{"slug": "mimo-code-run-xiaomis-free-claude-code-alternative-in-10-minutes", "title": "MiMo Code: Run Xiaomi’s Free Claude Code Alternative in 10 Minutes", "summary": "Xiaomi released MiMo Code, an open-source AI coding agent that forks OpenCode and adds persistent cross-session memory, three days ago. The tool, which installs in one command and is available under an MIT license, has become the most-watched open-source AI coding agent on GitHub. MiMo Code offers three configuration paths, including a free anonymous mode and a paid tier at $1 per million input tokens, and claims to outperform Claude Code on tasks exceeding 200 execution steps.", "body_md": "MiMo Code dropped three days ago and is already the most-watched open-source AI coding agent on GitHub. Xiaomi’s terminal agent forks from [OpenCode](https://opencode.dev), adds persistent cross-session memory that Claude Code still lacks, ships under an MIT license, and installs in one command. If you’ve been eyeing alternatives to Claude Code — especially after [this week’s agentic billing shock](https://byteiota.com/github-copilot-billing-agentic-cost-jump-2026/) — here’s how to get MiMo Code running and when it’s actually worth using.\n\n## Install in One Line\n\nRequirements: Node.js 18 or later. That’s it.\n\n**Mac and Linux:**\n\n```\ncurl -fsSL https://mimo.xiaomi.com/install | bash\n```\n\n**Windows (via npm):**\n\n```\nnpm install -g @mimo-ai/cli\n```\n\nRun `mimo`\n\nafter installation and a TUI setup wizard launches automatically. It walks you through three configuration paths depending on what you need.\n\n## Three Ways to Configure It\n\nThe setup wizard offers these options:\n\n**MiMo Auto** — Anonymous, zero-config mode using a shared inference pool. Rate-limited but free. Good for evaluating MiMo Code before committing to an API key. Not suitable for production or sustained work.\n\n**Xiaomi MiMo Platform API Key** — Sign up at [platform.xiaomimimo.com](https://platform.xiaomimimo.com), generate a key, and you’re on the paid-but-cheap tier: $1 per million input tokens and $3 per million output tokens as of the May 2026 permanent price cut. The free Flash model on [OpenRouter](https://openrouter.ai) is also an option for lighter development work.\n\n**Import Claude Code Auth** — The path most existing Claude Code users will take. One step in the wizard imports your existing Anthropic credentials and routes them through MiMo Code’s harness. Before you do this, clear any conflicting environment variables:\n\n```\nunset ANTHROPIC_AUTH_TOKEN ANTHROPIC_BASE_URL\nmimo\n```\n\nIf you’d rather configure it manually, set these environment variables:\n\n```\nANTHROPIC_BASE_URL=https://api.xiaomimimo.com/anthropic\nANTHROPIC_AUTH_TOKEN=<your-mimo-api-key>\n```\n\nMiMo Code also supports 75+ OpenAI-compatible providers — Ollama for local models, OpenRouter, or any custom endpoint — configured through the TUI.\n\n## Your First Task: Compose Mode\n\nOnce configured, run `mimo`\n\nin any repo directory. To kick off an agentic task without micro-managing every step, press `Tab`\n\nto activate Compose mode. Give the agent a rough description — “refactor the auth module to use the new middleware pattern” — and it plans, codes, tests, and reviews without waiting for approval at each step.\n\nThis is functionally equivalent to Claude Code’s agentic mode. The key difference shows up when tasks run long.\n\n## The Memory System: Why This Actually Matters\n\nThis is the real reason to try MiMo Code, not the benchmarks.\n\nClaude Code loses everything at session end. Restart Claude Code tomorrow and it has no memory of today’s architectural decisions, preferred patterns, or project-specific context. You re-explain from scratch. For short tasks this is fine. For a multi-day refactoring project, it’s genuinely painful.