qybaihe/mu
mu (μ): a coding agent that thinks before it acts. A small, fast judge makes the routine calls, the big model does the work. Built on pi and AionUi.
About the project
A coding agent with a judgment kernel: a small, fast judge model makes routine calls (command risk, what stays in context, when work is done) while the big model does the coding. Ships as a CLI and a desktop app.
Useful for
- Run the CLI agent for project edits with automatic checks on risky commands
- Configure the local Laya judge instead of an LLM to make decisions without token cost
- Compare different judges in shadow mode before enabling a decision point
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 51 stars so far today, about 62 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 2 days old and already has 104 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #186.
- Recent forks include notable developers: @lvy010 (4,523 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 104
- Today
- 51 · ≈ 62 by evening
- Forks
- 6
- Issues and pull requests
- 2
- Watchers
- 0
- Language
- TypeScript
- License
- MIT
- Latest release
- v0.1.3 · September 23, 2026
- Created
- September 22, 2026
- Last push
- September 23, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 24, 2026Top new repositories this week: #186
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/qybaihe/mu)More in this category
-
8.1
NandhaKishorM/laya
Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.
-
8.1
google/ax
A declarative orchestrator for running autonomous AI agent workloads in a cluster, using a Kubernetes-like model with Task, Workspace, Gateway, and Model manifests. It sandboxes agents, pre-wires their environment, and…
-
7.6
unreallabsai/unreal-agent
Async-first agent harness in Go: sessions with persisted forkable history, input deduplication, an LLM-turn coordinator, and asynchronous operation execution via swappable components.
-
7.4
vectorize-io/hindsight
Hindsight is a long-term memory system for AI agents that stores facts and observations rather than just conversation history, reporting state-of-the-art results on the LongMemEval benchmark. It runs as a server…
-
7.4
strands-agents/harness-sdk
Open-source Python and TypeScript SDK for building and running AI agents: agent loop, tools, MCP, memory, multi-agent patterns and tracing in one package. Runs in your process with no hosted control plane and supports…
-
7.2
mikehasa/golive-skill
Agent Skill and Node CLI that takes an agent-built app live: hosting, database, domain, email and payments on your own accounts. Runs a detect → plan → approve → apply → verify cycle with no hosted backend or telemetry.