Install CLM.
The core package includes SQLite storage and FTS5 keyword recall. Add the optional local embedding model for semantic retrieval.
CLM writes its database to ~/.clm/clm.db. Override that location with CLM_DB_PATH.
Save what changed.
Store durable facts, decisions, preferences and project state. Pin only context that should appear at every startup.
note, fact, preference, project, decision, bug, identity or task
--importanceRelevance weight from 0.0 to 1.0
--pinInclude in the automatic hot layer
Ask naturally.
Recall combines exact search, semantic similarity and typed associative spreading. The output includes the score and retrieval path.
Two layers,
one database.
Automatic continuity
Pinned and salient memories are written between managed markers in an agent startup file.
On-demand recall
The full local store stays queryable through the CLI and MCP without filling every context window.
Connect your agents.
Claude Code
Codex
[mcp_servers.clm]
command = "python"
args = ["~/ai/clm/mcp_server.py"]Any MCP-speaking client can use the same five tools: save, recall, link, boot and stats.
Memory is not
a secret store.
SecretGate rejects credential-shaped content at the write boundary. Store secrets in 1Password and save only their op://Vault/Item/field references in CLM.