The way you build changed.
Your tools didn't.
You direct agents now; you don't hand-edit files. LodeFlow is a native workspace for directing coding agents: it hosts the real CLIs, runs a fleet across every project, and keeps you in flow.
Windows and Apple Silicon · free · bring your own agent subscription
You're directing agents across a dozen projects from a sprawl of terminal windows. Juggling which login still has quota. Losing your place on every restart. Dropping into an IDE built for hand-editing code you don't write anymore. It works. It's also a disaster.
It doesn't have to be. The way we build changed; the tools didn't. LodeFlow is built the other way around, for directing agents, not typing code.
Terminal-native. The agent's own CLI is the best interface anyone will build for it. So LodeFlow doesn't reimplement Claude Code, Codex or Kimi. It hosts the real binaries in real terminals and never gets between you and the agent. No imitation chat box; the thing itself.
Multi-agent-native. One agent is a demo. The real day is several at once, across every project you touch: the work codebase and the side project both live in one rail, each readable at a glance. Built around a fleet from the first commit, not a single-document editor with a chat panel bolted on.
Everything directing agents needs.
None of the IDE you don't.
Stop rationing your own subscriptions.
Shipping at work or wrangling a 2am side project, running agents means juggling plans: a work account, a personal Pro, an API key or three. Which one is this on? How much is left? LodeFlow enrols them once and picks per project — so the company plan never accidentally funds your historically accurate roguelike fishtank simulator.
Come back to receipts, not a wall of scroll.
You walked away. The agent didn't. Every turn ends with what changed, what it ran, and how sure the workspace is that the two match — graded inferred, corroborated, or exact, so a claim about your codebase always arrives with its evidence attached.
That's two pieces. The rest of what's built is here too — assembled and working as one, not a host plus four promises. The fifth is the bet, and it says so.
It just works
The agent's CLI is the best interface for it. So host the real one, don't rebuild it.
Direct the fleet
One agent is a demo. Directing ten across your projects is the job.
Sort your subscriptionsin progress
Your own paid accounts, enrolled once, picked per project. ToS-safe.
Review the work
You stopped typing code. Reviewing the decisions is the new work.
A project that learnsnext
Most tools forget between sessions. This one is being built to compound, so every session starts smarter than the last. It's the whole bet, and it's what's next.
You don't write code.
You write markdown.
Plans, notes, and the decisions you don't want the next session to reopen: all markdown, with a real editor and scroll-locked live preview. It's the surface vibe coding actually happens on, and we build for it like it matters.
Is
A native desktop workspace for vibe coders directing coding agents. It hosts the real agent CLIs (Claude Code, Codex, Kimi) faithfully in real terminals, never rebuilding their UI. It runs a fleet of them across all your projects, keeps your subscriptions straight so you're not guessing which account to burn, shows you what the agents changed, and is being built to learn your project so every session starts smarter than the last.
Isn't
Not an IDE. It doesn't instrument around code: no LSP, refactoring, debugger, autocomplete, or minimap. Change a line if you want; LodeFlow just doesn't build the machinery for it. Directing agents is the job, not typing code.
Hi, I'm Nathan. I'm building LodeFlow solo, and I direct agents all day. This is the calm workspace I wanted and couldn't find.
The devlog is the long-form answer.
Architecture decisions, how agents actually retrieve memory, the dead ends. Judgment narrated as it's made. The real interview is async.
Read the devlog