v0.3 · open-core + private intelligence · local-first

flowd
Some file work needs you.
A lot of it doesn’t.

The open-core engine watches repeated local file workflows and suggests automations you approve. Private Intelligence decides which suggestions surface, when, and how they’re worded — so the CLI stays quiet and useful. Still on your machine.

$ intelligence install open-core ⚠ v0.3 pre-release
product private intelligence open workflow engine safe allowlist · dry-run · undo local no cloud capture
flowctl — zsh

Open-core engine · Private Intelligence for decision quality · local SQLite · allowlist · dry-run · undo

private intelligence

The engine can be open. Decision quality is the product — ranking, timing, suppression, and wording that keep suggestions worth reading.

open core · flowd

Workflow engine

Capture, patterns, baseline suggestions, approve, dry-run, run, undo, and path allowlist. MIT, inspectable, useful alone.

  • Owns facts and actions
  • Deterministic baseline suggestions
  • No account, no capture sync
product layer · flowd-intelligence

Decision quality

Decides which suggestions surface, when they appear, and how they’re labeled — from your local feedback history.

  • Ranking & personalization
  • Timing, cooldowns, daily cap
  • Clustering & clearer wording

Private ≠ cloud. Intelligence evaluates locally. Turn it off and open-core still works. That boundary is the business model: infrastructure open, decision quality as the product.

what it changes in the CLI

With intelligence on, flowctl suggestions shows fewer low-value items, better order, and stable reason codes via suggestions --explain (e.g. timing.too_new, suppression.cooldown_after_reject).

what it never does

It does not invent filesystem facts, skip approval, run automations, or ship your capture data to a remote brain.

how to enable

Build with --features intelligence, set intelligence_enabled = true, and install a local license at ~/.config/flowd/intelligence.license.toml (or FLOWD_INTELLIGENCE_DEV=1 for development). Docs: Private Intelligence.

pricing

Open-core stays free. Private Intelligence is the product layer — still local, unlocked with a license file.

open core · mit

Free

Observe, baseline suggestions, approve → dry-run → run → undo, path allowlist, audit trail.

  • No account
  • No license file
  • Install
eval · time-boxed

Eval

Try Private Intelligence on your machine with an evaluation license.

  • Ranking / timing / suppress
  • Explain reason codes
  • Request eval
pro · individual

Pro

Quieter CLI for daily use — decision quality as the product.

  • Local license file
  • Personalization from feedback
  • Get Pro
team · orgs

Team

Pro plus shared policy packs and a commercial support lane.

  • Force-safe defaults
  • Partner / paid support
  • Talk to us

Prices: contact for current Eval / Pro / Team terms — we keep numbers out of the OSS tree until tiers stabilize. License check is local (`flowctl doctor`).

how it works

No blank canvas. No Zapier-style wiring. You keep working; open-core notices what repeats. Intelligence decides what is worth showing.

01 observe

Watch locally

Filesystem events in folders you choose. Optional clipboard, downloads, and terminal bridges.

02 detect

Spot repeats

Open-core turns rename/move sequences into patterns with counts and baseline scores.

03 rank

Intelligence

Private Intelligence ranks, delays, or suppresses — so the CLI stays quiet.

04 run

You approve

Dry-run first, then run. Undo and runs show keep every apply inspectable.

what's new

Hardening on the road to 1.0 — engine trust first, intelligence as the quality layer.

private intelligence boundary

Live client wiring, anti-annoyance caps, delay freshness, preference memory, and optional localhost LLM labeling for explain.

execution path allowlist

Dry-run, run, undo, and daemon auto-run stay inside observed_folders / execution_allowed_roots, including symlink escape checks.

daemon lifecycle + audit

flowctl daemon *, crash-recovery soak tests, and flowctl runs show for every dry-run / apply / undo.

packs & polish

Workflow pack registry, terminal mv/cp into directories, team policy packs (can force intelligence off).

