agents from a single interactive interface. It connects to major model providers through API keys, browser sign-in, or imported credentials, and accepts any OpenAI-compatible custom endpoint defined by a base URL and model ID.

Much of what sets it apart is how it handles long-running work. Project knowledge, session checkpoints, notes, and task logs are kept in a searchable database and injected back into context when a session resumes. When a model's window nears its limit, the context is rebuilt from memory plus recent messages using per-model thresholds. Work is tracked as a numbered task tree, so an interrupted session resumes at the exact node it left. The assistant can also review past sessions to extract lasting knowledge and package repeated workflows into reusable skills, helper agents, or commands.

For larger jobs, it can launch subagents that share the parent's context and run in parallel or in the background, tracked in a registry that supports cancellation. Scripted multi-agent workflows run in a sandbox with fixed phases and bounded retries, and a separate judge model can confirm that a stated goal is met before the agent is allowed to stop. A contract-driven loop takes a feature from clarification through specification, implementation, verification, and review, leaving documents in the workspace. Users can switch between a full-permission build agent and a read-only plan agent.

Other capabilities include permission rules with prompts for out-of-project access and an optional auto-approve mode for disposable environments, web search, browser control, screen operation, voice dictation, and reusable skills. The terminal interface can run locally against a remote server, and other terminals can attach to a running session by URL. Behavior is configured through project-level and global JSON files with published schemas.

## Tags

### Artificial Intelligence & ML

- [Terminal Coding Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/terminal-coding-agents.md) — Runs as a terminal coding agent that reads and edits project files, runs shell commands, and delegates work to LLM-powered agents.
- [Agent Memory Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-persistence.md) — Keeps project knowledge and decisions across sessions so the coding agent resumes with earlier context instead of starting over. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Agent Session Memory](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-session-memory.md) — Stores project knowledge, session checkpoints, and task logs in a searchable database and injects them back when a session resumes.
- [Context Memory Management](https://awesome-repositories.com/f/artificial-intelligence-ml/context-memory-management.md) — Controls what stays in the working context through automatic checkpoints and rebuilds so long sessions remain coherent within model limits. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Context Window Management](https://awesome-repositories.com/f/artificial-intelligence-ml/context-window-management.md) — Saves checkpoints and rebuilds context from memory plus recent messages when a model's window nears its limit, using per-model thresholds.
- [Automatic Context Compaction](https://awesome-repositories.com/f/artificial-intelligence-ml/long-context-processing/automatic-context-compaction.md) — Saves checkpoints automatically and rebuilds working context when the model window nears its limit, using per-model thresholds. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Multi-Agent Orchestration Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-orchestration-frameworks.md) — Spawns context-sharing subagents and runs scripted sandbox workflows that coordinate parallel agents with bounded retries and a judge model.
- [Subagent Delegation](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-orchestration/subagent-delegation.md) — Delegates work to helper agents that share session context, run in parallel or background, and can be tracked and cancelled. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Multi-Agent Task Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-task-orchestrators.md) — Splits large jobs across parallel subagents and scripted sandbox workflows with bounded retries, with an independent judge confirming completion.
- [Project Memory Retention](https://awesome-repositories.com/f/artificial-intelligence-ml/project-memory-retention.md) — Keeps a persistent record of the codebase across sessions so the assistant recalls its understanding of the project later. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Searchable Agent Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/searchable-agent-memory-stores.md) — Keeps project knowledge, checkpoints, notes, and task logs in a searchable database and injects them back into context when a session resumes.
- [Agent Lesson and Work Recording](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-lesson-and-work-recording.md) — Reviews past sessions to extract lasting knowledge into memory, prune outdated entries, and package repeated workflows into reusable skills. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Agent Stop Guards](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-stop-guards.md) — Prevents the agent from stopping until an independent judge confirms the stated session goal is met. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Agent Task Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-task-orchestrators.md) — Picks models and tools dynamically by task type and cost, and runs complex tasks across several agents working in parallel. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Agentic Project Memories](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-project-memories.md) — Persists project knowledge, checkpoints, and task progress across sessions and turns past lessons into reusable skills.
- [Autonomous Goal Pursuit](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-goal-pursuit.md) — Repeats planning and acting cycles on its own until a stated goal is reached, with a judge model confirming completion. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Build and Plan Agent Modes](https://awesome-repositories.com/f/artificial-intelligence-ml/build-and-plan-agent-modes.md) — Lets users switch with a key press between a full-permission build agent and a read-only plan agent for safe exploration. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Agent Workflow Scripting](https://awesome-repositories.com/f/artificial-intelligence-ml/code-execution-agents/agent-workflow-scripting.md) — Runs multi-agent workflows as scripts in an isolated sandbox with fixed phases, bounded retries, and parallel branches for repeatable orchestration.
- [Knowledge Distillation into Skills](https://awesome-repositories.com/f/artificial-intelligence-ml/knowledge-distillation-into-skills.md) — Finds repeated manual workflows in recent sessions and packages the most confident ones into reusable skills, helper agents, or commands. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Long Autonomous Runs](https://awesome-repositories.com/f/artificial-intelligence-ml/long-autonomous-runs.md) — Keeps project knowledge, checkpoints, and task progress so long-running work resumes exactly where it stopped across sessions.
- [Model API Provider Profiles](https://awesome-repositories.com/f/artificial-intelligence-ml/model-api-provider-profiles.md) — Registers any OpenAI-compatible provider by base URL, API key, and model ID, and declares which input types each model accepts. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Multi-Provider Model Support](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-provider-model-support.md) — Works with many model providers from one terminal interface, with language server, tool server, and plugin support for extension. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Persistent Task Trees](https://awesome-repositories.com/f/artificial-intelligence-ml/persistent-task-trees.md) — Tracks work as a numbered task tree whose progress is checkpointed so interrupted sessions resume at the exact node they left.
- [Reusable Instruction Skills](https://awesome-repositories.com/f/artificial-intelligence-ml/reusable-instruction-skills.md) — Matches tasks to bundled or custom instruction sets by name and relevance, loading them automatically or through a slash command. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Subagent Context Protection](https://awesome-repositories.com/f/artificial-intelligence-ml/subagent-context-protection.md) — Launches helper agents that inherit the parent's context, run in parallel or background, and are tracked in a registry supporting cancellation.
- [Subagent Orchestrations](https://awesome-repositories.com/f/artificial-intelligence-ml/subagent-orchestrations.md) — Launches helper subagents that share the parent's context, run in parallel or background, and report results back to the main agent. ([source](https://github.com/xiaomimimo/mimo-code#readme))

