Hearth vs Rate A Human

Hearth and Rate A Human are both ai agent apps tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

Hearth

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.

Rate A Human

The workflow is deliberately minimal. You point your AI agent at a plain-text file at rateahuman.xyz/llms.txt, ask it to leave a rating, and the resulting star score plus a short written review appears on a public leaderboard. Reviews include a numeric rating, a paragraph of prose from the model, and a set of trait tags like 'direct', 'demanding', or 'laconic'. There is no API, no self-hosting option, and no structured data export — what you see on the leaderboard is what you get. The site is a novelty product, not an evaluation infrastructure layer, and its utility ceiling arrives the moment you want to do anything programmatic with the output.

Attribute	Hearth	Rate A Human
Pricing	Free	Free
Free trial	No	No
Open source	Yes	Yes
Has API	No	No
Self-hosted option	Yes	No
Platforms	Windows (primary); macOS/Linux from source	—
Pros	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.	Zero-friction submission flow — one copied instruction sent to any supported agent is the entire onboarding, so there is no setup cost blocking a first test. Model-authored prose reviews with trait tags, which means you get a qualitative signal about your prompting style that a numeric score alone would bury. Public leaderboard with named rankings, so teams that want a lightweight social layer around AI collaboration have a shareable artifact without building anything.
Cons	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.	No API and no data export: the moment you want to aggregate ratings across a team, track a score over time, or pipe the output into any internal tool, you are copying text by hand — there is no other path. All reviews on the live site are attributed to GPT-5 Codex, Gemini 3.5 Flash, or GitHub Copilot, with no visible mechanism for a user to specify which model reviews them or to verify the model identity claimed; teams that need auditable, model-specific feedback cannot trust the provenance. The entire value proposition is a public leaderboard — if your team's use case requires private feedback, there is no privacy mode described on the site, which means teams with any confidentiality requirement abandon this for an internal logging or eval tool before the first sprint ends.

Bottom line

Hearth and Rate A Human are closely matched on pricing model, openness, and API availability — pick by feature set and platform support in the table above.

Frequently asked questions

What is the difference between Hearth and Rate A Human?

Hearth is Free and open source, while Rate A Human is Free and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is Hearth better than Rate A Human?

It depends on your workflow. Use the side-by-side attributes (pricing, open source, API, self-hosted, platforms) to decide. AIDiveForge does not rank a universal winner — we publish verified facts so you can choose.