Loading image...Kiro

Product

  • About Kiro
  • IDE
  • CLI
  • Web
  • Mobile
  • Crew
  • Pricing
  • Downloads

For

  • Enterprise
  • Startups
  • Students

Community

  • Overview
  • Ambassadors
  • Discord
  • Events
  • Powers
  • Shop
  • Showcase

Resources

  • Docs
  • Blog
  • Changelog
  • FAQs
  • Report a bug
  • Suggest an idea
  • Billing support

Social

Site TermsLicenseResponsible AI PolicyLegalPrivacy PolicyCookie Preferences
Loading image...Kiro
  • Enterprise
  • Pricing
  • Docs
SIGN INDOWNLOADS
Loading image...Kiro

Get Started

InstallationAuthenticationYour first project

Models

OverviewAvailable modelsReasoning effort

Features

How Kiro works
Specs
Steering
Hooks
MCP
Permissions
Custom agents
Agent Skills
Powers
CompactionKiroignoreCheckpoints and rewind
Built-in tools
Configuration scopes

IDE 1.x

What's new in 1.0
Setup & First Run
Editor
Chat
Experimental
Troubleshooting0.x reference

CLI

What's new in 3.0
Setup & First Run
Terminal UI
Chat
Headless modeACPAuto complete
Experimental
2.x reference

Crew

Quick startInstallationRunning 24/7
Chat
Agent Capabilities
Features
Subagents
Scheduling
Artifacts
Multi-instance
Task Runner
Memory
Knowledge
Snapshot & restore
Interfaces
Apps
ConfigurationSecurityTroubleshooting

Web - Preview

Setup & First RunIdentity Center
Connect your repositories
Working with the agent
Autonomous modeAutomations
Sandbox

Mobile - Preview

Overview

Commands and Reference

CLI commandsSlash commandsBuilt-in toolsExit codesSettingsIDE keyboard shortcuts

Billing

OverviewManaging your subscriptionUpgrading your planDowngrading your planCancelling your planPurchasing add-on creditsManaging your paymentsManaging usage notificationsManaging your taxesContacting billing supportDeleting your accountRelated questions

Enterprise

ConceptsOnboarding quickstart
Connecting your identity provider
Subscribe your teamManage subscriptions
Governance
Monitor and track
SettingsManaged updatesBillingIAMSupported regions

Privacy and Security

OverviewData protectionCode referencesCompliance validationInfrastructure securityIAM permissionsFirewalls, proxies, and data perimetersVPC endpoints (AWS PrivateLink)

Guides

Overview
Language support
Learn by playing

Migration

Migrating from Q DeveloperMigrating from VSCodeUpgrading from Q CLI
  1. Docs
  2. Crew
  3. Features
  4. Knowledge

Knowledge


The Knowledge Library is a curated store of external content you want the agent to reference. Unlike Memory (which builds automatically from conversations), Knowledge is intentional — you choose what goes in.

What it is

Add files, folders, or URLs to the library. Crew chunks, indexes, and embeds them so the agent can search and reference the content during conversations. Use it for:

  • Project documentation the agent should know about
  • API references and specs
  • Runbooks and SOPs
  • Code repositories you want the agent to understand
  • External articles or pages relevant to your work

Using the Knowledge panel

Open Knowledge from the dashboard sidebar. The panel lets you:

  • Add a source — local file, local folder (recursive), or URL
  • View items — see what's been ingested, its status, and chunked content
  • Pause / resume — control active ingestion
  • Remove sources — delete items from the library

Adding a folder source

When you add a folder, Crew scans it recursively:

  • Default ignores for OS junk files (.DS_Store, *.tmp, *.swp, etc.)
  • Per-source ignore_patterns for customization
  • A confirmation step shows what will be ingested before it starts
  • Progress is visible inline as files are processed

Adding a URL source

Crew fetches the URL content, chunks it, and indexes it. Useful for documentation sites, API references, or articles you want the agent to draw from.

How it's searched

The agent searches the Knowledge Library through the local_knowledge_search MCP tool. This happens automatically when the agent determines it needs reference material — you don't need to invoke it manually.

Search uses vector similarity (embeddings) when available, with keyword fallback. Results include the source and relevant content chunks.

Knowledge vs. Memory

KnowledgeMemory
How content gets inYou add it manually (files, folders, URLs)Automatic from conversations
What it storesExternal documents and referencesPreferences, history, lessons, facts, episodes
User actionRequired (add sources, confirm)None (self-learning)
Best for"The agent should know about this documentation""The agent should remember what I prefer"
PanelDedicated Knowledge sidebar itemInspectable via Settings → Memory

Both contribute to what the agent knows, but they serve different purposes and are managed differently.

Embeddings

Knowledge items are embedded for semantic search using the same in-process embedding runtime as Memory. The model downloads automatically on first start (~610 MB). Until it lands, search falls back to keyword matching.

No setup needed — embeddings are always-on.

When the agent uses Knowledge

The agent searches Knowledge when:

  • You ask about something that matches content in the library
  • A triggered skill or workflow references library content
  • The local_knowledge_search tool fires based on relevance signals

It doesn't dump the entire library into context — it retrieves the most relevant chunks for the current question.

Page updated: August 4, 2026
Memory
Snapshot & restore