### Development Tools & Productivity

- [Terminal AI Coding Assistants](https://awesome-repositories.com/f/development-tools-productivity/terminal-ai-coding-assistants.md) — Reads and edits project files, runs shell commands, and manages version control from a single interactive terminal interface driven by AI agents. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Terminal Coding Assistants](https://awesome-repositories.com/f/development-tools-productivity/terminal-coding-assistants.md) — Reads and edits project files, runs shell commands, and manages Git from inside a terminal-based AI coding assistant. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Resumable Project Sessions](https://awesome-repositories.com/f/development-tools-productivity/resumable-project-sessions.md) — Injects stored project knowledge, checkpoints, notes, and task logs when a session resumes so work continues where it stopped. ([source](https://github.com/xiaomimimo/mimo-code#readme))

### Part of an Awesome List

- [LLM Provider Configurations](https://awesome-repositories.com/f/awesome-lists/ai/llm-providers-and-models/llm-provider-configurations.md) — Connects to major model providers via API keys, browser sign-in, or imported credentials, or any custom endpoint by base URL and model ID. ([source](https://github.com/xiaomimimo/mimo-code#readme))

### Security & Cryptography

- [Database Memory Persistence](https://awesome-repositories.com/f/security-cryptography/identity-access-management/session-management/stateful-session-persistence/agentic-session-persistence/database-memory-persistence.md) — Stores project knowledge, checkpoints, notes, and task logs in a searchable database and reloads them when a session resumes. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [API-Key-Only Provider Connections](https://awesome-repositories.com/f/security-cryptography/api-key-management/api-key-only-provider-connections.md) — Guides first-launch setup to connect model providers through platform sign-in, imported credentials, API keys, or custom providers. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [AI Agent Permissions](https://awesome-repositories.com/f/security-cryptography/permission-based-access-control/ai-agent-permissions.md) — Prompts before out-of-project actions, applies allow and deny rules, and offers optional auto-approval in disposable environments. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Persisted Permission Rules](https://awesome-repositories.com/f/security-cryptography/persisted-permission-rules.md) — Passes every tool action through allow and deny rules, prompting for out-of-project access, with an optional auto-approve mode for disposable environments.
- [Hierarchical Task Trees](https://awesome-repositories.com/f/security-cryptography/process-sandboxes/session-resumption/ai-agent-sessions/session-task-tracking/hierarchical-task-trees.md) — Organizes work into a numbered task tree and saves progress at checkpoints so interrupted sessions resume at the exact node. ([source](https://github.com/xiaomimimo/mimo-code#readme))

### Software Engineering & Architecture

- [End-to-End Feature Delivery](https://awesome-repositories.com/f/software-engineering-architecture/end-to-end-feature-delivery.md) — Runs a contract-driven loop from clarification through specification, implementation, verification, and review, leaving feature documents in the workspace. ([source](https://github.com/xiaomimimo/mimo-code#readme))
- [Client-Server Architecture](https://awesome-repositories.com/f/software-engineering-architecture/client-server-architecture.md) — Splits a lightweight local terminal client from a separate server that runs the session and accepts remote attachments by URL.
- [AI-Driven Feature Implementation](https://awesome-repositories.com/f/software-engineering-architecture/incremental-implementations/ai-driven-feature-implementation.md) — Runs a contract-driven loop taking a feature from clarification through specification, implementation, verification, and review, leaving documents in the workspace.

### Data & Databases

- [Project Knowledge Retention](https://awesome-repositories.com/f/data-databases/technical-knowledge-bases/knowledge-retention-tools/project-knowledge-retention.md) — Scans recent session traces, saves lasting knowledge to project memory, and removes outdated entries to keep context accurate. ([source](https://github.com/xiaomimimo/mimo-code#readme))