Claude-Mem: Persistent Long-Term Memory for AI Coding Agents

Solving AI Agent Amnesia: Meet Claude-Mem

One of the most persistent hurdles in working with command-line AI coding assistants (such as Claude Code, Antigravity CLI, and OpenCode) is context fragmentation across sessions. When a developer ends a terminal session, the agent's working context is wiped clean. The next day, the developer must re-explain architectural decisions, project conventions, and previously resolved edge cases.

claude-mem is an open-source memory compression and retrieval engine created by thedotmack. It passively monitors developer interactions, compresses key discoveries into structured observations, and seamlessly primes future agent sessions with relevant context.

What is Claude-Mem?

claude-mem operates as an intelligent background memory worker. Rather than dumping raw conversation transcripts into future prompt windows—which rapidly drains token budgets—claude-mem extracts semantic summaries of bug fixes, architectural choices, and dependency discoveries.

When a new session starts, the agent queries its memory database to recall pertinent project history before writing code.

Key Core Features

1. Passive Background Observation

claude-mem hooks into five critical lifecycle stages (SessionStart, UserPromptSubmit, PostToolUse, Stop, and SessionEnd). It documents what worked, what failed, and why, without requiring manual intervention from the engineer.

2. Progressive 3-Layer Retrieval (~10x Token Savings)

To preserve context window capacity, claude-mem implements a tiered retrieval model:

1. Search Index: Returns compact observation IDs and titles (~50–100 tokens per result).
2. Timeline Slice: Provides chronological context around relevant findings.
3. Detail Fetch: Loads full technical observations only for the specific items needed.

3. Hybrid Search (SQLite FTS5 + Chroma Vector DB)

Search queries leverage both lexical matching and vector similarity. Whether an engineer searches for an exact error string or asks conceptually about "how auth tokens are signed," the engine finds the corresponding record.

4. Real-Time Web Viewer & Privacy Controls

The engine includes a lightweight local web dashboard displaying active memory streams. Developers can inspect, edit, or remove stored observations, or wrap proprietary strings in <private> tags to exclude them from persistence.

5. Quick Installation

Claude-Mem can be installed globally or through native plugin marketplaces:

# Automated setup
npx claude-mem install

# Or inside Claude Code
/plugin marketplace add thedotmack/claude-mem
/plugin install claude-mem

Conclusion

As software engineering workflows increasingly transition to autonomous terminal agents, long-term memory becomes a foundational requirement. claude-mem provides a clean, token-efficient foundation that turns isolated coding sessions into an evolving, shared intelligence layer.

Want to eliminate session amnesia in your coding agent? Check out the Claude-Mem GitHub Repository.