Introduction
Getting started with Knowns CLI - the knowledge management tool for developers
Introduction
Knowns is a CLI-first knowledge and workflow layer that gives AI persistent memory of your project context. Document once, link everywhere.
v0.18 expands Knowns with code intelligence, smoother workspace switching, richer AI chat UX, and the 3-layer Memory System introduced in the v0.17 generation.
Latest In The v0.18 Series
- v0.18.0: Code intelligence, code graph UI, workspace switching, and chat UX upgrades
- v0.18.1: Public docs refresh for the new code/browser/chat flows and installer version pinning examples
- v0.18.2: Shared runtime queue, script-aware
knowns update, runtime logs, and stability improvements - v0.18.3: Runtime adapter install, MCP-first retrieval guidance, and better semantic memory retrieval/search filtering
How To Use These Docs
If you are new to Knowns, read the docs in this order:
- Installation
- Task Management
- Workflow
- CLI Reference
- Feature-specific pages such as MCP, memory, code intelligence, or Web UI
Why Knowns?
Modern development involves juggling tasks, documentation, and context across multiple tools. Knowns brings everything together in a simple, git-friendly format that works seamlessly with AI assistants.
Key Benefits
- Semantic Search: AI-powered search using vector embeddings. Find by meaning, not just keywords
- AI Chat: Built-in project-aware chat inside Knowns, powered by OpenCode
- Spec-Driven Development: Write specs first with
/kn-spec, link to tasks, auto-sync ACs - CLI-First: Everything accessible from your terminal
- AI-Ready: Automatic context loading via
@doc/...,@task-..., and@template/...references - Skills System:
/kn-*namespace for task, spec, plan, implement, verify workflows - Code Intelligence: Dedicated code search, symbols, deps, and graph flows for code-aware AI work
- Memory System: Working, project, and global memory layers for durable AI context
- Dashboard + Web UI: Faster local interface for Kanban, docs, memory, graph, and chat
- Knowledge Graph: Visualize relationships between tasks, docs, and memories
- Template System: Generate code with Handlebars templates linked to documentation
- Import System: Share docs and templates across projects from Git, npm, or local sources
- Git-Friendly: All data stored as Markdown in
.knowns/folder
Prerequisites
Knowns requires Node.js 20+ for npm-based installation. See the Installation Guide for platform-specific instructions.
Quick Start
# Install
curl -fsSL https://knowns.sh/script/install | sh
# Initialize in your project
cd your-project
knowns init
# Create your first task
knowns task create "Setup project" -d "Initial setup" --ac "Dependencies installed"
# Open local UI + AI Chat
knowns browser --open
# (Optional) Auto-setup Claude Code MCP
knowns mcp setupCore Concepts
Tasks
Tasks are the primary work items in Knowns. Each task has:
- Title: Clear summary of what needs to be done
- Description: Context and requirements
- Acceptance Criteria: Testable outcomes
- Status: todo, in-progress, in-review, blocked, done
Documentation
Documentation lives in .knowns/docs/ as Markdown files with frontmatter. Reference docs anywhere using @doc/path or @docs/path syntax (both work identically).
Time Tracking
Built-in timers let you track time spent on tasks. Generate reports by date range, label, or project.
Templates
Code generation with Handlebars (.hbs) templates. Each template can link to documentation for context-aware generation.
# List templates
knowns template list
# Generate code
knowns template run component --name ButtonNext Steps
- Installation Guide - Detailed setup instructions
- Task Management - Learn about task workflows
- Memory System - Persistent context for AI agents
- Code Intelligence - Index and explore symbols, deps, and code graph context
- Template System - Code generation with templates
- Import System - Share docs across projects
- CLI Reference - Complete command reference
- Philosophy - Core principles behind Knowns
- Contributing - How to contribute to Knowns
- Roadmap - Current direction from the main Knowns repository
- License - MIT license summary