Kage
About
A framework for collaborative agent memory. Kage is shared, code-grounded memory for developers and their coding agents: capture a learning once — a bug cause, a decision, a gotcha — and the whole team plus every agent recalls it next time it's relevant. Memory is grounded in you
Details
- Author
- kage-core
- Downloads
- 305
- Categories
- Developer Tools, AI, Knowledge Base
Jump to
- Shared memory grounded in your actual code.
- Stored as git-tracked JSON reviewed in pull requests.
- Citations validated on write to maintain accuracy.
- Stale memory automatically withheld and flagged.
- Works with Claude Code, Codex, Cursor, and Windsurf.
- No vector database, API key, or service to run.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
KageCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Run the command npx -y @kage-core/kage-graph-mcp to try it in about 30 seconds. Memory is stored as git-tracked JSON that is reviewed in pull requests, and it works with any MCP client.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"kage": {
"kage": {
"command": "npx",
"args": [
"-y",
"@kage-core/kage-graph-mcp"
]
}
}
}
}McpServers
{
"kage": {
"command": "npx",
"args": [
"-y",
"@kage-core/kage-graph-mcp"
]
}
}A framework for collaborative agent memory. Kage is shared, code-grounded memory for developers and their coding agents: capture a learning once — a bug cause, a decision, a gotcha — and the whole team plus every agent recalls it next time it's relevant. Memory is grounded in your actual code and stored as git-tracked JSON reviewed in PRs, not a personal vector blob that drifts: citations are validated on write, and stale memory (whose code was deleted or refactored) is withheld from recall and flagged for you. Works with Claude Code, Codex, Cursor, Windsurf, and any MCP client. No vector DB, API key, or service to run. Try it in 30s: npx -y @kage-core/kage-graph-mcp demo
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
