Open-source & free agent CLIs, one canvas
Bring the coding agents you already use. VibeFuse is the free desktop layer that keeps them arranged with terminals and browsers — ideal if you want high capability without paying for yet another IDE seat.
Join Fuse Intelligence — manage subscriptions & downloads
Already registered?
By registering you agree to our Terms and Privacy Policy.
VocalFuse is a Fuse Intelligence product.
FREE AI AGENT HARNESS · v0.1.23
The free Windows desktop harness for Windows 10+: spawn Terminal, Browser, YouTube, Files, Vibe Agent chat,
and Claude Code, Codex, Gemini, Cursor, or Qwen as draggable canvas widgets — with Jarvis wake word, local Whisper STT,
Piper TTS, MCP tools, HyperFrames video, Skill Seekers, named sessions, nine themes, and a marketplace where you can sell skills. $0 forever with your complimentary VF- license.
Latest release v0.1.23 · Windows x64 · Free forever · No harness subscription
Register once — a complimentary VF- key is written to your profile. No checkout, no monthly fee for the harness.
Claude Code, Codex CLI, Gemini CLI, Cursor CLI, and Qwen run as live widgets — serious AI coding agents, not a toy chat box.
Free local voice transcription and text-to-speech for hands-busy harness sessions.
Bring the coding agents you already use. VibeFuse is the free desktop layer that keeps them arranged with terminals and browsers — ideal if you want high capability without paying for yet another IDE seat.
Browse fuseintelligence.org/marketplace, save to your library, and widgets sync into the canvas on launch. Publish from Settings → Marketplace with manifest.json + index.html.
Compare approaches across Claude and Codex in parallel, keep a terminal watching tests, and leave a browser on docs — that is modern AI coding agent desktop work.
One Fuse Intelligence login covers free VibeFuse and paid VocalFuse when you need system-wide dictation outside the canvas.
PowerShell with session restore beside a Files explorer that previews images, video, audio, and PDFs from your workspace folder.
Embedded Chromium for docs and research; bookmark pages as chromeless widgets. Marketplace iframe widgets load via widget://.
A tool-using chat assistant plus Claude Code, Codex, Gemini, Cursor, and Qwen — run multi-agent side-by-side on one canvas.
Main process owns PTYs, voice engines, and MCP in C:\vibefuse\; the React renderer is your widget canvas with twelve-tab Settings. Details in VibeFuse docs → Architecture.
Yes. Every Fuse Intelligence account gets a complimentary VF- license at no charge. There is no checkout and no monthly fee for VibeFuse. Create a free account, copy your key from Account → Product Keys, and install from /downloads/VibeFuse/.
VibeFuse is a high-capability Windows AI agent harness: Terminal (PowerShell), Browser, YouTube, Files explorer, a Vibe Agent chat assistant that can create and edit Agent Skills, AI coding agent widgets for Claude Code, Codex CLI, Gemini CLI, Cursor CLI, and Qwen, Google Workspace and Drive MCP connections, and a live marketplace for community widgets and SKILL.md packages.
Yes. Hold the title-bar voice dock to record. Speech is transcribed locally on your PC with whisper.cpp for free — useful for dictating prompts into AI coding agents without cloud audio uploads.
Yes. Enable the Jarvis wake word in Settings → Voice and say “Jarvis”. VibeFuse plays a short “Yes, sir?” acknowledgement, then records your command. Local Whisper and Piper keep the whole loop on your PC.
Switch the voice dock to Note-Taking, click the orb to record, and click again to stop. VibeFuse transcribes the take locally, summarizes it into bullet points with a title, and uploads it to your profile — review notes at Account → Notes or in Settings → Notes.
Yes. Jarvis (voice) and the Vibe Agent chat widget can spawn, tile, resize, rename, focus, and remove widgets on command — for example “Jarvis, open three terminals and tile them.” Layouts use tile/fill/row/column arrange modes or exact x/y/w/h coordinates.
Yes. Replies are spoken by Piper with the Jarvis voice, running on-device. With an OpenAI-compatible chat provider configured, the voice assistant speaks a short reply line — free local TTS for developer workflows, not a cloud TTS subscription.
VibeFuse is a free Fuse Intelligence product that wraps and runs popular open-source and vendor AI coding CLIs (Claude Code, Codex, Gemini, Cursor, Qwen) in one desktop canvas. Agent CLIs remain theirs; VibeFuse is the free harness, marketplace, voice, and session layer.
Register for free, copy your VF- key from Account → Product Keys, download VibeFuseInstaller.exe from /downloads/VibeFuse/, paste the key in Setup, and launch. The installer fetches the app and missing local voice models before first run.
Browse fuseintelligence.org/marketplace — save widgets and Agent Skills to your library while signed in. Widgets sync into C:\vibefuse\widgets and skills into C:\vibefuse\skills on next launch.
Build a folder with manifest.json and index.html, open Settings → Marketplace in the desktop app, and publish the folder. Your listings appear publicly on fuseintelligence.org/marketplace, and you can unpublish or republish any time.
Agent Skills are Claude/Codex-compatible SKILL.md folders in C:\vibefuse\skills. They appear in the left-rail Skills section. Save them from the marketplace, drop a folder on disk, or ask Vibe Agent to create_skill / update_skill. Any connected provider agent can read the same files.
Yes. Vibe Agent (and Jarvis) can list_skills, create_skill, update_skill, delete_skill, execute_skill, read_skill, and read_skill_file. The Skills rail and Settings → Skills refresh as soon as a skill is written.
Open Settings → Tools. Use the Google Workspace card (Gmail, Drive, Calendar, Docs, Sheets, Tasks, Slides, Meet, Contacts) or the Google Drive card (read-only Drive). Sign in with Google once — both cards share the same OAuth account — then Connect. Enable Workspace APIs in Google Cloud if tool calls fail.
Settings → Agent includes OpenAI, Ollama (Local), Ollama Cloud, NVIDIA NIM, Featherless, Google Gemini, Groq, Together AI, OpenRouter, Plugsky, and Custom OpenAI-compatible endpoints. Each card keeps its own API key, endpoint, and model.
The fourteenth Settings tab: Piper endpoint/voice/speed/volume, Whisper endpoint and ggml model picker, HyperFrames Studio start/stop, Skill Seekers Connect, and Crawl4AI + SearXNG endpoints.
Yes. Finish Stripe Connect, set a price on Account → Marketplace, and publish. Sellers keep 80%. Buyers get the package in C:\vibefuse\skills or \widgets.
A local HTML-to-video studio on port 4567. Vibe Agent can compose a video about your workspace folder, render an MP4 to C:\vibefuse\hyperframes\renders, and spawn a Video widget.
A local Python MCP cloned to C:\vibefuse\Skill_Seekers. It searches docs-to-skill presets (React, Godot, Blender, Claude Code, Unity, and more) before you create a duplicate skill. No API key.