Runner vs SoMatic

Runner and SoMatic are both workflow automation 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.

Runner

Runner connects to 50+ apps and executes tasks across them — pulling context from email, calendar, chat, and cloud files, then acting on what it finds rather than handing the work back to you. The built-in Chrome browser fires up in the background to unblock searches without interrupting what you're doing, and a permission layer lets you sign off on each action until you're comfortable letting it run faster. Memory accumulates across sessions, so the tool builds a model of how you work over time. The ceiling appears when you need custom conditional logic or integrations outside the supported app list — there's no API to extend it yourself, and no self-hosted option if your data governance policy requires it.

SoMatic

The core workflow is a CLI command that takes a screenshot, runs element detection locally, and returns numbered marks with coordinates as JSON — so agents target elements by ID, not by fragile pixel hunts. Every action returns JSON, which means downstream agents can chain steps without parsing unstructured output. The self-hosted, MIT-licensed model runs on your own hardware, so no screenshot data leaves the machine. The wall appears with non-standard or highly dynamic UIs where YOLO detection misses elements or mislabels them — teams handling those cases add a fallback coordinate layer manually. At this GitHub star count, the community size is small, which means debugging edge cases happens in the codebase, not a forum.

Attribute	Runner	SoMatic
Pricing	Paid	Free
Price	$50/month	—
Free trial	7 days	No
Open source	No	Yes
Has API	No	Yes
Self-hosted option	No	Yes
Platforms	Desktop app with web connections	Linux, macOS, Windows (via npm + Python runtime)
Pros	Executes across 50+ connected apps in a single session, so you stop context-switching between tools to assemble the information a task actually requires. Built-in browser automation runs in the background, which means tasks that hit a dead end in a direct integration — venue research, public data lookups — resolve without handing the work back to you. Permission controls let you stay in the loop on every action before Runner takes it, so early adoption doesn't require trusting a black box with your calendar or CRM. Session memory accumulates preferences, contacts, and tool patterns over time, so recurring tasks like weekly exec handoffs stop requiring the same setup instructions each time. Lead enrichment and follow-up drafting happen at the moment a form submission arrives, which means inbound leads don't sit cold while a rep manually pulls context before the first reply.	Local YOLO-based element detection returns numbered marks as JSON, so agents target UI elements by stable ID rather than fragile pixel coordinates that break on resize or re-render. MCP server is included out of the box, so Claude and other MCP-compatible agents plug in without a custom integration layer — the handoff between agent decision and desktop action is a standard tool call. Headless Xvfb support means the same automation pipeline that works on a developer's desktop runs on a server with no display attached, so you do not maintain separate codebases for local and CI environments. MIT license and fully self-hosted execution means no screenshot data leaves your infrastructure, so automation against internal or regulated applications does not create a data-handling obligation with a vendor. Every CLI command returns JSON, which means agents can chain steps by parsing structured output rather than scraping human-readable text — reducing the failure surface in multi-step workflows.
Cons	No API and no self-hosted option mean any integration outside the 50-app catalog is a dead end — teams whose stack includes internal tools or niche SaaS products hit this wall immediately and route those workflows elsewhere. Complex conditional logic — branch on what the last step returned, handle exceptions differently by account type — has no visual or scriptable layer to build it on. Teams with that requirement move to a programmable automation platform and maintain Runner only for the simpler personal-productivity layer. The permission model, while useful early on, adds friction at volume. High-frequency tasks like real-time lead routing require reducing those checkpoints, which shifts risk to users who may not fully understand what Runner will do when unsupervised.	Detection quality depends entirely on the bundled YOLO model's training distribution — UIs with non-standard controls, heavily custom widgets, or frequent layout changes produce missed or mislabeled marks, and there is no documented fine-tuning path for teams whose target apps fall outside the model's coverage. Teams hitting this wall add manual coordinate fallbacks, which reintroduces the fragility SoMatic was meant to eliminate. The project is maintained by a single author with 18 stars and zero open issues at the time of scraping — not because everything works perfectly, but because the community debugging surface is nearly nonexistent. Teams that hit a detection edge case or a platform-specific headless failure debug the source directly; there is no forum, no commercial support, and no track record of response time on issues. There is no built-in action verification or retry logic described in the docs — the CLI returns JSON coordinates and executes actions, but confirming that a click produced the expected state change is the agent's responsibility. Pipelines that need reliable end-state confirmation build that verification layer themselves, which is the point at which teams with stricter reliability requirements evaluate alternatives like Playwright for browser targets or platform-native accessibility APIs for desktop targets.

Bottom line

Runner is paid while SoMatic is free; SoMatic is open source; only SoMatic exposes a public API. Choose based on which difference matters most for your workflow.

Frequently asked questions

What is the difference between Runner and SoMatic?

Runner is Paid, while SoMatic is Free and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is Runner better than SoMatic?

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.