Entries matching “auth”

Meta's engineering write-up on Muse security: isolated VMs, a separate Sentinel permission authority, credential surrogation and layered prompt-injection defenses, with bug bounties up to $300,000.

@AshutoshKD

@AshutoshKD

An Express-based Muse connector that books Uber rides from natural language, with routes for fare estimates and ride requests, connector auth middleware and a privacy page.

@TheStreamCode

@TheStreamCode

opencode plugin that bills Muse Spark usage to a Muse Code monthly subscription through a Meta device-code login instead of a pay-as-you-go API key.

@Nomadiction8991

@Nomadiction8991

Portuguese-language repository of versioned agent skills for OpenCode and Muse, each a lean SKILL.md with references and templates (ticketing, conventional commits, skill authoring, frontend design).

@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.

@sureshsankaran

@sureshsankaran

A Muse workspace skill that manages a Tailscale tailnet from chat, listing devices and generating auth keys, with the API token held in the Muse vault and attached via a runtime surrogate.

@stricker67-ai

@stricker67-ai

Provider config that lets OpenClaw use Muse Spark models authenticated by Muse Code's browser login instead of a Meta Model API key, no plugin or patched build needed.

@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.

@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.

@m5it

@m5it

A four-in-line game built with the AIIA framework, where the plan came from the author's own model and the build then switched to Muse Glimmer running on 16 GB of VRAM.

@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.

@alpharomercoma

@alpharomercoma

A reproducible setup serving Muse Glimmer 30B on one AMD MI300X with a custom 11 GB vLLM 0.28.0 ROCm image, exposed as an authenticated OpenAI-compatible endpoint and driven from the pi CLI.

My creation

Guys, I've been programming in Vibe, using Gemini 3.8 Flash in Antigravity, basically creating consciousness and intelligence, primarily using Jev, with Muse Spark 1.3 to do a Minecraft speedrun, but with creativity. And I have two instances: one is the director, the cinema, the cameraman, and the other is Andy, this character who has the life dice. And, guys, I'm surprised by the result, because they really seem to create a personality while playing. He experiences things. I had an episode where he died and became depressed, and I configured him to come back and pick up the items. And basically, with the physics and everything involving the game and Jev, this allows for practically human gameplay. And you'll be posting on my channel, the link is below, how this journey went. But I'm very happy with the AI's capabilities and Jev's revolutionary ability to make decisions. And the result was impressive. https://www.youtube.com/@supersuperinteligencia https://preview.redd.it/8qsmj95bxirh1.png?width=2560&format=png&auto=webp&s=332e69d6d5964cf8d30a866fb490376db405597a

Its a beginning. Not 100% accurate, use with caution. Will try to update it as soon as it can.

@rafaelnovaes22

@rafaelnovaes22

A hybrid FastAPI gateway where a 1-bit BitNet layer on CPU filters routine traffic and Muse Spark 1.3 is called only for sales, urgency, money or low-confidence cases; the author estimates the local filter handles about 60-70% of volume.

I made a 400 page pdf html docs words txt from 400 Google docs any ai/agent app can't make it I Tried

CellCog explains the Muse connector platform: a three-step describe/review/list flow at muse.ai/platform, directory vs custom connectors, and Stripe Link payments.

Malwarebytes reports Patrick Wardle's finding that a local app can change an undocumented Muse setting to redirect dictation traffic, exposing voice prompts and account auth tokens.

@obaid

@obaid

Agent plugin and stdio MCP server for Resemble AI media authenticity that works with Muse: run investigations on public URLs, submit deepfake detect jobs and ask follow-ups on reports.

@Pascapone

@Pascapone

DeepSeek Harness bundle that exposes an authenticated Muse Code CLI as a one-shot subagent_muse tool running muse exec --json in the parent workspace.

@AshutoshKD

@AshutoshKD

A Muse connector powered by TMDB that exposes search, trending, now-playing, upcoming and top-rated movies, TV shows and people lookups behind connector auth.

Chandra Bhavanasi ⛷

@chanduiiit

Started using @Muse a few days ago and yesterday I asked it to negotiate my ATT fiber bill. I pay $80/m and authorized it to take any offer less than $70/m. It negotiated $40/m and 3mo free. #muse is nothing short of amazing! Great job @alexandr_wang @finkd

@Anil-matcha

@Anil-matcha

A community catalog of Meta Muse integrations and 150 connector skills with capability, authentication and permission notes, plus workflow templates for using Muse with connectors.

@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.

@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.

@dangkhoa2016

@dangkhoa2016

A self-hosted llama.cpp serving stack that runs Muse-Glimmer-30B GGUF with DFlash2 speculative decoding on Kaggle's NVIDIA T4 x2, exposed through an authenticated OpenAI-compatible gateway.

@bertybirdbot

@bertybirdbot

A reusable skill pattern for connecting a Muse agent directly to site APIs instead of driving a browser: a vaulted credential, a surrogate-auth helper and a tiny CLI per service.

@EclipseAditya

@EclipseAditya

Pi coding agent extension that adds Muse Spark 1.2, 1.2-contributor and 1.1 via the Meta Model API, a maintained fork that fixes a false auth warning on pi v0.84+.

@murpheycandler

@murpheycandler

A small Inspect evaluation on Muse Glimmer that tests whether incentive framing changes what an agent reports to its principal when the evidence is held constant; the author reports a null result.

@evangit2

@evangit2

A guide and tooling for pointing Muse Code's meta provider at any OpenAI-compatible gateway with API-key auth and no Meta login, including workarounds for 1.0.1's bearer-withholding change.

Nadia Dubois walks through API key setup, auth, tool-calling config and cost control for Muse Spark 1.3 at $1.25/M input and $4.25/M output tokens.

@dkm90x

@dkm90x

Muse Mac Connector is an open-source macOS menu-bar app that exposes an authenticated tool set over a Cloudflare tunnel so Meta Muse can take user-approved actions on files and apps on the user's Mac.

@BlockedPath

@BlockedPath

Meta Model API OAuth for the pi coding agent. It routes Muse Spark through the openai-responses provider, since the author notes the Muse prompt cache hits about 0% on /chat/completions, and sends 24h prompt-cache retention.

A 4-byte GGUF header edit that raises Muse Glimmer 30B's 131,072 context limit to 262K. The author shows YaRN scaling only adds prefill cost on this architecture, and verified 262K with 8 slots on one RTX 4090.

@alexanderradahl

@alexanderradahl

A fork of Spotify's shunt plugin for Claude Code and Codex whose hooks block full reads of large files and route them to Muse Spark via muse exec; the author measured about 4,800 tokens out and 300 back on a 617-line file.

Iam_

@SPAC89

Try planning with Muse Spark 1.3 Max and then executing with Muse Spark 1.3 xHigh Contributor agents, It cuts costs by more than 90% while still giving you frontier model quality. Honestly, Muse Spark 1.3 Max is one of the best models on the market right now. Everything you see

MindStudio notes Muse Spark 1.3 topped DeepSWE at 75.4 and placed third on Artificial Analysis, yet in a hands-on game-clone test produced "a cube shooting at other cubes."