We only use strictly necessary cookies for authentication and payment processing — no tracking or marketing. Privacy Policy
Clear action limits and LLM budgets. Bring your own LLM on every plan. No hidden fees.
excl. tax
or €194/year excl. tax (save €34)
excl. tax
or €602/year excl. tax (save €106)
* Investigations and fixes are capped by both the action limit and the LLM budget when using CrashLoom AI. BYOLLM agents are only capped by the action limit — no LLM budget consumed.
Each plan has two types of limits: action limits (investigations/mo, fixes/mo) and an LLM budget in USD. Action limits are the maximum number of operations per month. With CrashLoom AI agents, each operation also consumes from your LLM budget — so the budget may run out before you reach the action limit. With BYOLLM agents, no LLM budget is consumed, so you can use the full action limit. Limits reset at the start of each billing period.
You can use your own LLM API keys on any plan. BYOLLM agents only count against action limits and don't consume your LLM budget, so they keep running even when the budget is exhausted.
Yes! You can upgrade or downgrade your plan at any time. Changes take effect immediately, and we'll prorate any charges.
We integrate with Sentry, Firebase Crashlytics, GitHub CI, GitHub Issues, and custom webhooks. We also offer an MCP server so you can query crash data from Claude, Cursor, or any MCP-compatible client.
Yes, we need read access to analyze crashes in context and write access to create pull requests. We use secure OAuth with minimal scopes and never store your code permanently.
Applications are your mobile/web apps (iOS, Android, etc.). Agents are AI configurations that analyze crashes. You can create specialized agents for different types of crashes or apps.