contextkeeper runs on your own machine — the client starts it, so there is no endpoint to ping. 159 installs a week from pypi. Last commit 14 Apr 2026.
Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.
Today is the operative word: we check contextkeeper every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add contextkeeper -- uvx contextkeeper
{
"mcpServers": {
"contextkeeper": {
"args": [
"contextkeeper"
],
"command": "uvx"
}
}
}
[mcp_servers.contextkeeper]
command = "uvx"
args = ["contextkeeper"]
{
"mcpServers": {
"contextkeeper": {
"args": [
"contextkeeper"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"contextkeeper": {
"args": [
"contextkeeper"
],
"command": "uvx"
}
}
}
Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.
Zero-config AI context generation and code quality toolkit with Claude Code Agent Mode support
Session handoff for Claude Code: list sessions and build handoff docs another agent continues from.
Context sync layer for AI agents. Ensures continuity and eliminates memory drift automatically.
Local-first memory and session continuity for AI coding agents over MCP. No cloud, no telemetry.
Token and context budget for AI agents. Tracks spend and gates the session.
Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome.
Answers built from our own checks of this server.