Codebase Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 30 453 installs a week from npm. Last commit 16 Sep 2026.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
We read the source, 20 h ago · rules 3dff92dd89df
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.
postinstall: node install.js
этот файл ставится пользователю, но в репозитории его нет
archivePath := filepath.Join(tmp, "cbm."+ext)
const probe = spawnSync(binPath, ['--version'], {
subprocess.run(
RUN apt-get update && apt-get install -y --no-install-recommends \
gcc g++ make cmake \
return _popen(cmd, mode);
KEY="${HOME}/.claude/cbm-vm/id_ed25519"
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 codebase-memory-mcp -- uvx codebase-memory-mcp
{
"mcpServers": {
"codebase-memory-mcp": {
"args": [
"codebase-memory-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.codebase-memory-mcp]
command = "uvx"
args = ["codebase-memory-mcp"]
{
"mcpServers": {
"codebase-memory-mcp": {
"args": [
"codebase-memory-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"codebase-memory-mcp": {
"args": [
"codebase-memory-mcp"
],
"command": "uvx"
}
}
}
Local codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Code knowledge graph over MCP: token-budgeted context for AI coding agents.
Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.
Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
Codebase knowledge graph — architectural awareness for AI coding agents via MCP
Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory.
Read-only visualization for Cortex memory, knowledge, sessions, traces, and codebase graphs.
Answers built from our own checks of this server.