Lockstep runs on your own machine — the client starts it, so there is no endpoint to ping. 70 installs a week from npm. Last commit 25 Oct 2026.
Decision memory for AI coding agents: captures decisions once, briefs every agent before it acts.
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const p = path.join(sqlDir, file);
${like ? sql`AND (d.scope_ref ILIKE ${like} OR EXISTS (SELECT 1 FROM decision_versions v WHERE v.decision_id = d.id AND v.rule_text ILIKE ${like}))` : sql``}
const SECRET_LIKE = /(^|\/)(\.env(\..*)?|\.npmrc|\.pypirc|id_[a-z0-9]+|credentials(\.json)?|.*\.(pem|key|p12|pfx|keystore))$/i;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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": {
"command": "npx",
"args": [
"-y",
"lockstep-cli"
]
}
}
}
[mcp_servers.lockstep]
command = "npx"
args = ["-y", "lockstep-cli"]
{
"mcpServers": {
"lockstep": {
"command": "npx",
"args": [
"-y",
"lockstep-cli"
]
}
}
}
{
"servers": {
"lockstep": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"lockstep-cli"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
LOCKSTEP_VENDOR (Agent vendor label used for session registration (e.g. claude-code, cursor). Optional; defaults to unknown).
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.