> For the complete documentation index, see [llms.txt](https://docs.zerve.ai/zerve-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zerve.ai/zerve-docs/reference/limits.md). # Limits Every limit in Zerve, in one place. This page brings together the limits described throughout these docs. Follow the links for details. ## Compute | Limit | Value | See | | --------------------------------------------------- | ----------------------------------------------- | ----------------------------------------------------------------------- | | Any block run | 12 hours | [Limits and concurrency](/zerve-docs/compute/limits-and-concurrency.md) | | Lambda block run time | 15 minutes | [Compute types](/zerve-docs/compute/compute-types.md) | | Lambda memory | 10 GB | [Compute types](/zerve-docs/compute/compute-types.md) | | Lambda scratch storage | 10 GB | [Compute types](/zerve-docs/compute/compute-types.md) | | Fargate CPU and memory | Up to 16 CPUs and 120 GB | [Compute types](/zerve-docs/compute/compute-types.md) | | Fargate scratch storage | 20 to 200 GB, default 20 GB | [Compute types](/zerve-docs/compute/compute-types.md) | | Kubernetes and Armada scratch storage (self-hosted) | Up to 200 GB, default 10 GB | [Compute types](/zerve-docs/compute/compute-types.md) | | GPU retry window | Never (default), 15 minutes, 1 hour or 12 hours | [GPUs](/zerve-docs/compute/gpus.md) | | Automatic retries if compute fails | 3 | [Limits and concurrency](/zerve-docs/compute/limits-and-concurrency.md) | ## Concurrency and Fleet | Limit | Value | See | | ------------------------------------ | ------------------------------------------ | ----------------------------------------------------------------------------------- | | Block runs at once, per organization | 100 by default, adjustable from 1 to 1,000 | [Limits and concurrency](/zerve-docs/compute/limits-and-concurrency.md#concurrency) | | Block runs at once, per user | 100 | [Limits and concurrency](/zerve-docs/compute/limits-and-concurrency.md#concurrency) | | Runs in one Fleet | 250 | [Fleet](/zerve-docs/compute/fleet.md) | | Shortest scheduled job interval | 5 minutes | [Scheduled jobs](/zerve-docs/ship-your-work/scheduled-jobs.md) | ## Agents | Limit | Value | See | | ---------------------------------- | -------------------------------------------------- | ------------------------------------------------------------------------------------------- | | Agent run | 60 minutes | [Credit caps](/zerve-docs/agents-in-the-workspace/evolve-mode/credit-caps.md) | | Evolve Mode credit cap | 50 credits by default | [Credit caps](/zerve-docs/agents-in-the-workspace/evolve-mode/credit-caps.md) | | Evolve Mode direct edits | At most one new block per run, before it delegates | [Evolve Mode](/zerve-docs/agents-in-the-workspace/evolve-mode.md) | | Attachments per message | 5 files, up to 1 MB each and 2 MB in total | [Giving the agent context](/zerve-docs/agents-in-the-workspace/giving-the-agent-context.md) | | Learnings overview, and each topic | 128 KB | [Learnings](/zerve-docs/agents-in-the-workspace/learnings.md) | | Learnings topic summary | 280 characters | [Learnings](/zerve-docs/agents-in-the-workspace/learnings.md) | ## Superagents | Limit | Value | See | | -------------------------- | --------------------------------------------------------- | ------------------------------------------------------------------------------- | | Daily budget | 25,000 credits, which is both the default and the maximum | [Budgets and credits](/zerve-docs/superagents/budgets-and-credits.md) | | Daily budget reset | Midnight UTC | [Budgets and credits](/zerve-docs/superagents/budgets-and-credits.md) | | Team size | Up to 1,000 active workers and coordinators by default | [How the team works](/zerve-docs/superagents/superagents/how-the-team-works.md) | | Shortest schedule interval | 5 minutes | [Schedules](/zerve-docs/superagents/schedules.md) | | Channels per superagent | One of each type | [Channels](/zerve-docs/superagents/channels.md) | | Superagent name | 128 characters | [Superagent settings](/zerve-docs/superagents/settings.md) | | Team member role | 60 characters | [How the team works](/zerve-docs/superagents/superagents/how-the-team-works.md) | | X posts | 280 characters, with up to 4 images | [X](/zerve-docs/superagents/channels/x.md) | ## Organizations and plans | Limit | Value | See | | -------------------------------- | --------------------------------- | ---------------------------------------------------------------------------- | | Members on Free and Pro plans | 10 | [Members and roles](/zerve-docs/administration/members-and-roles.md) | | Members on Team plans | The number of seats you've bought | [Members and roles](/zerve-docs/administration/members-and-roles.md) | | SSO connections per organization | 1 | [SAML single sign-on](/zerve-docs/administration/saml-sso.md) | | Organization name | 128 characters | [Organization settings](/zerve-docs/administration/organization-settings.md) | ## Assets | Limit | Value | See | | --------------- | -------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------- | | Connection name | Up to 255 characters: letters, numbers and underscores, starting with a letter or underscore | [Data connections](/zerve-docs/data-and-assets/connections.md#naming-rules) | --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.zerve.ai/zerve-docs/reference/limits.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.