Open Free Max drives the official Claude Code, Codex, OpenCode, Gemini, Vibe and Kimi CLIs interactively — all from one Mission Control screen, on your subscription, never your API bill. No Electron. No extension host. Sessions that never get lost, and a private, searchable memory that stays on your machine.
Free · Windows v2.5.0 (.msi) · macOS v2.5.0 (.dmg)
Installers aren't code-signed yet. On Windows, click
More info → Run anyway if SmartScreen warns
you. On macOS, drag the app to Applications, then run
xattr -cr "/Applications/Open Free Max IDE.app"
and open it via System Settings → Privacy & Security → Open Anyway.
See the install guide.
Open Free Max uses up to 200× less memory than Antigravity, Cursor or Visual Studio. No bundled Chromium, no extension host — just your OS WebView and a native Rust core.
Not another Electron behemoth. Not a chatbot wrapper around one API. A thin native shell over the official agent CLIs — with the editor, tabs and screenshot workflow you actually want on top.
Spin up as many CLI sessions as you want — across projects and providers — and watch them all from a single control room. Each pane is its own live PTY: glance at what every agent is doing, jump in to steer one, and let the rest keep working.
You're done being the for-loop. Hand OFM one repetitive task — a brief split into N units — and it runs them across a pool of agents, in parallel, on your subscription. The engine carries the whole batch to the end on its own — for hours or days, without you in front of the screen.
10,000 profiles to enrich. 50 sites to scaffold. A security audit across every repo. You launch it once and the orchestrator does the rest — fanning work out, watching every session, and picking up exactly where it left off.
Coding agents are brilliant and amnesiac — every session starts from zero. OFM gives each project a persistent memory with a built-in search engine, so what you did with one agent is there for the next one — in any CLI. And it all stays on your machine.
Signed entitlement so the client can't be pointed at a fake backend. Public key burned in at build time…
Access tokens stay HS256; only the entitlement is RS256-verified client-side…
OFM quietly builds a private knowledge base of each project — past conversations, decisions and durable facts — and lets you search it instantly or feed it back to the next agent.
Memory is computed and stored entirely on-device. Open Free Max does not collect, transmit or retain your prompts or the agents' replies — there is no telemetry of your LLM exchanges and no server to send them to. Delete memory.db and the memory is gone, instantly.
Providers split usage in two: interactive — a human typing and reading — runs on your normal subscription. Programmatic — SDKs, headless runs, third-party app protocols — drains a capped credit pool and then bills at API rates.
-p runsBuilt on Tauri — your OS WebView and a native Rust core. No bundled Chromium, no VS Code extension host. Up to 200× less RAM than Antigravity, Cursor or Visual Studio, even with several agents running.
OFM drives the official CLIs in interactive mode — a human in the loop. Your usage stays on the Max / Pro plan you already pay for, never the metered programmatic path.
Close the app, reopen it, and every agent tab replays its full conversation. OFM never owns the transcript store — so a conversation is impossible to lose or corrupt.
Paste or drop any number of images into a prompt. OFM writes them to disk and shows thumbnails — you never type a file path, and clipboard paste just works on native Windows.
Every project gets a private, searchable memory of what your agents did — past conversations and distilled facts, fed back to the next session. 100% local: OFM never collects or uploads your LLM exchanges.
Pilot as many agent CLIs as you want from a single screen — every session live in its own PTY, across projects and providers. Steer one, let the rest run.
Hand it one repetitive job and a pool of agents runs it in parallel until it's done — surviving crashes, reboots and token-limit windows by auto-resuming. The for-loop is no longer you.
Open a project living inside a WSL distro and the agent runs in Linux — node, git and the CLI from your distro, the right PATH guaranteed. Nothing to install on the IDE side.
The agent CLI already stores every transcript on disk. OFM keeps only a tiny map of which sessions were open — and rebuilds it from disk if it's ever missing. That's the bug other tools can't fix, fixed by design.
Hit Ctrl+V or drag images straight into the prompt. OFM saves each one, shows a thumbnail chip, and injects the real paths at send time. Drop ten — no path-typing, no silent clipboard failures.
