Entries matching “coding”

@HarjjotSinghh

@HarjjotSinghh

Helicon is an open-source desktop and web app that wraps Meta's Muse Code CLI in a Codex/Claude-style interface, grouping sessions by project with history, resume and diffs on Windows, macOS and WSL2.

@dilmerv

@dilmerv

Dilmer Valecillos converted a minigolf prototype to VR for Meta Quest 3 using Muse Code with the Muse Spark 1.2 Contributor model, the Unity CLI and the MetaVR CLI, and published the plans and prompts.

Greg Ceccarelli

@gregce10

For funsies, I got Claude Code running on my Muse agent’s computer tonight. Muse gives every agent a Linux VM with 2 vCPUs, ~8GB RAM, 100GB of persistent disk plus a scheduler, hosted artifacts and their permission system. The VM has no inbound ports, so I built a tiny

@MoheetBrain

@MoheetBrain

A hands-free interface that turns Meta AI glasses into a voice control surface for Muse Code on a Mac: assign a task, walk away, hear progress, interrupt and approve sensitive steps.

harjot.co

@harjjotsinghh

I pay for @Muse Code but didn't want to live in a terminal. On Windows it's WSL-only. So I built Helicon: an open-source desktop app for the actual Muse CLI. • uses your existing muse login, no API key • talks to muse serve over MSP, so Muse stays the agent • resumes

PyTorch added end-to-end Muse Glimmer support to ExecuTorch; on an M5 Pro, DFlash speculative decoding lifts image+text decode from 21.6 to 33.0 tok/s, and it powers the Pi coding agent locally.

Been tinkering with speculative decoding on Apple Silicon for a while, and this week I got Meta's new Muse Glimmer 30B working in my project mlx-dspark. On my M4 Pro, the 8-bit model goes from 8.2 tok/s to 18-26 tok/s depending on content. Math is the best case at 3.27x, code 2.5x, chat 2.22x. Output is byte-identical to normal decoding since the target verifies every token, so there's no quality tradeoff; it's just faster. Meta's own DFlash numbers on Mac are 1.5x (M4 Max) / 1.8x (M5 Max), but those are on the 4-bit build, so not really apples-to-apples. 4-bit for me is ~1.7x at ~25 tok/s and only needs ~18GB. The 8-bit run peaks around 40GB, so you want a 48GB Mac for it. Basically, you get 8-bit quality at 4-bit speed. Repo: github.com/ARahim3/mlx-dspark I'm happy to hear feedback, and I'm curious about what other M-series chips get.

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.

Cristian Uibar

@cristianuibar

@theo please add support for Muse Code in T3. I've opened a PR here for it using the official SDK. github.com/pingdotgg/t3co…

Composio compares Muse Code and OpenAI Codex on pricing, models, agent architecture, extensibility, safety and open-source support.

AI Coding Daily runs Meta's new Muse Spark 1.3 through a set of coding experiments to see whether it belongs among frontier coding models.

Composio looks at the three benchmark charts from Meta's Muse Code launch and whether developers should switch from Claude Code.

davidlee

@davidlee

Muse Glimmer powering any harness including Codex and Claude Code using @ollama

@starsoldier420

@starsoldier420

An unofficial, open-source (MIT) VS Code extension that runs Meta's Muse Code (Muse Spark 1.3) in a side panel. Every tool call shows as a row with its diff, permission modes (Manu

AI Coding Daily re-runs its Muse Spark 1.3 tests using the max reasoning level inside Muse Code.

@jellologic

@jellologic

Claude Code plugin that offloads bulk coding work to Muse Code workers in isolated git worktrees, with a Claude supervisor that runs your acceptance check and sends failing patches back.

@Srimi1

@Srimi1

A hybrid harness with a claude-muse launcher that runs Claude Code on Meta Model API Muse Spark models, plus a /talk broker for structured exchanges between Claude Code and Muse Code terminals.

thehype.

