Getting started

Quick Start

Three steps: install Knowit into a project, tell your agent to use it, and start storing knowledge.

1. Install Knowit into a project

Terminal

$ npx knowit install

The wizard initializes the local memory store, writes MCP config for your clients, and can update agent instruction files for you. See Installation for per-client details.

2. Tell your agent to use it

If you are not using the installer-managed instructions, add this to your client instruction file — AGENTS.md, CLAUDE.md, or .github/copilot-instructions.md:

CLAUDE.md

## Memory

This project uses Knowit as the default persistent knowledge base
for AI coding agents.

- Before planning or implementing, call `resolve_context` with
  the task description and repo name.
- After finishing a task, call `capture_session_learnings` to
  store durable rules, decisions, and patterns.
- Prefer Knowit over repo-local markdown memory files unless the
  user explicitly asks for a file.

3. Start storing and retrieving context

Terminal

$ knowit add rule "No direct DB access from controllers" \
  "All database access goes through repository classes." \
  --scope repo --repo api-gateway --tags architecture,layers

$ knowit resolve "implement user authentication" --repo api-gateway --domain auth

From here, your agent handles most of the loop on its own: it calls resolve_context before planning and capture_session_learnings after finishing. Read How It Works for the full picture.

Browse what you have

Terminal

$ knowit list --repo api-gateway
$ knowit show <entry-id>
$ knowit stats
$ knowit preview # read-only local browser UI