privacy

You don’t have to choose between automation and keeping work on your machine.

local capture

Events stay in a local SQLite database. No accounts, no sync of capture data, no telemetry.

explicit zones

Only folders and optional bridges you enable. Clipboard and terminal observation stay off by default.

inspectable safety

flowctl status, suggestions --explain, runs show, and plain SQL. See privacy docs.

vs other tools

Most tools wait for you to describe the workflow. flowd starts by watching — from the terminal.

vs Zapier / n8n
They ask you to wire integrations first. flowd detects repeated local file work and proposes an automation after the fact.
vs screen agents
Broad desktop control tools watch the screen. flowd stays narrower: files, bridges, deterministic rename/move actions, undo.
vs shell aliases
Aliases help when you already know the pattern. flowd finds the pattern from history; Private Intelligence keeps the suggestion stream from becoming noise.
vs “just open source AI”
Open-core owns the engine. Private Intelligence is the closed decision-quality layer — still local — that turns detection into a product people pay for.

install

v0.3 installs from source (or Homebrew HEAD). You need a stable Rust toolchain.

# clone & install
git clone https://github.com/nickvd7/flowd && cd flowd
./scripts/install.sh
# or: cargo install --path crates/flow-cli && cargo install --path crates/flow-daemon

# first-run setup + daemon
flowctl setup --watch ~/Downloads --watch ~/Desktop
flowctl daemon start
flowctl daemon status

# core loop (open-core)
flowctl suggestions
flowctl approve 1
flowctl dry-run 1
flowctl run 1
flowctl runs show 2

# Private Intelligence (sibling flowd-intelligence checkout)
cargo install --path crates/flow-cli --features intelligence --force
# config: intelligence_enabled = true
# license: ~/.config/flowd/intelligence.license.toml  (or FLOWD_INTELLIGENCE_DEV=1)
flowctl doctor
flowctl suggestions --explain

# optional Homebrew HEAD (open-core)
brew install --HEAD --formula Formula/flowd.rb

faq

Short answers before you install.

What is Private Intelligence?

The product layer on top of open-core. It ranks, times, suppresses, and phrases suggestions so the CLI stays quiet and useful. Open-core owns facts and actions; intelligence only influences presentation. See docs/intelligence.md.

Is intelligence required? Does it upload my data?

No and no. Open-core works alone with baseline suggestions. Private means a closed decision policy evaluated locally — not a cloud brain. Capture stays in SQLite on your machine.

Does any of my data leave my computer?

No. Observation, patterns, suggestions, and automations stay in local SQLite. Open-core has no cloud sync of capture data. Optional local LLM labeling talks only to localhost.

What does flowd actually record?

Filesystem events in folders you configure. Optional clipboard metadata, browser-download bridge records, and terminal-history bridge lines — all off by default except folder watching.

Can automations escape watched folders?

Not when the allowlist is enforced (default). Destinations must stay under observed_folders or explicit execution_allowed_roots. Symlink escapes are rejected.

How long until the first suggestion?

After a rename/move workflow repeats enough times in watched folders. For rare workflows, use flowctl teach from-session.

Will it change files without asking?

No. Approval is required. A dry-run is required before flowctl run unless you pass --force. Daemon auto-run stays off by default.

Do I need integrations?

Not for local files. Bridges are optional NDJSON files for downloads/terminal history — no SaaS connectors.

support

Two lanes: public open-core issues on GitHub, private product questions here.

open-core · public

GitHub Issues

Bugs, setup help, suggestion-quality / dogfood notes, and features — via templates so we can triage.

product · private

Intelligence & commercial

Evaluation access, Private Intelligence questions, partner / paid support — use the form below (not public issues).

  • Still local-first — don’t paste secrets
  • We route product feedback into the backlog

contact

Private line for Intelligence / commercial support. For open-core bugs, prefer GitHub Issues.

or plain old email: [click to reveal]