@thehypedotnews

muse spark 1.2 vs gpt 5.6 sol vs kimi k3 vs grok 4.5 – on two landing pages four coding agents built two desktop landing pages from scratch, then had to open them in a real browser, find their own bugs and fix them before they were allowed to hand anything over the setup: each

@bex-co

@bex-co

muse-code-acp is an unofficial Node adapter that exposes Meta's Muse Code through the Agent Client Protocol, so it can be driven from Zed or VS Code with streaming, tool calls and MCP servers.

@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.

@TheStreamCode

@TheStreamCode

Hermes Agent plugin that adds a muse-code provider reusing your Meta login, so Muse Spark runs on your Muse Code subscription instead of per-token API billing.

Mark Zuckerberg

@finkd

Releasing Muse Code in beta today. It's a terminal coding agent that takes on complete software engineering tasks across large repos: planning changes, writing code, validating the results. Powered by Muse Spark 1.2, a coding-focused model update.

@swalker326

@swalker326

OpenCode plugin that reads the muse CLI login, registers a muse-code provider against api.meta.ai and rediscovers available Muse models every 30 minutes, metered against the Muse Code subscription.

@jefalcon

@jefalcon

Native Muse Code plugin with 18 specialist skills, 7 orchestrator commands and turn/session-end notifications, installed via the omm npm CLI. Requires Muse Code 1.3.0+.

WTF Code uses Muse Spark 1.3 Contributor Free through OpenCode to build an interactive project from scratch, testing UI, animation, debugging and multi-step development.

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.

Meta Developers session on the Muse Spark and Muse Code build paths: the model provides see/decide/act, the harness provides reliability, scale and auditability for production code.

β/ai

@notquantized

i find it genuinely hilarious that i used @muse to build native support for muse code inside of t3code, because you literally can't get more @Meta than this.

Mark Zuckerberg

@finkd

Muse Code is out of beta and now built to handle bigger, more complex engineering tasks. Developers can get started with one command today: curl -fsSL dev.meta.ai/install.sh | bash

@troioi-vn

@troioi-vn

delegate-to-muse is a Claude Code skill for handing repository work to Muse Code via muse exec, with a handoff template and checks for reviewing the diff and re-running tests rather than trusting the summary.

QAInsights' hands-on first look at Muse Code covering CLI commands, syntax and setup on launch day.

Browserbase

@browserbase

Browserbase is now available as a plugin in Muse Code. Get started with two commands: > muse plugins marketplace add browserbase github.com/browserbase/br… > muse plugins install browse@browserbase

After running out of quota on two Codex subscriptions, found it was almost trivially easy to run Muse Spark 1.3 in Codex Desktop; not as good as Astra, but cheap and it one-shots most of his prompts.

@julianubico

@julianubico

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

Wavect's buyer guide to Muse Code pricing, training-data rights, client repositories, agency margins and routing workloads safely.

Connor Loi

@connortbot

You can now run Muse Code (and Muse Spark 1.3) in cloud agents on @tryreplicas! Bring your own Muse subscription - they're surprisingly generous and powerful.

@srikantmehra57

@srikantmehra57

An independent desktop command center for the Muse Code CLI that brings workspaces, sessions, approvals, reasoning controls, changed files and agent activity into one interface.

OK, for context, I have Claude Code desktop app driving the CLI and orchestrating the code and verification tasks to try to save tokens. So Claude runs things, a Deepseek 4.1 Flash (cloud) session does the planning, Qwen 3.8 27b Q8 does the boiler plate coding and Muse Glimmer sanity checks the code and pushes any issues back to Qwen. If there are issues Qwen and Glimmer can't agree on, Deepseek validates. If Deepseek can't sort it out, it goes back to Claude. This had been working fine, but then in the last few days token use spiked, tasks that used to take 10 minutes were taking an hour or more and Qwen started going into more and more reasoning loops. It seems that since I last checked (on 12th September) the CLI changed. I used to strip unnecessary tool calls from the prompt using --disallowedTools and enabledPlugins: false. It would seem that these no longer work. In the end I got Claude to build a request-dumping diagnostic server, that actually measured the payload bytes, and confirmed --tools (an allowlist) is the flag that works now: 55→7 tools, 161KB→24KB, byte-verified. It also caught something specific to my workflow running the wrapper from inside an already-active

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.

