Introduction

Agentfleet is a platform for composing AI agents into auditable, identity-aware workflows. You define what should happen (steps bound to real tools), who does it (an agent with its own registered identity), and Agentfleet handles the execution: model calls, tool calls, token exchange, retries, and observability.

Why Agentfleet?

Most agent frameworks give an LLM a bag of tools and a long-lived API key. That works for demos and fails audits. Agentfleet takes a different position:

• Every step runs under a delegated identity. Before a step executes, Agentfleet exchanges the initiating user's token for a short-lived agent token scoped to exactly that step's resource and tool (RFC 8693 token exchange). The issued token records both the user (sub) and the agent (act.sub), so downstream systems always know who asked and who acted.
• Tools are real, discovered, and scoped. Tools come from MCP servers you register as resources. Each tool carries an OAuth scope, and the exchange requests only that scope — least privilege by construction.
• Everything is observable. Runs record every model call (tokens, latency, round), every tool call, and a cross-step context channel with provenance (was this value a tool output, model text, or caller input?).

The building blocks

Concept	What it is
Agent	An AI worker with its own identity registered in your identity provider.
Resource	An MCP server (an API surface) the platform can call.
Tool	A callable operation imported from a resource, with an OAuth scope.
Step	A reusable unit of work: an instruction plus one tool.
Workflow	An ordered sequence of steps.
Run	One execution of a workflow by an agent, with inputs and full telemetry.
Schedule / Trigger	Fire a workflow automatically — on a cron cadence, or on an inbound event.
Eval suite	A scored, repeatable test suite over a workflow, to catch regressions.
Model provider	The LLM configuration (provider, models, token limits) agents use.

How a run works

1. You queue a run: pick a workflow, pick an agent, and supply inputs.
2. For each step, Agentfleet exchanges a token — your identity delegated to the agent, restricted to the step's resource and tool scope.
3. The agent's model reasons over the step instruction and the accumulated run context, and calls the step's tool with the delegated token.
4. Outputs are promoted into the run context (toolResult_1, modelResponse_1, …) so later steps can use them.
5. The run completes (or fails, with the reason recorded), and every call is available in the run inspector.

Ready? Head to Getting Started.