Skip to main content
This page covers workspace-level settings for Fleet, including secrets configuration and usage monitoring.

​
Workspace secrets

Fleet uses workspace secrets to store API keys for models and tools. The following secret types are available:
  • Required model key: An OpenAI or Anthropic API key is required for Fleet to make LLM API calls. The agent graphs load this key from workspace secrets for inference.
  • Agent builder specific secrets: Secrets prefixed with FLEET_ are prioritized over workspace secrets within Fleet. This way, you can better track the usage of Fleet vs other parts of LangSmith which use the same secrets. If you have both OPENAI_API_KEY and FLEET_OPENAI_API_KEY, the FLEET_OPENAI_API_KEY secret will be used.
  • Optional tool keys: Add keys for any tools you enable. These are read from workspace secrets at runtime.
    • EXA_API_KEY: Required for Exa search tools (general web and LinkedIn profile search).
    • TAVILY_API_KEY: Required for Tavily web search.
    • TWITTER_API_KEY and TWITTER_API_KEY_SECRET: Required for Twitter/X read operations (app-only bearer). Posting/media upload is not enabled.
  • MCP server configuration: Fleet can pull tools from one or more remote Model Context Protocol (MCP) servers. Configure MCP servers and headers in your workspace settings. Fleet automatically discovers tools and applies the configured headers when calling them. For more information, refer to the Remote MCP servers page.
Fleet supports custom models per agent. See Custom models for more information.

​
Add a secret

To add a secret:
  1. In the LangSmith UI, navigate to Settings and then move to the Secrets tab.
  2. Select Add secret and enter the secret name (for example, OPENAI_API_KEY or ANTHROPIC_API_KEY) and your key as the value.
    Ensure that the secret keys match the environment variable names expected by your model provider.
  3. Select Save secret.

​
Usage and spend limits

The Usage page gives workspace admins visibility into Fleet spend and the ability to set spend limits for agents and users. This page is will only be visible to users with the fleet:read-admin-config permission.

​
View current spend

The Usage page shows your workspace’s total spend over a selected time period (Last 7 days or Last 14 days), along with total threads and total runs. A daily spend chart provides a visual breakdown of costs over the selected period. The Breakdown section lets you view spend details in two ways:
  • By agent: See each agent’s total cost, number of runs, first and last used dates, owner, and weekly limit.
  • By user: See each user’s spend and activity.

​
Set spend limits

Spend limits let you control how much agents and users can spend. Managing spend limits requires the fleet:write-admin-config permission.

​
Default weekly spend limits

In the Default Weekly Spend Limits section, you can configure:
  • Per-Agent Default Limit (USD): Set a default weekly spend limit that applies to all agents in the workspace.
  • Per-User Default Limit (USD): Set a default weekly spend limit that applies to all users in the workspace.
Limits are week-to-date and reset on Mondays.

​
Override limits for individual agents and users

You can override the default spend limit for individual agents or users to set a custom weekly limit.

​
Spend limit behavior

  • Changes to spend limits may take a few minutes to propagate across all running agents.
  • Spend limits are checked at the start of each run. If a run begins while usage is under the limit, it will be allowed to complete even if the final cost exceeds the limit.
  • Spend calculations are based on traces. Deleting traces will affect reported usage and spend enforcement.
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.