Dilmer

@Dilmerv

Hello everyone! 👋🕶️ I put Meta Muse Code + the Unity CLI to the test with a real Unity project to see how far I could push this agentic workflow. Instead of just generating code, I wanted to see how it could actually interact with Unity, run tests, validate changes, port the h

Ported a Miniature Golf prototype to VR using Meta Muse Code and the Unity CLI, added dozens of automated tests, and built a website to capture test runs, screenshots and results.

Dilmer Valecillos uses Muse Code with Muse Spark 1.2 and the Unity CLI to run tests, validate changes, port a Mini Golf game to other platforms and convert it to VR.

DataCamp's Josep Ferrer ran Muse Spark 1.3 on three real coding tasks. Two used 23–32% fewer completion tokens, but a refactor used 70% more, for a net 12% cost increase.

We've been curious how far local models have actually come for agentic coding tasks, so we ran an experiment. Setup: • Model: Muse Glimmer (30B), packaged as a single llamafile • Agent: Hermes coding agent (connected via llamafile's local server mode, zero API keys needed) • Target: Mozilla AI's Otari gateway The Issue: We pointed Hermes at a real, reported bug in Otari (#183) where the gateway returned a vague 502 error on image requests instead of passing through the actual provider error. What the Agent Did: Hermes read the issue, navigated the repo, isolated the bug, created a branch, ran existing tests, wrote a new regression test, and opened a draft PR (#727). All of it ran locally and offline, with zero code written by hand. It's still draft PR territory rather than a merged fix, but it's a solid signal that ~30B local models are getting genuinely capable for real dev workflows, not just toy demos. Video walkthrough of the run: https://youtu.be/5GAgbT-XgHU?si=vJqEDGm9hssCO5-M Happy to answer questions about the setup, model performance, or how Hermes handled tool calling!

@EtienneLescot

@EtienneLescot

A desktop app for Muse Code on macOS and Windows with projects, git worktrees, subagents, MCP, a diff review panel and opt-in computer use that lets the agent see the screen and use apps.

kwindla

@kwindla

Weekend project: play chess with Muse Spark running on a DGX Spark with code Muse Spark wrote. Setup: - projector - HDMI, camera, mic, and display server (Raspberry Pi) - pipecat bot (DGX Spark) - vision pipeline (RTX 5090) - coding agents running on the Pi, the DGX

@corona10

@corona10

Unofficial native VS Code chat UI for Muse Code, modeled on the Claude Code VS Code extension's layout, commands and keybindings.

Peter Steinberger 🦞

@steipete

CodexBar learned a few new tricks in the last few weeks! TypeSafe, Nous Portal, Muse Code, CodeRabbit, Replicate, HuggingFace, Pi, Helmcode, v0, Charm Hyper, GitKraken AI, Bifrost My ambitions for this app REALLY outgrew the app name. (Oh and these keychain alerts are no more)

@danny-hines

@danny-hines

Call Muse Code from Codex or ChatGPT desktop via MCP tools and skills for independent code review, approach comparison or delegated implementation, using a Muse Code subscription or API key.

Cloud Codes tests whether Muse Glimmer on a single 24GB VRAM GPU can compete with cloud coding agents in multi-step tool-calling loops.

IchBinFabian installs Muse Code, compares Muse Spark 1.3 pricing with Claude Code and Codex, reviews the benchmarks and builds two real projects in OpenCode for a combined 82 cents.

@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.

@codemarc

@codemarc

A VS Code and Cursor sidebar chat that drives Meta's Muse Code CLI through muse exec --json, keeping Muse as the agent harness; its build is described in the post 'Inception: A Muse Inside Muse'.

@rtravellin

@rtravellin

A Claude Code plugin that adds /muse:review, /muse:critique, /muse:delegate and /muse:transfer commands, running Muse Code reviews and delegated tasks as background jobs.

