MiMo-Code na Xiaomi Claude Code alternative?

MiMo-Code na wetin?

MiMo-Code na terminal coding agent wey Xiaomi MiMo team build and release as open source on 15 June 2026 under MIT license. E dey run as CLI (command line interface) tool for your shell. E dey read and edit files for project, run shell commands, use git, and keep notes about the codebase between sessions.

The structure dey similar to Claude Code. You go describe task for plain language, the agent go suggest edits and commands, then you approve dem. Two differences dey important. The source dey open, so you fit read exactly wetin the agent send go the model. And the model na separate choice from the agent, so the same harness fit connect to Xiaomi models, OpenAI-compatible endpoint, or model wey you host by yourself.

The repository name na MiMo-Code and the command wey e install na mimo. Documentation use both names, so search for either one go find the same tool.

Where MiMo-Code come from, and why e matter

MiMo-Code na fork of OpenCode, the open-source terminal agent from the sst project. The LICENSE file still get the original Copyright (c) 2025 opencode line, and the README get one short section about the relationship. One open issue dey for the repository, asking Xiaomi to give the OpenCode contributors fuller credit than just keeping one license line.

Knowing this dey explain something wey fit otherwise look impossible. A project wey first release for June 2026 already dey ship with polished TUI (text user interface), plugin system, provider abstraction wey fit talk to many model APIs, MCP (model context protocol) support, and LSP (language server protocol) integration. Dem no do all this work within six weeks. E come with the fork. The new things from Xiaomi na the memory layer and the connection to Xiaomi own models.

If you don already run OpenCode for VPS, the layout and keybindings go feel familiar, because na the same code dey underneath.

Wetin “models and agents co-evolve” really mean

The repository tagline na “Where Models and Agents Co-Evolve”. This phrase get two different claims, but na only one get published detail wey back am.

The first claim concern runtime, and dem document am. MiMo-Code dey keep persistent memory store for each project, backed by SQLite full-text search, together with session state and task progress. Two slash commands dey control am. /dream dey pull durable knowledge from recent sessions and write am into project memory. /distill dey turn procedure wey dey repeat into reusable skill. Xiaomi own engineering write-up talk say these dey run on cycle of roughly one to four weeks, instead of after every session. So agent behaviour for your repository dey change over time, while the model file remain the same.

The second claim concern training, and for here you need reason well. Xiaomi describe post-training of MiMo-V2.5 as three-stage pipeline: supervised fine-tuning, then large-scale agentic reinforcement learning (RL), then on-policy distillation from several specialist teacher models into one student. Agentic RL mean say dem train the model with multi-step tool-calling episodes instead of single question-and-answer pairs. This one real, and na why the model fit stay consistent across long tool sequences. But Xiaomi never publish training report wey show say dem optimise the model inside this specific harness, with the harness changing as response.

So understand “co-evolve” as statement of intent from team wey own both sides. The benefit wey you fit actually observe dey narrower, but e still get value: na the same people dey write the tool schemas and system prompt and ship the model, so dem fit each other. Claude Code no fit work like that, because its harness na client of fixed API model. Anthropic dey train its models for agentic use too, but you no fit swap the model from underneath the harness.

MiMo-Code session for terminal dey look like this

When you run mimo, e go open full-screen terminal interface. You go type task, agent go read files, propose change, then ask before e write or run anything. Apart from default build mode, e get plan mode and compose mode, plus subagent system wey dey hand part of job to separate agent run. E also carry plenty built-in skills, wey be prepackaged procedures wey agent fit call by name. Skill fit also change how agent dey work instead of wetin e know. Na this idea dey behind Ponytail, skill wey make agent use the smallest change wey go work.

Make you know these few details before you start.

• By default, approval dey happen for each action. Flag --dangerously-skip-permissions remove the prompts. The name clear, so use am only when mistake no go cost anything.
• E fit run without interactive terminal. mimo run dey take prompt and execute non-interactively, na wetin script or CI job need. Web interface dey available too.
• Configuration dey inside files wey you fit commit. Project dey read .mimocode/mimocode.jsonc, while global settings dey inside ~/.config/mimocode/mimocode.jsonc.
• Credentials no dey inside those files. Dem dey go ~/.local/share/mimocode/auth.json, so keep that path out of git and any backup wey you dey share.

Agent wey fit run shell commands na program wey you don hand your shell give. Give am e own machine and e own user. The safest way to test new one na disposable VM wey you fit destroy after the session, because bad command go cost you rebuild instead of restore.

MiMo-Code really pass Claude Code?

Xiaomi launch material make one clear claim: run the same model inside both harnesses, and MiMo-Code score higher. Na these published figures.

[
  {
    "tool": "MiMo-Code",
    "swe_bench_pro_pct": 62,
    "terminal_bench_2_pct": 73
  },
  {
    "tool": "Claude Code",
    "swe_bench_pro_pct": 57,
    "terminal_bench_2_pct": 68
  }
]

For SWE-bench Pro, Xiaomi report 62 percent for MiMo-Code against 57 percent for Claude Code. For Terminal Bench 2, the figures na 73 percent and 68 percent. The point be say the model remain the same, so the gap of about five points come from the agent system, not from the model.

