Get This Tool
Hearth
Pricing
- Model
- Free
Summary
Most desktop automation tools require your activity to leave the machine — your files, your commands, your context all routed through someone else's cloud before anything happens. Hearth is the answer to that: a fully local AI agent that controls your computer directly, with no account, no telemetry, and no cloud dependency.
Hearth runs on your own hardware and handles the tasks that usually demand a SaaS subscription: opening applications, reading and writing files, driving a real browser you can watch, and carrying memory of past sessions — all without a single request leaving your network. The MIT license means you can fork it, extend it, and ship modified versions without legal friction. That said, the GitHub repo shows 9 stars and 297 commits from a single-org project, which signals early-stage software rather than a hardened production runtime. Windows is the primary target; Linux and macOS support is not confirmed by the page. Teams that need cross-platform deployment or enterprise support will hit the ceiling fast.
Bottom line: Pick Hearth if you need a fully local, auditable AI that controls a Windows desktop without routing data offsite — but plan for significant self-maintenance work the moment you need cross-platform support or multi-machine deployment.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Fully local execution with no telemetry or account requirement, which means sensitive file operations and internal automation never leave the machine — eliminating the data-residency risk that blocks cloud tools in regulated environments.
- MIT license with a self-hosted architecture, so you can fork, modify, and redistribute without licensing negotiation — the thing that stops most teams from customizing a SaaS automation tool at all.
- Voice and natural-language input connected directly to OS-level actions, so non-technical users can run repetitive file and app tasks without writing scripts or maintaining a workflow canvas.
- Reusable, installable 'skills' that the community can share, which means automation one developer builds for cleaning a downloads folder can be packaged and reused by anyone on the same stack — no rebuild from scratch.
- A visible, watchable browser session rather than headless automation, so you can audit exactly what the agent is doing in real time instead of debugging a black-box scraper after it goes wrong.
Cons
Sign in to edit- The project targets Windows explicitly; the page does not confirm Linux or macOS support. Teams running mixed-OS environments or deploying to Linux servers cannot use Hearth without forking the codebase and porting the OS-control layer themselves — at which point they are maintaining their own tool, not adopting one.
- At single-digit GitHub stars and a single-org contributor base, there is no meaningful community to surface bugs, maintain compatibility with OS updates, or keep pace with new local model releases. When a Windows update breaks the file-control layer, the fix timeline depends entirely on one maintainer.
- There is no multi-user, logging, or audit-trail architecture described anywhere in the repo. Teams that need to demonstrate who ran what automation and when — for compliance, for incident review, or for shared-machine safety — will find nothing here and will move to a tool like Open Interpreter paired with structured logging, or a managed RPA platform, before the first audit request arrives.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Windows (primary); macOS/Linux from source
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-07-19T08:15:57.516Z
Best For
Who it's for
- Users wanting a fully local computer-controlling AI
- Windows users seeking agentic automation without cloud
What it does well
- Automate desktop workflows like cleaning downloads folders
- Control browser and apps via natural language
- Voice-driven file and application management
- Share and install reusable skills for repetitive tasks
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Hearth
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Hearth free?
- Yes — Hearth is fully free to use. There is no paid tier.
- Is Hearth open source?
- Yes. Hearth is open source.
- Can I self-host Hearth?
- Yes. Hearth supports self-hosting on your own infrastructure.
- What platforms does Hearth support?
- Hearth is available on: Windows (primary); macOS/Linux from source.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Cloud dependency is the unspoken cost of most AI automation tools — your data leaves, your costs scale with API calls, and your privacy policy gets longer. Hearth flips that: the vendor describes it as ‘the local AI that actually runs your computer,’ handling file management, app control, browser automation, and voice commands entirely on the user’s own machine. The core workflow is natural-language or voice instruction → local model inference → direct OS action, with no external API call required for the control layer.
The differentiating feature is full local memory combined with real browser control. The docs describe a browser you can watch execute — not a headless scraper, but a visible, controllable session — paired with session memory that persists context between interactions. For a privacy-sensitive workflow like managing a legal downloads folder or automating internal tooling on an air-gapped machine, that combination is the architecture most cloud tools cannot match.
Hearth fits individual power users and developers building shareable ‘skills’ — reusable automation scripts the community can install. It does not fit teams that need centralized logging, role-based access, audit trails, or multi-user orchestration. The repo shows no issues open and no pull requests, which means either the codebase is clean or the community is too small to surface bugs at scale — at this star count, assume the latter. Teams running production workflows across more than one machine will find themselves maintaining a fork rather than a product.
The project ships with both a CLI launcher and a tray/window GUI, a PowerShell installer, and a build pipeline for packaged releases. The MIT license and CONTRIBUTING.md indicate the project is structured for outside contribution, but community adoption is early-stage by any measurable signal on the repository.