Context Keeper

Project memory for Claude. Records design decisions, pipeline flows, and constraints so Claude maintains context across conversations.

The Problem

As conversations get long, Claude loses the "why" behind earlier decisions. New conversations start blank. This causes Claude to make changes that break established patterns — like rewriting a pipeline step it doesn't remember exists.

The Solution

Context Keeper gives Claude 8 tools to record and retrieve structured project context:

All data stored as human-editable JSON files in .context/ inside your project directory. Zero external dependencies.

Install

pip install context-keeper

Claude Code

claude mcp add --scope user context-keeper -- python /path/to/context-keeper/server.py

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "context-keeper": {
      "command": "python",
      "args": ["/path/to/context-keeper/server.py"],
      "env": {
        "CONTEXT_KEEPER_PROJECT": "/path/to/your/project"
      }
    }
  }
}

Set CONTEXT_KEEPER_PROJECT to the root of your project. If omitted, it uses the current working directory.

How It Works

Recording Context

When you make a design decision:

You: Let's use JSON files instead of SQLite for storage.
Claude: [calls record_decision with summary, rationale, and alternatives]

When you establish a workflow:

You: The deploy pipeline is: run tests, build, push to registry, deploy.
Claude: [calls record_pipeline with ordered steps]

When you set a rule:

You: Never run Conductor from source. Always use the exe.
Claude: [calls record_constraint with rule, reason, and hardness=absolute]

Retrieving Context

At conversation start, Claude calls get_project_summary to see all active decisions, pipelines, and constraints. Before making changes, it calls get_context with relevant tags to check for conflicts.

Relevance Scoring

Without embeddings or external services, Context Keeper scores entries using:

• Tag match — overlap between query and entry tags
• Text match — query words found in summary/rationale/rule text
• Recency — recently verified entries score higher
• Status — active entries prioritized over superseded

Results are capped by a configurable token budget (default: 4000 tokens).

Claude Code Hook Setup

Context Keeper includes hooks that snapshot your context before Claude Code compaction and detect if anything was lost afterward.

Add to your Claude Code hooks config (~/.claude/settings.json):

{
  "hooks": {
    "PreCompact": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "python /path/to/context-keeper/hooks/pre_compact.py"
          }
        ]
      }
    ],
    "Stop": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "python /path/to/context-keeper/hooks/post_compact.py"
          }
        ]
      }
    ]
  }
}

Replace /path/to/context-keeper with the actual install path. Set CONTEXT_KEEPER_PROJECT env var if your project isn't in the current working directory.

At session start, Claude calls get_compaction_report to check if the last co

... View full README on GitHub