Introducing the ContextStore CLI

Your context repository might span multiple spaces — Product, Marketing, Engineering. But when you're working in a coding agent, it only sees the current project directory. Your product vision is in one space. Your brand guidelines are in another. Your engineering architecture docs are in a third. The agent has no idea any of it exists.
The ContextStore CLI fixes this. Run cstore from any directory and your agent can browse, search, read, and write documents across all your spaces. No folder permissions to grant. No paths to remember. Just context, available everywhere.
A quick tour
Install ContextStore and the CLI is included. Run cstore help to see what's available. Here are the commands you'll use most:
List your spaces and documents:
cstore ls # list all spaces
cstore ls Product --stats # list docs in a space with word counts
cstore tree Product # show the full folder structurecstore ls # list all spaces
cstore ls Product --stats # list docs in a space with word counts
cstore tree Product # show the full folder structureRead documents:
cstore read Product/vision.md # full document
cstore read Product/roadmap.md --head 20 # just the first 20 linescstore read Product/vision.md # full document
cstore read Product/roadmap.md --head 20 # just the first 20 linesSearch across everything:
cstore search "onboarding" # full-text search
cstore search "PIX-\d+" --regex # regex search
cstore search "auth" --folder Product # scope to a foldercstore search "onboarding" # full-text search
cstore search "PIX-\d+" --regex # regex search
cstore search "auth" --folder Product # scope to a folderConcatenate documents for bulk context:
cstore cat Product/ --headers # dump all docs in a foldercstore cat Product/ --headers # dump all docs in a folderTrack tasks:
cstore tasks Product/ --pending # show incomplete checkboxes
cstore check Product/roadmap.md "Launch beta" # mark one donecstore tasks Product/ --pending # show incomplete checkboxes
cstore check Product/roadmap.md "Launch beta" # mark one doneThe CLI also supports creating, editing, moving, and deleting documents. Run cstore help <command> for details on any command.
Why this matters for agents
The real power of cstore is what it enables for your AI agent. When an agent has access to cstore, it can pull context from any space without you having to set up folder access or copy files around. Working on a feature in your codebase? The agent can cstore read Product/vision.md to understand why the feature matters. Writing marketing copy? It can cstore search "brand voice" --space Marketing to find your style guide.
This works because cstore operates like git — it walks up from the current directory looking for a .contextstore/settings.yml file, and it can target any space by name with the --space flag. Your agent doesn't need to know where files live on disk.
Get started
The CLI ships with ContextStore but needs a one-time install. Open ContextStore, click the gear icon in the lower left to open Settings, then click the CLI tab. Click Install to open the install dialog.

The dialog walks you through three steps: copy the install command, paste it into Terminal (you'll be prompted for your password), and verify with cstore help.

Once installed, try:
cstore helpcstore helpYou should see a list of all available commands. From there, try reading a document or searching for a term. Once you're comfortable, tell your agent about it. Add a note to your AGENTS.md that cstore is available, what spaces it can access, and which documents matter most — like your Vision, Roadmap, and key Specs. That's all the agent needs to start pulling in the right context on its own.
Comments
You might also like…
How to use ContextStore with Claude Desktop
A step-by-step guide to connecting ContextStore to Claude Desktop using Cowork. Grant folder access, co-create documents with Claude, and give your AI the context it needs.

Make your AGENTS.md a table of contents
Most AGENTS.md files try to do too much. Treat yours as a table of contents — link to essential docs, let your LLM know where to look, and keep the file itself short and scannable.

The hidden cost of remote MCPs
Remote MCPs add a round-trip tax every time your AI needs context. Local Markdown files are faster, cheaper, and more reliable. Here's why that matters.

Introducing ContextStore: a native Mac app for context repositories
Poor AI output is usually a context problem, not a prompting problem. ContextStore is a native Mac app that makes it easy for anyone on your team to build and manage a Markdown-based context repository.
