mu
mu is an open-source coding agent with a judgment kernel: a small, fast judge model makes the many routine decisions in each turn so the main model only gets the context it needs. It ships as a command-line tool and a desktop app and aims to keep coding sessions focused and cheap.
Updated
✨ Try AgentScout's free AI image generator →Good for: writing code, coding in the terminal, controlling a computer, open-source agents
Use cases
About mu
mu is listed in our coding category and is aimed at builders. mu is an open-source coding agent with a judgment kernel: a small, fast judge model makes the many routine decisions in each turn so the main model only gets the context it needs. It ships as a command-line tool and a desktop app and aims to keep coding sessions focused and cheap. Pricing, as the maker states it: Open source. Maturity: Active. We last checked the official link on 2026-10-23.
mu at a glance
- Category: Coding
- Built for: Developers and teams building with AI agents
- Pricing: Open source (as the maker states it)
- GitHub: qybaihe/mu · 537 stars (as of Oct 23, 2026)
- Official site: usemu.dev
- Listed on AgentScout: Oct 23, 2026
mu FAQ
What is mu?
mu is an open-source coding agent with a judgment kernel: a small, fast judge model makes the many routine decisions in each turn so the main model only gets the context it needs. It ships as a command-line tool and a desktop app and aims to keep coding sessions focused and cheap.
How much does mu cost?
mu's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Where can I find mu's source code?
On GitHub at qybaihe/mu, which had 537 stars as of Oct 23, 2026.
What are alternatives to mu?
Similar tools include opencode, Context Mode, Kilo Code, Paritok, MonoCode and Tov.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
mu ratings and reviews
Be the first to rate mu: tap 1 to 5 stars below. A written review is optional.
mu alternatives
Other coding tools in our directory. See all coding tools →
opencode
Open-source terminal coding agent that works with many model providers.
Context Mode
Context window optimizer for coding agents that sandboxes tool output and persists session memory.
Kilo Code
Open-source AI coding agent for VS Code, JetBrains, the CLI and the cloud that works with 500+ models at no markup.
Paritok
Paritok is a compression gateway that sits between a coding agent and its LLM. Using its own open-source 4B code-aware model, it shrinks tool output, files and conversation history on the fly without losing what the agent needs, which cuts token bills and lets agent sessions run longer before they hit context limits.
MonoCode
MonoCode is a desktop app that puts the coding agents you already pay for behind one interface. It drives Claude Code, Codex, Cursor, Grok Build, OpenCode, Antigravity, Pi, Hermes Agent, Devin and others, using the subscriptions and logins already on your machine, so you never buy tokens through it. Each tab is an agent session and one composer sends work to whichever agent you pick, so several sessions can run side by side. It runs on macOS, Windows and Linux, with an iOS app in public beta.
Tov
Tov is an experimental programming language designed to be written by coding agents. It uses TypeScript syntax minus a few traps (no any, null or loose equality, separate int and float types, and failing calls marked with try), so agents already know how to write it, and its compiler returns machine-readable fixes the agent can apply after every edit. Programs compile to small, fast native binaries, with published benchmarks against Rust, Bun and Node. Agents can learn it from the site's llms.txt.
Related lists
🏆 Ranked in: opencode alternatives · OpenAI Codex CLI alternatives
🔁 Listed in: Gemini CLI alternatives · OpenAI Codex CLI alternatives · opencode alternatives
Badge for makers
Built mu? Add this badge to your README or site. It links back to this page. About badges
