Questions, answered

Flame is an AI-native IDE: a full development workspace for people who juggle many projects at once. It pairs the editor you know with multi-project workspaces, git worktrees, an integrated and broadcast terminal, live previews, and an Agents Manager for AI tasks.

Flame features a powerful editor that feels immediately familiar, with all the standard shortcuts and features. What's different is everything around it: a real multi-project workspace, git worktrees so branches live side by side, a broadcast terminal that runs one command across many repos, a cross-project dependency diagram, and an Agents Manager, not a chat box bolted onto a single folder.

Bundled language servers cover TypeScript/JavaScript, HTML, CSS/SCSS/LESS, JSON, YAML, Bash, Dockerfile, PHP, Vue, Svelte, Astro, and Markdown. Native servers for Python, Rust, Go, C/C++, Java, C#, Kotlin, Swift, Dart, and PowerShell are driven when present. ESLint, Biome, Stylelint, and Ruff attach automatically.

macOS (Apple Silicon and Intel), Windows (x64 and arm64), and Linux (AppImage and .deb). It ships as a native desktop app with the same features everywhere.

Claude (Fable, Opus, Sonnet, and Haiku) out of the box, plus OpenAI and Gemini via API key, and fully local models through Ollama or LM Studio. You can set a default per surface and override the model per conversation.

Yes. Each task can run in its own git worktree and branch, so multiple agents work in parallel without touching your working tree, and you set a concurrency limit for the whole fleet.

Every action is permissioned by scope and category, isolated in a worktree, and reviewable as a diff before it lands. You commit with AI or by hand, then merge, open a PR, or push, with auto-merge only when the branch is clean.

The workspace itself is local-first and works offline. For AI, point Flame at a local model via Ollama or LM Studio and nothing leaves your machine.

No. Flame's server binds to 127.0.0.1 by default and reads your files locally. Your code is only sent to an AI provider when you ask an agent to act, and with a local model, not even then.

Encrypted at rest on your machine (protected by the OS keychain in packaged builds) and never echoed back to the UI. Integrations like GitHub/GitLab tokens are stored the same way.

Yes. Security-relevant actions (opening a terminal, writing a file, pushing to a remote, and every tool an agent invokes) are recorded to an audit log that distinguishes you from the agent.

Join the early-access waitlist. Invites go out in waves: add your email and we'll send your build when a slot opens.

Early access is free while we build with you. We'll share pricing well before anything changes, and waitlist members hear first.