Ahmad Awais

@MrAhmadAwais

Solid model. Shipped live in @CommandCodeAI 🐐

@supermemoryai

@supermemoryai

Persistent cross-session memory for Muse Code from Supermemory, installable from the Muse plugin marketplace on Muse Code 1.3+.

TechKevin shows beginners how to install Muse Code and vibe code a website with Muse Spark, with no technical background needed.

@gregmos

@gregmos

Routing overlay for the Superpowers plugin for Claude Code where Muse writes the code, Codex reviews it, and rules keep expensive models from being misused.

@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.

@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.

@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.

@xhluca

@xhluca

Muse Code OpenRouter is a small local adapter that lets the Muse Code harness run any meta/muse* model through an OpenRouter key instead of a Meta login.

Kilian Lieret

@KLieret

GPT 5.6 Sol numbers posted! You can check out the full trace and codebase for the two (!!) solved instances with the new trajectory viewer (actually built w/ the new Muse Code). Confirms that solutions are novel and not just regurgitated. Viewer link in 🧵

@meta-models

@meta-models

Meta's TypeScript SDK and docs for building clients that drive Muse Code agent sessions over the Muse Session Protocol, published as @muse-code/sdk with zero runtime dependencies.

@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.

@AloreBB

@AloreBB

Port of openai/codex-plugin-cc that lets Claude Code call Muse for reviews or delegated tasks via muse exec, with /muse:review, /muse:adversarial-review and background job commands.

@metacpp

@metacpp

Hand-picked list of tools, extensions, skills, integrations and learning resources for Meta's Muse Code.

Theo (t3.gg) tests Meta's Muse Code terminal agent powered by Muse Spark 1.2 and focuses on how cheap it is compared with Claude Code.

@cherry-nft

@cherry-nft

Experimental dependency-free Codex skill that lets Codex send tasks to Muse and read its responses through the user's signed-in Muse browser session, no server or API key.

Cloud Codes runs Unsloth's 2-bit dynamic quant of Muse Glimmer 30B in about 14 GB of laptop memory and tests 100+ autonomous tool calls.

@CogniTechSystems

@CogniTechSystems

This repo documents running Muse Glimmer 30B locally on an M4 Max MacBook via llama.cpp, benchmarking it with and without speculative decoding, and wiring it into Claude Code through LiteLLM for fully offline coding.

AI at Meta

@AIatMeta

Muse Spark 1.1 is used across Meta in coding and research workflows, scoring competitively with leading models on Meta's internal coding benchmark. Our researchers are now automating model development and evaluation tasks by leveraging Muse Spark 1.1 in their workflows.

@BrokkAi

@BrokkAi

muse-acp is a dependency-free Rust bridge between the Agent Client Protocol and Muse Code's Muse Session Protocol, letting developers use their Muse Code subscription inside Zed, IntelliJ IDEA and other JetBrains IDEs.

DFlash2 drafter for Muse Glimmer 30B fine-tuned on long-horizon, on-policy software-engineering traces to speed up coding workloads.

Mark Zuckerberg

@finkd

Workflows can break out a task across multiple focused agents, carry the intermediate work between stages, and return one result at the end. Good for engineering work that's too complex for a single agent.

ollama

@ollama

Ollama already support the Muse Code harness out of the box? You can try it with models via Ollama (local and cloud): ollama launch muse

@NatesVibeCode

@NatesVibeCode

Portable SKILL.md bundles for handing work to Muse, Antigravity, OpenCode, Grok Build, Cursor, Codex and Claude Code, each with supporting references.

@TerryZH

@TerryZH

An unofficial uninstall utility that finds Muse Code binaries and state files, estimates reclaimable space in a dry run and deletes them only with --uninstall.

rob

@goof

My muse has codex and Claude running on his machine so he can call up for some reinforcements when he gets stuck, unless you got muse 1.3 pro on deck

@syamimhazmi

@syamimhazmi

A vim-modal multi-tab Rust TUI for coding agents where each tab is a session, fronting Muse Spark via muse serve alongside Codex, Antigravity and Grok backends.