\n\nMiMo Code addresses this architecturally with two commands:\n\n**/dream** — Run this at the end of a session or after a significant milestone. It scans recent session traces, extracts persistent knowledge into project memory, deduplicates, and removes stale entries. Think of it as the agent summarizing what it learned about your codebase into a long-term store.\n\n**/distill** — Run this after you’ve repeated the same manual workflow a few times. The agent identifies high-confidence patterns from recent work and auto-packages them as reusable skills or subagents. Tedious tasks you do repeatedly become automated.\n\nXiaomi’s self-reported data claims MiMo Code outperforms Claude Code on tasks exceeding 200 execution steps, with a win rate above 65% and 40–60% fewer tokens used. Take those specific numbers with appropriate skepticism — they’re unverified, and the comparison is against Claude Sonnet 4.6, not Opus 4.8. But the underlying mechanism is real: persistent memory prevents goal drift on long-horizon tasks in a way that purely session-scoped agents can’t. [VentureBeat’s deep-dive](https://venturebeat.com/technology/xiaomis-new-open-source-agentic-ai-coding-harness-mimo-code-beats-claude-code-at-ultra-long-200-step-tasks/) on the architecture is worth reading for more context.\n\n## Honest Assessment: When to Use It\n\nMiMo Code is three days old. The benchmarks are self-reported. The ecosystem is weeks, not years, from maturity. Here’s where it actually makes sense:\n\n**Use MiMo Code for:** Long, multi-session tasks where Claude Code context loss is a real problem. Cost-sensitive workloads — the free Flash model on OpenRouter covers substantial development work. Open-source or non-sensitive repos where you’re comfortable with a newer tool. Experimenting with custom model backends (Ollama, local weights).\n\n**Stick with Claude Code for:** Enterprise workflows where audit trails and explicit approval gates matter. Tasks where Claude Opus 4.8’s reasoning quality is the bottleneck. Any situation where you need a proven track record over several months of production use.\n\nThe practical play for most developers is running both: MiMo Code for long-horizon autonomous tasks and cost control, Claude Code for high-stakes reasoning work. The memory import path makes switching between them frictionless.\n\n## Get Started\n\nThe [MiMo Code GitHub repository](https://github.com/XiaomiMiMo/MiMo-Code) has full documentation, open issues, and the growing MiMo-Skills library. If you want the model without the harness, [platform.xiaomimimo.com](https://platform.xiaomimimo.com) has API access and pricing. MiMo-V2-Flash is available free on OpenRouter for developers who want to test before committing. For context on [what MiMo Code claimed at launch](https://byteiota.com/mimo-code-open-source-benchmarks/), see our earlier coverage.\n\nThree days in, MiMo Code is already a serious option. It won’t replace Claude Code for everyone today. But for long tasks and tight budgets, it’s worth the ten minutes to find out.", "url": "https://wpnews.pro/news/mimo-code-run-xiaomis-free-claude-code-alternative-in-10-minutes", "canonical_source": "https://byteiota.com/mimo-code-run-xiaomis-free-claude-code-alternative-in-10-minutes/", "published_at": "2026-06-15 19:24:32+00:00", "updated_at": "2026-06-15 19:45:14.250114+00:00", "lang": "en", "topics": ["ai-tools", "ai-agents", "developer-tools"], "entities": ["Xiaomi", "MiMo Code", "OpenCode", "Claude Code", "GitHub", "OpenRouter", "Anthropic", "Ollama"], "alternates": {"html": "https://wpnews.pro/news/mimo-code-run-xiaomis-free-claude-code-alternative-in-10-minutes", "markdown": "https://wpnews.pro/news/mimo-code-run-xiaomis-free-claude-code-alternative-in-10-minutes.md", "text": "https://wpnews.pro/news/mimo-code-run-xiaomis-free-claude-code-alternative-in-10-minutes.txt", "jsonld": "https://wpnews.pro/news/mimo-code-run-xiaomis-free-claude-code-alternative-in-10-minutes.jsonld"}}