Coding & dev tools

@sadiksaifi

@sadiksaifi

Pi extension that lets you sign in with a Meta Muse Code subscription via device code and pick meta-muse models, verifying the subscription so it never falls back to pay-as-you-go.

A community-built VS Code chat UI for Muse Code, Meta's agentic coding CLI, inspired by the Claude Code extension; about 145 installs on the Marketplace.

@QuJindai

@QuJindai

A Muse skill and thin gh-style CLI for the GitHub REST API that authenticates through a stored custom.github connector, so the skill never handles the raw token.

@luckeyfaraday

@luckeyfaraday

An unofficial loopback shim that lets Meta Muse Code use OpenAI Responses APIs, OpenRouter, Codex OAuth and the official Claude Code CLI, switchable from Muse's /model menu.

@albertodepaola

@albertodepaola

Out-of-tree Hermes Agent model-provider plugin for the Meta Model API and the Muse Spark family, including the low-cost muse-spark-1.2-contributor tier.

@LucasDuys

@LucasDuys

sol-loop pairs a GPT planner on a Codex subscription with Muse Spark in opencode as executor, which returns evidence and diffs for each atomic spec; the author says over 99% of tokens run on Muse.

@kengzzzz

@kengzzzz

An installer for a muse profile in OpenAI Codex plus helper binaries, including a Meta device-code login helper, so Codex can run on Muse without the muse binary.

@Wraient

@Wraient

A Go reverse proxy with an embedded dashboard that lets Claude Code and OpenAI/Codex clients use muse-spark models through a Muse Code subscription, authenticated with the muse login credential.

Federico Ramirez uses Muse Code and Spark 1.3 for GitHub issue-to-PR workflows. He finds output readable and $15/month good for 2-4 hours of continuous coding, but skill execution inconsistent and the sandbox too restrictive.

@latekaapi

@latekaapi

A native macOS window for Muse Code that drives muse serve over MSP and renders approvals, questions, plans, todos and tool output as interface elements instead of terminal text.

@julianubico

@julianubico

Unofficial adapter that exposes Muse Code over the Agent Client Protocol on stdio, designed to run as an acpx custom agent.

@zereight

@zereight

Pi extension that registers a muse-code provider through @muse-code/sdk over the Muse Session Protocol, resuming the same Muse session when switching models mid-conversation.

@anuragdhar

@anuragdhar

A VS Code extension that runs the Muse Code CLI in a sidebar and also adds Muse Spark 1.2 models to VS Code Chat Agent Mode, with inline completions and live token and cost tracking.

OpenRouter

@OpenRouter

Muse Spark 1.3 is now available on OpenRouter! Built for long-running agentic, multi-agent, and coding workflows. It tracks what it learns, handles conflicting inputs, and asks for clarification or confirmation when needed. Use it now: openrouter.ai/meta/muse-spar…

@atameric

@atameric

An unofficial macOS desktop client that speaks MSP over muse serve, offering streaming markdown, visible tool calls, session history shared with the terminal and screenshot attachments.

@kamellperry

@kamellperry

A reverse-engineered local CLI and FastAPI wrapper that talks to Meta AI's Muse Spark and exposes an OpenAI-compatible /v1/chat/completions endpoint, with a browser playground and a SQLite request ledger.

OpenRouter

@OpenRouter

Muse Spark 1.1 is available now on OpenRouter for US-based developers. openrouter.ai/meta/muse-spar…

AI John walks through installing OpenCode, creating an API key and connecting Muse Spark 1.3 on the Contributor Free tier, noting prompts may be used for training.

@shelajev

@shelajev

A Docker Sandboxes kit that runs Meta's Muse Code CLI in an isolated sandbox, allowing network access only to the Meta services needed for install, auth and model requests.

Patrick Donohoe

@patrickdonohoe

Introducing floo, a cloud platform where your personal agent can build and run apps for you. Tell Muse what you need. It builds the software. floo handles hosting, data, and login, giving your Muse tools it can keep using and you an app to see and guide its work. Launching

@karimkfoure

@karimkfoure

An OpenCode plugin that ports Muse Code's subagent coordination core: durable child workers, a ledger mailbox and admission control, so subagents survive crashes and respect capacity.

WTF Code shows how to wire Muse Spark 1.2 into OpenCode through the OpenCode Zen API and tests it as an Opus 4.8 challenger.

@pinta-ai

@pinta-ai

Pinta AI adapter that forwards Muse Code lifecycle hook events to an OTLP collector and can optionally enforce guard decisions, verified end to end against muse 0.1.0.

@souta-lab

@souta-lab

A Pi fork that runs Muse Code's system prompt and tool interface on Pi's agent loop and TUI, as an open, hackable harness for Muse Spark 1.3.

@phareim

@phareim

musecode adds a /musecode slash command, a Haiku relay agent and a muse-run CLI so Claude Code Workflow fan-outs run their leaf tasks on the free Muse Spark 1.3 model through opencode.

