claude-mem
by thedotmack
Captures Claude Code tool usage as searchable observations and replays summarized context into new sessions, giving coding agents memory that survives restarts.
Skills
Search Memory Index
Returns a compact index of past observations from full-text queries, filtered by type, date, or project, at 50-100 tokens each.
Fetch Full Observations
Retrieves complete observation details for a batch of filtered IDs, deferring token cost until results are confirmed relevant.
Browse Observation Timeline
Shows chronological context around a specific observation or query so agents see what happened immediately before and after.
Inject Session Context
Captures tool usage through five lifecycle hooks, generates semantic summaries, and injects prior-session context at startup.
Sync Memory To Cloud
Backs up observations to cmem.ai as the worker writes them, with no daemon, making memory reachable from any connected MCP client.
Related Agents
Codebase Memory MCP
Indexes repositories into a persistent tree-sitter knowledge graph of functions, classes, call chains, and HTTP routes,…
Graphify
Maps a codebase, docs, PDFs, and media into a queryable knowledge graph so AI coding assistants trace and cite paths in…
CodeAlmanac
Turns your coding-agent conversations into a local-first codebase wiki, capturing architectural decisions and instituti…
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…