Skip to content
UsecaseBoard
← All use cases
gitlabMeta-Muse

Muse Jailbreak: let Meta Muse drive your local Chrome session

Show HN / GitLab pablosanzo/musejailbreak: independent macOS menu-bar bridge (not affiliated with Meta) that tunnels a dedicated local Chrome to Muse so the personal agent can see the screen and click/type on sites where you are already logged in. Cloudflare Quick Tunnel with AES-256-GCM E2E (fallback sish); share URL+token with Muse after toggle-on. Explicit risk warning: real browser control including purchases—use only with trusted agents and never unattended on sensitive accounts.

Save ideas in this browser. Upvotes count across the board.

Prompt excerpt

Install Muse Jailbreak, turn on the tunnel, paste URL+token into Muse, then ask Muse to complete a logged-in web task in the dedicated Chrome—review every sensitive step.
Explore all →
docsMeta-Muse

metacua: Muse Spark operates a real Mac via native GUI computer-use

Meta’s official macOS cookbook ships metacua—a hackable CLI where Muse Spark captures the screen, calls computer tools with normalized 0–1000 coordinates, and executes native mouse/keyboard events until `computer.stop`. Distinct from community Muse Jailbreak (Chrome tunnel): this is Model API + local GUI loop. Warning: real Mac control; prefer a VM/dedicated user; leave `--allow-bash` off unless isolated.

Meta MuseMuse Sparkmetacua
Source ↗
blogMeta-Muse

Meta Muse Wonder: frontier model for personal and professional agents

Meta AI Research (Oct 12) ships Muse Wonder and Muse Wonder Full for long agent workflows: Active Memory carries user context across sessions; Active Focus stays on goals with check-ins before high-impact actions; demos cover browser/app work (run planning, custom gifts, seating charts) plus frontier coding. Available via Meta Model API and Muse Code (Wonder Full for Muse Code subscribers); will power Muse experiences for subscribers first. Soft-dupes Muse Spark Open already on-site—this card is the Wonder series agent release.

Muse WonderMuse Wonder FullMuse+2
Source ↗
githubagent-debugging

Agentfork: fork an LLM agent mid-run and sweep the broken step

Show HN (Oct 17): agentfork records every LLM and tool call, then lets you fork a failed run at any step and sweep prompts, models, or tool results with pass rates instead of anecdotes. Earlier steps replay from a local cache so you only pay for the step under test; OpenAI/Anthropic wrappers plus LangGraph support. Headline demo: a refund agent that reads cents as dollars keeps failing on bigger models until one system-prompt line fixes it (3/3 pass). pip install agentfork-cli; traces stay on-disk in .agentfork/traces.db.

agentforkOpenAIAnthropic+1
Source ↗
docsMeta-Muse

Muse Code /migrate: import Claude Code and Codex skills into Muse

Muse Code can load skills from built-in, user, project, and plugin sources, and discovers `~/.claude/skills` and Codex skill roots by default. The bundled `/migrate` skill imports Claude Code or Codex memory notes and MCP servers; `muse skills import --from claude|codex` brings skills across. Built-ins include `/plan`, `/grill` (stress-test a plan into a written scope contract), `/taste`, and `/threejs`.

Muse CodeMeta MuseClaude Code+1
Source ↗