Context Keeper is a tool that helps Claude maintain project memory by recording design decisions, pipeline flows, and constraints across conversations. It allows for structured retrieval of this context to prevent loss of information during interactions.
From the registry: Project memory for Claude: decisions, pipelines, and constraints across conversations.
$ pip install context-keeperPlease install the `context-keeper` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install context-keeper** — Install via pip. Run: `pip install context-keeper`
Canonical MCP server config (stdio transport):
- command: `python`
- args: ["<path-to-context-keeper>/server.py"]
- optional environment variables:
- `CONTEXT_KEEPER_PROJECT`: Project root path (defaults to CWD).
Note: Zero external dependencies; stores context as JSON files in .context/.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CONTEXT_KEEPER_PROJECTrequiredSet to the root of your project; if omitted, it uses the current working directory.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.