F FanOn

Remove AI logistics from software development

Build software. FanOn removes AI logistics.

FanOn is a local AI execution and automation platform for developers. Use the CLI to run local AI tasks, summarize repository context, ask project questions, keep FanOn updated, and experiment with repo-memory.

Install FanOn Documentation
Developer-first Direct Mode first Directory-aware context Alpha
Developer Existing workflow
FanOn Runs local AI capabilities
CLI Summarize and ask files, folders, repos
Automation repo-memory experimental, pending apply

What FanOn is

A practical local AI layer for software development.

FanOn helps developers run useful local AI work without managing a pile of model, runtime, context, and automation details.

Today that means CLI capabilities, directory-aware context, a local dashboard, update guidance, and experimental app-backed automations.

Problem / Observation / Belief

Local AI is useful. The logistics are still too visible.

Developers should be able to ask useful questions over their codebase without first becoming local AI infrastructure operators.

Problem Every tool becomes another place to manage models, context, setup, and workflow.
Observation Many everyday development tasks are bounded enough for local AI experiments.
Belief Make local AI feel like a developer tool, not an infrastructure project.

What works today

Concrete alpha capabilities without pretending this is finished.

FanOn is alpha software. The installer and updater are working, and Direct Mode is the recommended first path. Automations and repo-memory are experimental and intended for feedback.

Local CLI Run local AI tasks from the terminal.
Repository context Summarize and ask questions over files, folders, or repos.
Directory-aware context Point `--context` at a directory and skip common generated noise.
Updates Use `fanon update` to inspect and apply CLI updates.
repo-memory Experiment with pending, reviewable AI-ready repository memory.

How FanOn works

Automation = when. Application = what. Workflow = how. Runtime = where.

FanOn Core provides the platform. Applications define the work. The first built-in application, repo-memory, is experimental and writes pending artifacts that must be explicitly applied.

1 Run a local capability

Summarize code, ask about a project, review a focused change, or open the dashboard.

2 Use app-backed automation

repo-memory can run after commits and stage pending repository-memory updates.

3 Review before apply

Generated artifacts are owned outputs. Developers and agents provide feedback.

Why FanOn

Local AI needs a product layer, not another pile of configuration.

Local models run the work. Tool protocols connect assistants. FanOn turns those pieces into developer-facing capabilities, readiness checks, policies, metrics, and setup instructions without making every developer become an AI infrastructure operator.

Not just Ollama FanOn organizes local models into capabilities, diagnostics, and workflows.
Not just a protocol FanOn is the execution and capability layer behind connected tools.
Local first Eligible tasks run close to the developer before reaching for cloud providers.
Visible Readiness, usage, and dashboard output make execution decisions inspectable.

Trust

Execution decisions should be visible.

FanOn is developer infrastructure, not employee monitoring. The product is shaped around local-first defaults, transparent execution, and developer control.

Read the trust model

Pilot / status / fit

Useful enough to test. Early enough to shape.

FanOn is a local/dev MVP, actively dogfooded, and not production-ready yet. It is currently being tested through real CLI and local-model workflows. We are looking for design partners dealing with AI provider sprawl, rising AI costs, local model experimentation, or privacy concerns around cloud-by-default AI workflows.

Status Local/dev MVP in learning and validation.
Best fit Engineering managers, staff engineers, platform teams, and AI infrastructure teams.
Workflows Coding assistants, local model experiments, and AI cost optimization.

Design partners

Help shape the layer that should already exist.

We are looking for conversations and feedback from teams who want AI execution to feel simpler, more private, and more intentional.

Join the Design Partner Program

Takes about 2 minutes. This is a design-partner conversation, not a sales process.