Treat these numbers as vendor numbers. Xiaomi run the evaluation and publish am, and MiMo-Code no dey appear for the public SWE-bench or Terminal-Bench leaderboards, so no independent person don reproduce the gap. Xiaomi dey unusually direct about the limit of its own result. The company write-up say these benchmarks measure one-shot problem solving for issues inside one repository, and say for its own testing, the two agents perform about the same below roughly 200 execution steps. The claimed advantage dey show for long runs, and one-shot benchmark no cover that case.

Na this be the honest reading. Five-point gap for benchmark wey vendor run na reason to try the tool. E no be reason to move work wey your team depend on go am.

Wetin MiMo-Code cost to run

For launch, Xiaomi release one free channel wey dem call MiMo Auto, and you fit use am without registration. From the beginning, dem describe am as something wey go last for limited time. The release notes for version 0.1.9 on 24 July 2026 mention say the free MiMo-V2.5 trial go end. No build workflow on top am.

Paid access to Xiaomi platform cheap compared with frontier providers. As of August 2026, the published international price for MiMo-V2.5-Pro na $1.00 per million input tokens when cache miss happen, and $3.00 per million output tokens, for context up to 256K. Prices fit change, so read the current page before you plan budget.

The other option na to use your own hardware. Dem publish the weights for MiMo-V2.5 and MiMo-V2.5-Pro on Hugging Face under MIT license, so nothing stop you from serving dem yourself. But make you plan for the real scale. Model wey get one million token context window no be work for ordinary VPS. You go need VPS wey get GPU attached or dedicated machine. Smaller local models na different kind work, and e dey closer to running Ollama on VPS to self-host LLM.

MiMo-Code fit also connect to other vendors. E fit migrate existing Claude Code login, connect OpenAI account, accept API key for another provider, or talk to any OpenAI-compatible endpoint. Check the terms of consumer subscription before you connect am. Provider terms decide which clients fit use subscription plan, and CLI from another vendor no always dey covered.

You suppose move commot from Claude Code?

If you already dey pay for Claude Code and e dey work, no. Version 0.1.9 for late July 2026, six weeks after the first release, na the honest signal. Version number wey be 0.1.x mean say breaking changes fit happen between releases, and configuration format still dey change. This dey okay for tool wey you dey evaluate, but e dey painful for tool wey team depend on.

MiMo-Code deserve serious consideration for four situations.

• The bill na your problem. Xiaomi token prices dey far below frontier vendors, and the agent itself no cost anything.
• You need read the harness. Open source mean say you fit inspect the prompts and tool definitions. This matter for security review or audit.
• You want make the agent and model be separate purchases, so changing one no go force you change the other.
• The code no fit commot your network. Open weights make self-hosted backend possible instead of negotiation.

Cursor and Copilot na different comparison. Both dey inside editor, while MiMo-Code dey inside terminal. This difference shape more of your workday than any benchmark score, and the comparison of Claude Code with Cursor, Codex and Copilot explain the trade-off well.

MiMo-Code dey run for VPS wey you don rent already

Terminal agent suppose dey for server. E dey keep session open for hours, e need stable network, and e suppose continue to run even when you close laptop lid. The normal way na the same one wey people dey use for other terminal agents: long-lived session for small server wey you fit reconnect to from anywhere, as we explain for how to run coding agent for tmux on VPS.

Give am dedicated unprivileged user, and point am to clone of the repository instead of your only copy. The account wey e run as na the limit of wetin e fit reach. Na this control still dey work when prompt go wrong.

The project get 2 distribution methods: shell installer wey dem serve over HTTPS, and npm package wey dem name @mimo-ai/cli for any machine wey already get Node.js. For server wey matter to you, prefer the npm package. You fit read wetin dey inside the package before e run, and you no dey pipe remote script directly into shell. For broader view of other things wey deserve space for that box, the roundup of self-hosted AI agents na the map.

FAQ

MiMo-Code free dey?

The agent free and open source under MIT license, so you fit read am and modify am. Na the model wey dey behind am cost money. Xiaomi release limited-time free channel wey dem call MiMo Auto when e launch, and the release notes from 24 July 2026 talk say that trial don end, so plan for paid access. As of August 2026, the published international price for MiMo-V2.5-Pro na $1.00 per million input tokens when cache miss happen, and $3.00 per million output tokens. You fit also point MiMo-Code to any OpenAI-compatible endpoint and pay another vendor instead.

MiMo-Code na the same thing as OpenCode?

E start as fork of OpenCode and e still share the core. The terminal interface, plugin system, provider abstraction, and MCP integration all come from that codebase, and OpenCode copyright line still dey inside repository LICENSE file. Xiaomi add persistent memory layer wey SQLite full-text search dey back, extra agent modes, and direct access to its own models. If you sabi OpenCode, you don already sabi most of how MiMo-Code dey behave.

I fit use MiMo-Code with Claude or GPT models instead of Xiaomi own ones?

Yes. The first-run setup offer to migrate existing Claude Code login, connect OpenAI account, or accept API key for another provider, and you fit configure any OpenAI-compatible endpoint by hand for ~/.config/mimocode/mimocode.jsonc. Check the terms of consumer subscription before you connect am, because provider terms control which clients fit use subscription plan.

MiMo-Code safe to run for my main machine?

Treat am like any agent wey fit run shell commands. By default, e dey ask for approval before every action, and --dangerously-skip-permissions go turn those prompts off; na so most accidents dey happen. Run am as dedicated unprivileged user, against clone of the repository, and preferably for machine wey you fit destroy and rebuild. The blast radius na the account wey e run as, so keep that account small.