Lockstep runs on your own machine — the client starts it, so there is no endpoint to ping. 27 installs a week from npm. Last commit 17 Sep 2026.
Decision memory for AI coding agents: captures decisions once, briefs every agent before it acts.
Today is the operative word: we check Lockstep 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 lockstep -- npx -y lockstep-cli
{
"mcpServers": {
"lockstep": {
"args": [
"-y",
"lockstep-cli"
],
"command": "npx"
}
}
}
[mcp_servers.lockstep]
command = "npx"
args = ["-y", "lockstep-cli"]
{
"mcpServers": {
"lockstep": {
"args": [
"-y",
"lockstep-cli"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"lockstep": {
"args": [
"-y",
"lockstep-cli"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
LOCKSTEP_VENDOR (Agent vendor label used for session registration (e.g. claude-code, cursor). Optional; defaults to unknown.).
The author declared them in the registry entry; get the values from the project itself.
Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.
Self-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach.
Local-first memory for coding agents; stores decisions, bugs, and context across sessions.
Git-native decision memory for coding agents: only the decisions still in force for the edited path
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Persistent memory graph for coding agents: hypotheses, evidence, and decisions survive sessions.
Memory for coding agents: the decisions, the dead ends, and where the last session stopped.
Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.
Answers built from our own checks of this server.