FAQ
Short answers to common questions about Nib, models, pricing, privacy and bringing your existing setup.
General
What is Nib?
One place to work with AI, on any model. It reads your code, edits files, runs commands and checks its work, using the provider and model you choose. It runs as a desktop app and a CLI on one shared runtime. Nib Crew, AI teammates that work on a schedule, runs locally today; the web app is available, and cloud crews are coming soon.
Is Nib ready for daily use?
Nib 0.1 is an early preview. The core runtime, harness, provider layer, CLI and desktop shell exist and are tested, but expect rough edges and changes before 1.0. Commit your work before long sessions, and read the changelog when you update.
What does Nib cost?
Nib needs an account on every plan. The Free plan is $0 and includes 2,500 agent actions a month on your own keys, plus a monthly allowance of efficient Nib models and 400 welcome credits. Pro is $20 a month ($200 billed yearly) and includes Nib models every week, typically about 40 small coding tasks a week (how we measure), with unlimited use of your own keys. Max, Ultra, Team and Enterprise are on the pricing page.
With your own keys, you pay your model provider directly, and nothing is added to your provider's bill. For Nib models, usage inside your plan shows as a share of your plan; usage beyond your plan is charged at list price × 1.05, which includes a disclosed 5% fee.
Models
Which models work best?
Frontier models from Anthropic, OpenAI and Google do best on long, open-ended tasks. Open-weight models such as GLM, DeepSeek, Kimi, Qwen and MiniMax cost less per token, and Nib's harness adapts to them. Nib picks a strong default when you add a provider; Models and effort shows typical picks.
How does Nib handle different models?
Nib works with any endpoint that speaks the OpenAI, Anthropic or Gemini API, and adapts its tools to each model family: apply_patch for GPT models, str_replace-style edits for Claude and Gemini, and hash-anchored line edits for weaker and local models. It replays each provider's reasoning state and repairs malformed tool calls from open models. See Tools and Providers and gateways.
Can I use a local model?
Yes. Point Nib at Ollama, LM Studio, vLLM or any OpenAI-compatible server. Choose a model that supports tool calling and give it at least 32k tokens of context. Expect smaller models to need more guidance.
Can I use my company's gateway?
Yes, if it speaks the OpenAI, Anthropic or Gemini API. Enter its base URL and key. Gateways that need extra headers (Portkey, Cloudflare) can be configured with them.
Can I switch models in the middle of a session?
Yes, with /model or the model picker. The conversation carries over. The first turn on the new model won't benefit from the previous provider's prompt cache.
Does Nib work with my Claude Pro or Max subscription?
No. Nib connects with API keys from providers and gateways. It doesn't sign in with consumer chat subscriptions.
Your existing setup
Does Nib work with the setup I already have?
Yes. Nib reads AGENTS.md, CLAUDE.md, GEMINI.md, .claude/settings.json, skills, subagents, commands, hooks and .mcp.json where they are, so there is nothing to migrate, and you can keep using other agents on the same repository. Configuration that Nib doesn't read directly comes over with the import: in the desktop app's setup, or with nib import. Plugins in the .claude-plugin format install with nib plugin (see Hub). Details are in Import your setup.
Privacy and security
Does my code go to Nib's servers?
Not unless you use a cloud feature. With your own keys, the daemon sends model requests directly to the provider you chose, and your code and session history stay on your machine. Cloud features go through Nib's servers even with your own keys: sync carries your sessions, managed web search (when you haven't set a search key of your own) carries the agent's queries, and cloud dictation carries your voice. With Nib models, requests pass through Nib's managed gateway to the provider; we keep usage metadata such as token counts and cost, not the content. You need a Nib account either way. The Privacy Policy lists exactly what reaches Nib's servers; see also Security and privacy.
Does Nib collect telemetry?
Crash reports and usage metrics are off by default. Nib asks once, and you can change your choice in Settings → Privacy. See Security and privacy.
Can the agent delete my files or run dangerous commands?
Only with your approval, unless you've pre-approved it with rules or a permissive mode. Edits are checkpointed so you can rewind them. Shell commands can be sandboxed. Writes to .git, agent configuration and shell startup files need your approval in every mode but bypass. Shell side effects such as deleted directories or pushed commits can't be rewound, so be deliberate about what you allow.
Platforms
Which platforms are supported?
The desktop app runs on macOS 12 Monterey or later. Windows and Linux follow in a later release. The CLI runs on macOS, Linux and Windows. The OS sandbox for shell commands is available on macOS and Linux.
Is there an IDE extension?
In preview. The VS Code extension puts sessions, diffs and approvals in a sidebar, and Zed, JetBrains and other editors that speak the Agent Client Protocol can run Nib through nib acp. Neither is in a marketplace yet. Nib also works alongside any editor: file paths in the transcript open in your editor, and the CLI runs in any terminal, including the one inside your IDE.