Skip to content

Latest commit

 

History

History
58 lines (42 loc) · 3.38 KB

File metadata and controls

58 lines (42 loc) · 3.38 KB

AgentKit Documentation

中文索引 · Project README

This guide is organized by the problem an application needs to solve. You do not need to enable every subsystem: start with the runtime, then add only the capabilities your agent needs.

Recommended Reading Paths

For a first agent:

  1. Run the root five-minute example.
  2. Learn the run methods and event lifecycle in Runtime and events.
  3. Use Testing to make the behavior deterministic.

For a production assistant:

  1. Add Sessions and persistence.
  2. Use Multi-session management when serving more than one conversation.
  3. Add Context management before conversations grow large.
  4. Review Tool management, especially timeouts and large results.

For work that may take hours or days:

  1. Start with the production-assistant path.
  2. Use Durable goals for restart and reconnect semantics.
  3. Connect Scheduling and wakeups when work must start later or recur.
  4. Use MCP or Skills only where the task requires them.

For coordinated specialist work:

  1. Define bounded, isolated specialists with Subagents.
  2. Give each specialist only the tools and MCP servers it needs.
  3. Combine with Durable goals when work must survive across step boundaries.

Guides

Guide Covers
Runtime and events Ask, streams, events, lifecycle, request values, HITL, queues, multimodal input
Sessions and persistence Session restore/save, checkpoints, stores, concurrency, retention
Multi-session management Creation, reconnect, ownership, pagination, archive, fork, and Agent lifecycle
Durable goals /goal-style loops, async execution, reconnect, recovery, leases, idempotency
Scheduling and wakeups Reliable integration with cron, queues, cloud schedulers, and supervisors
Subagents Declarative specialists, isolation, budgets, events, nested HITL and goal integration
Context management Full history versus model context, automatic compaction, ordering with reduction
Skills Local SKILL.md discovery, custom backends, validation and boundaries
MCP Managed transports, tool discovery, limits, authentication, reconnection and ownership
Tool management Policy, aliases, hooks, repair, result reduction, dynamic tool search
Testing Mock models, mock tools, streaming failures and interaction assertions

Runnable programs live in the examples directory. Public API details also remain available through Go package documentation.

Documentation Conventions

  • Examples always pass a non-nil context.Context. Use context.TODO() when the correct lifetime is not known yet.
  • Zero-value optional configurations shown as &agentkit.SomeConfig{} are intentionally safe defaults.
  • “Durable” means state survives through the configured store. It does not mean a stopped process continues executing without a worker or supervisor.
  • File-backed stores target one local process. Database-backed transactional implementations are required for multi-replica ownership.