@reduced2ash

@reduced2ash

Integration that makes Muse Code a first-class agent in the Herdr terminal workspace manager, tracking idle, working and blocked states, without rebuilding Herdr.

@SecretLUL

@SecretLUL

Muse Code Remote is an open-source web UI and outbound WebSocket relay that lets users drive their terminal Muse Code agent from any browser without opening ports.

@aminamos

@aminamos

Four graphical frontends for Muse Code (Tauri apps for Windows and macOS, Expo apps for iOS and Android) plus a Deno relay, so every run executes through muse on the subscription login.

Solution: So after more research it seems that this KHO was recently activated in the latest Ubuntu kernel which zorin is based on. It seems to be for live updates of kernel and whatever but it puts quite a bit of strain on system that requires a lot of memory like AI work load. So I edited my GRuB file to turn it off. I was lucky that somehow my 7.0.0-30 kernel had a bug that disabled the KHO also thank you to Muse Spark AI for able to run all the trace and helped me figuring it out. KHO locked out 2gb of RAM causing my Llama cpp out of memory error. The original post So I been running Zorin OS as my semi daily driver for learning AI and fun. I been plague with odd behavior as I run my AI on knife edge consuming nearly all 16 GB of Ram and 8 GB of VRAM. I found something odd, that my AI would failed to load depending on which kernel. It turn out at least one of the culprit was KHO it somehow ate about 2GB of RAM. I found this because my Kernel 7.0.0-30 and the old 6.17 load my AI just fine but kernel 7.0.0-28 and the latest 7.0.0.-31 always failed to load. Below is the AI analysis that I had it trace issue through my system: - `-30` boot `-2`: `Memory: 15384980K avail / 8261

mihawkxxx

@mihawkxxxxx

Incredible result from Muse Spark 1.3. A procedurally generated Minecraft world in a single HTML file. All of this cost me 10 cents for the entire development. The cheapest powerful AI is now available to everyone and very fast.

Jon ONeill

@HouseHackerJon

Its been 1 day and I had added almost 100 features to 4 apps im building while I slept 300m tokens used Muse QA’s them and pushed to prod as well If you want 1B tokens free sign up here Redeem my code in Settings within 48 hours of joining and we'll both get 1 billion @Muse

@akshat12

@akshat12

A Herdr integration that uses Muse Code lifecycle hooks to show muse panes as working, idle or blocked (approval needed) in Herdr's sidebar, with no Herdr fork.

Andrew Brown's three-hour freeCodeCamp course on building apps and agent workflows with Muse Spark and the Muse Code CLI, ending in a full-stack Go/SQLite/Docker build.

Mark Zuckerberg

@finkd

There's an SDK in developer preview for building your own agents on Muse Code. Embed them in your apps, connect custom tools, stream progress, and resume sessions later.

@LimpingNinja

@LimpingNinja

Oh My Pi plugin that registers an authenticated Muse Code install as the muse-code model provider, with a persistent muse serve host and a bundled muse-spark agent for task delegation.

freeCodeCamp's write-up of its three-hour Muse course by Andrew Brown, covering model benchmarks, API integrations, agent frameworks, the Muse Code harness, and a Go/SQLite/Docker full-stack build.

@dirtysouthalpha

@dirtysouthalpha

Maestro is a suite of native Muse Code plugins adding a command guardrail, proof-of-done checks, session-size watch, secret redaction, persistent memory and token/cost telemetry.

Vercel added Muse Spark 1.3 (meta/muse-spark-1.3) to AI Gateway on launch day, with 1M-token context, text/image/PDF input, and both standard and contributor pricing tiers.

We tried using Meta's new Muse Code agent, but it has a bug that doesn't let it sign in from a docker container. So we did a fun experiment: Meta claims Muse Spark 1.2 was co-trained with their Muse agent harness. So we extracted instructions from their system prompt and added them to the Cline harness. TL;DR of this special prompting: - Trust source code over the user prompt, so read every call site and existing tests before starting the task - Weigh edge and error cases as heavily as the happy path - Always reproduce the bug before fixing - Don't trust the first passing test suite, and verify suspicious looking half-baked tests - Never stop at just editing, keep working until the change is verified complete. We then asked this modified harness to fix a real bug from our repo, and compared the results to the original Cline agent harness. Results: - Used 2.7x fewer tokens (19.7M → 7.2M) - Finished 2x faster (49min → 24min) - Cost 2.4x less ($7.69 → $3.25) Same Muse Spark 1.2 model, same task, only the prompting changed. Incredible how much of a performance gain Meta was able to achieve training it on these special instructions!

@everyai-com

@everyai-com

A set of small fixes that let Muse Spark run in pi, Agent Orchestrator, opencode and other OpenAI-compatible tools, handling its non-standard SSE event and missing model-catalog entries.