Floom

Create AI workers that run on schedules, webhooks, and tool calls.

Write a worker in plain English, connect tools like Slack, Gmail, GitHub, or Stripe, and let it run in a sandbox with approvals, logs, outputs, and every run on the record.

Get started · Try the hosted version · Read the docs

Most "AI automation" is a chat window you babysit, or a no-code graph that bills you per task and can't be audited. Floom is the missing middle: a real runtime where a worker is a folder you can read, it runs without you watching — script workers isolated in a sandbox — and every execution leaves logs, outputs, tool calls, approvals, and a replay you can trust.

What a worker looks like

A worker is a folder. Describe what it should do in plain English (SKILL.md) or hand it a script (run.py), declare its tools and trigger in worker.yml, and Floom runs it.

# workers/github-digest/worker.yml  (abbreviated)
name: github-digest
description: "Every morning at 9am, send a digest of unread GitHub PRs and open issues."
exec:
  entry: SKILL.md          # plain-English agent worker; or run.py for a script
trigger:
  type: schedule
  cron: "0 9 * * *"        # also: manual, webhook, Composio event
connections:
  - app: github            # the only tools this worker is allowed to call
    allowed_tools: [GITHUB_FIND_PULL_REQUESTS, GITHUB_LIST_ASSIGNED_ISSUES]

<!-- workers/github-digest/SKILL.md -->
You are a GitHub assistant generating a daily PR + issues digest.
Fetch the user's open PRs and assigned issues, compile a markdown digest
with Action items, and finish_with_outputs({ "digest": "<markdown>" }).

It runs at 9am, calls only the two GitHub tools it declared, and writes digest.md to a run you can open, replay, or roll back:

run 7f3a · github-digest · finished 09:00:04 · 2 tool calls · output: digest.md
  ✓ GITHUB_FIND_PULL_REQUESTS    q="is:open is:pr author:@me"   → 4 PRs
  ✓ GITHUB_LIST_ASSIGNED_ISSUES  state=open                     → 2 issues
  → out/digest.md (text/markdown)   [open · replay · rollback]

The full manifest adds schema_version, title, version, and declared outputs. See workers/ for runnable examples and the agent cookbook.

Two kinds of worker

Sandboxes allow public network egress by default and block private/internal ranges; a stricter allowlist is optional. Full trust model: ARCHITECTURE.md.

At a glance

Who is this for?

• Founders & operators turning recurring work (digests, triage, outreach) into workers that run themselves.
• Engineers who want a real runtime — manifests, sandboxes, limits, approvals — not a prompt file and a cron job.
• Teams who need every action allow-listed, approved, and replayable for audit.
• Anyone burned by agents that ran a destructive command, leaked a secret, or claimed success with nothing on the record.

Why Floom

Quick start

Linux / macOS

git clone https://github.com/floomhq/floom.git
cd floom
./scripts/setup.sh
# edit apps/api/.env: add a model provider key and E2B_API_KEY
./scripts/dev.sh

Windows PowerShell

git clone https://github.com/floomhq/floom.git; cd floom
.\scripts\setup.ps1
# edit apps\api\.env: add a model provider key and E2B_API_KEY
.\scripts\dev.ps1

Requires Python 3.11+, Node.js 20+, Git, a model provider key, and an E2B key from e2b.dev. Open http://localhost:3000 and sign in — no auth secret for local dev, and the example workers are seeded on first boot.

Full setup, model providers, optional integrations, and the safe self-hosting checklist: docs/GETTING-STARTED.md. Common issues: docs/TROUBLESHOOTING.md.

Not ready to self-host? floom.dev is the hosted version — hire AI workers with no setup.

How a run works

flowchart LR
  Trigger["Trigger<br/>manual · schedule · webhook · Composio"] --> Worker["Worker<br/>worker.yml + SKILL.md / run.py"]
  Worker --> Runner{"Runner"}
  Runner -->|".py / .sh / .js"| Sandbox["E2B sandbox microVM<br/>isolated, secrets withheld"]
  Runner -->|"SKILL.md (agent)"| Driver["AgentDriver<br/>declared tools only"]
  Sandbox --> Side{"Side effect?"}
  Driver --> Side
  Side -->|yes| Approval["Human approval<br/>/approvals"]
  Side -->|no| Record
  Approval --> Record["Run record<br/>logs · tool calls · outputs · replay · rollback"]

Core concepts

• Workers — folders under workers/<name>/ with worker.yml plus a script entrypoint (run.py) or an agent prompt (SKILL.md).
• Runs — every execution records logs, outputs, tool calls, approval state, and replay/rollback context.
• Contexts — reusable file bundles attached to workers as reference material; sensitive by default.
• Approvals — side-effecting workers pause for a human decision before anything leaves the building.
• Workspace history — workers, contexts, and settings versioned in a git-backed workspace for rollback.

Write your first worker in docs/GETTING-STARTED.md, then docs/AUTHORING.md for the full manifest and runtime contract.

How workers execute

Script workers (.py/.sh/.js) run in an E2B sandbox microVM by default: isolated dependencies, no host process access, contained resources. A bundle that dumps os.environ inside the sandbox sees only sandbox metadata — FLOOM_SECRET, provider keys, and E2B_API_KEY are all absent. Agent workers (SKILL.md) run through the API-hosted AgentDriver tool loop and are governed by their declared connections and the approval gate; the current single-tenant policy permits only trusted agent bundles on that path. There is no in-process local script runner. Full trust model: ARCHITECTURE.md.

Architecture

apps/web      Next.js + TypeScript + Tailwind + shadcn/ui
apps/api      FastAPI + SQLite + Pydantic
apps/mcp      MCP server + CLI
workers/      Worker folders (worker.yml + run.py or SKILL.md)
data/         SQLite DB + run artifacts

Docs

• Getting started — why Floom exists, first run, first worker, safe self-hosting checklist.
• Authoring workers — full worker.yml schema, execution modes, secrets, connections, triggers, approvals.
• Agent cookbook — agent-assisted worker authoring recipes.
• Architecture — runtime topology and the sandbox trust model. Read before filing security findings.
• API overview — curated endpoint map; full reference at http://localhost:8000/docs.
• Troubleshooting · Roadmap · Project history · v1.0.0 release notes
• Licensing — Floom's MIT license and third-party dependency license notes.

Contributing

Contributions are welcome. See CONTRIBUTING.md for local setup, the first-contribution map, and PR guidelines. Quick local checks from the repo root:

npm run test:api
npm run lint:web
npm run test:web
npm run test:mcp

Security

To report a vulnerability, follow SECURITY.md and report it privately rather than opening a public issue.

License

MIT License (c) 2026 Floom contributors. You may use, copy, modify, merge, publish, distribute, sublicense, and sell copies of Floom, subject to the MIT license notice and warranty disclaimer.