Open Free Max is used by vibe coders, authority content creators, ghostwriters, course builders, copywriters, and product designers — anyone who already pays for Claude Max, Codex or a similar LLM subscription and needs to produce, iterate, and ship at scale without writing pipeline code.
Ships entire products by describing them. Never reads the diff.
Describe the feature, the agent builds it. OFM keeps multiple build sessions live across your projects so you steer by outcome, not syntax. Hit your quota mid-sprint? Sessions park automatically and auto-resume when your plan refreshes — the build never stops.
30 LinkedIn posts. One Sunday morning.
Feed Plan your editorial calendar — a topic list and a master prompt. It fans the work across agents and runs until every post, thread, and newsletter draft is done. Your subscription covers the entire batch; you cover the strategy.
Ten clients. Ten live agents. Zero context confusion.
Each client lives in its own persistent session — its own context, files, and conversation history. Switch projects without re-briefing. Close the laptop, return tomorrow: every session is exactly where you left it.
A full programme before lunch.
Your curriculum has 40 lessons — all the same structure. Give Plan the syllabus and a template prompt. It runs all 40 in parallel, parks when tokens run out, and auto-resumes the next morning. The programme is ready when you wake up.
500 product pages. Not 500 manual prompts.
SEO pages, product descriptions, email sequences, localised copy — repetitive content at scale is exactly what Plan was built for. Define the brief once, let OFM run the batch. Still on your subscription, never the API meter.
From user research to user stories in one session.
Run UX synthesis, competitive analysis, and spec writing as parallel agent sessions. Long sessions survive reboots — close the laptop, pick up tomorrow with full context intact. OFM orchestrates; you think.
One provider adapter, the agents you already use. No lock-in.
Anthropic — session resume, names, fork
OpenAI — interactive CLI
Open source agent CLI
Google — interactive CLI
Mistral — interactive CLI
Moonshot — interactive CLI
Open Free Max
Open Free Max is the IDE. Your agent usage keeps running on the Claude, Codex or Gemini subscription you already have — OFM never adds an API meter. Start with a 7-day free trial, no credit card.
Everything in Open Free Max.
$19.9/mo regular price — locked in while the launch offer lasts.
Download OFM, sign in, and your 7-day trial starts automatically.
Download the installer for your OS and run it — a native .msi on Windows, a .dmg on macOS (Apple Silicon & Intel). No package manager, no build step, no command line required.
OFM Pro is $9.90/month as a launch price (regular price $19.90/month), with a 7-day free trial and no credit card. That's the price of the IDE itself — your agent usage keeps running on the Claude / Codex / Gemini subscription you already have. See Pricing.
No. OFM never touches your tokens, keys or auth. It launches the official agent CLI, which handles its own subscription login. You sign in once where you already do.
OFM only ever drives the official CLI in interactive mode (a real human typing and reading). It deliberately avoids the SDK, headless `-p` and ACP paths that are billed against the metered programmatic credit pool.
No. The new persistent memory is computed and stored entirely on your machine, in a single local memory.db file. Open Free Max does not collect, transmit or retain your prompts or the agents' replies — there's no telemetry of your LLM exchanges and no server to send them to. You search your own history locally, and deleting the file wipes the memory instantly.
Plan turns OFM into an autonomous orchestrator. You give it one repetitive job — a brief split into units — and it runs a pool of interactive agent sessions in parallel until the whole batch is done. It survives crashes and reboots, and because it stays on your subscription it expects to hit token limits: it parks and auto-resumes when your plan refreshes. Each unit writes its own output (a file or folder), so the run is idempotent and fully resumable.
Windows (with native WSL2 project support) and macOS — the Tauri core covers both with a small, native footprint.
Those embed Chromium plus the VS Code extension host, which is heavy, and they re-implement session storage — the place where agent conversations get lost. OFM stays thin and leans on the CLI's own durable store.
A lightweight native IDE for Windows and macOS. Download it and drive every agent you already pay for.
Free · Windows v2.5.0 (.msi) · macOS v2.5.0 (.dmg)
Installers aren't code-signed yet. On Windows, click
More info → Run anyway if SmartScreen warns
you. On macOS, drag the app to Applications, then run
xattr -cr "/Applications/Open Free Max IDE.app"
and open it via System Settings → Privacy & Security → Open Anyway.
See the install guide.