Fimo
Build

Build custom agents.

Describe what it should do and pick when it runs. Fimo brings the skills, writes the agent as code in your repo, and deploys it next to your website.

Under the hood

Technical by design.

Fimo brings the skills, the agent is plain code, and it runs deployed beside your website.

We ship the skills

Deploying, editing content and schema, SEO, translations, media generation. Fimo ships the skills agents load on demand, so your brief stays a few lines of plain language.

Agents are code

An agent is a folder of plain files: GOAL.md, SOUL.md, config.yaml. Versioned, diffed, and reviewed like the rest of your codebase. No black box.

Deployed next to your website

Agents run alongside your deployed site with access to its code, content, and assets. They act on schedules and events, not in a chat window.

Your workflow

They live in your repo.

your-repo
agents/
seo/
GOAL.mdREQUIRED
SOUL.mdOPTIONAL
capabilities.yamlOPTIONAL
config.yamlOPTIONAL
skills/BUILT-IN
scripts/OPTIONAL
references/OPTIONAL
assets/OPTIONAL
plugins/DEFERRED
.envGITIGNORED

In your repo

An agent is just a folder of plain files, committed next to your site. Versioned with your code, reviewed in pull requests, and improved by anyone who pulls the repo.

Reviewed by anyone

Every change is a pull request your team can approve: devs, editors, PMs. Auto-merge the low-risk stuff, gate the rest.

Any AI

Author with Claude Code, Codex, Cursor, or whatever your team runs. Fimo is attached to your site, not a coding tool.

Superpowers

Enhanced context. Real actions.

Every agent runs in an isolated environment with full read and write access to everything that makes your site. If you can describe it, an agent can run it.

Generate reportsPropose changesCreate new pagesOptimize LighthouseTranslate releasesRefresh screenshotsGenerate reportsPropose changesCreate new pagesOptimize LighthouseTranslate releasesRefresh screenshots
Archive unused assetsA/B test headlinesFix broken linksAnything you can describeAudit accessibilityDraft changelogsSummarize analyticsArchive unused assetsA/B test headlinesFix broken linksAnything you can describeAudit accessibilityDraft changelogsSummarize analytics
Localize landing pagesTrack keyword rankingsTag new productsCompress hero videosDraft the newsletterSyndicate the blogLocalize landing pagesTrack keyword rankingsTag new productsCompress hero videosDraft the newsletterSyndicate the blog
Full read and write onCodebaseDatabaseContentAssetsRuns history
FAQ

Questions about agents.

Coding agents (Claude Code, Codex, Cursor) help your developers write code. Fimo agents run on your deployed site. They translate, audit, validate, and ship for the whole team.
Skills are the capabilities Fimo ships with every site: deploying, editing content and schema, SEO, translations, media generation. Agents load them on demand, so a few lines of brief are enough to get real work done.
Deployed next to your website. Each run gets an isolated environment with access to the site code, content, and assets, does its work, and ships the result as a pull request.
No. Anyone can describe an agent in plain language and pick when it runs. Your developers wire up anything custom, and anyone with review permission approves the work.
Agents work against your production environment, but every change they propose happens in a new isolated environment for review.
Yes. Daily, weekly, on every deploy, when content is published, or only when you ask. Whatever cadence fits.
Every change is a proposal you can review and reject. Low-risk changes (alt-text, translations) can auto-merge based on rules you set. Higher-risk changes always need a human.
No. Whether they use Cursor, Codex, Claude Code, or anything else, Fimo agents work the same. They're attached to your site, not to a coding tool.
By environment-hours. Free includes a small allowance; Pro and Business include more, then $0.10/env-hour beyond that.
Keep exploring

Where to next.

Start building.

Join 2,000+ teams shipping autonomous websites with Fimo.