agentskit.js
Use Cases

Research agent

Build a research agent that searches, cites, summarizes, and runs as a repeatable job or interactive assistant.

Research agents are where the runtime, tools, and memory layers start to shine together. The common shape is:

  • search and browsing
  • multi-step synthesis
  • source tracking
  • optional long-running or scheduled execution

Typical stack

npm install @agentskit/adapters @agentskit/runtime @agentskit/tools @agentskit/memory @agentskit/observability
LayerPackageWhy it matters
Provider@agentskit/adaptersFlex between hosted and local models
Runtime@agentskit/runtimeLets the agent search, inspect, compare, and iterate
Tools@agentskit/toolsWeb search, fetch, browser, filesystem, integrations
Memory@agentskit/memoryKeep prior findings and working context
Ops@agentskit/observabilityCompare runs, inspect tool behavior, control cost

What the architecture usually looks like

  1. A task arrives as a prompt, CLI command, or scheduled job.
  2. The runtime decomposes the task into multiple tool-assisted steps.
  3. Search and browser tools collect evidence.
  4. The agent writes structured findings to files or downstream systems.
  5. Observability captures traces for replay and quality review.

Good defaults

  • Keep maxSteps explicit so research runs stay bounded.
  • Save source links and snippets as structured output.
  • Use memory to avoid re-researching the same topics in follow-up runs.
  • Add evals if the research output feeds external customers or exec workflows.

Best follow-up guides

When AgentsKit is especially strong here

Research agents benefit from AgentsKit when you want a clean separation between provider, runtime, tools, and operations. It becomes easy to run the same core workflow in a CLI, a job runner, or a UI without rebuilding the agent from scratch.

✎ Edit this page on GitHub·Found a problem? Open an issue →·How to contribute →

On this page