agent-memory

[](https://github.com/dklymentiev/agent-memory/actions/workflows/ci.yml) [](https://goreportcard.com/report/github.com/dklymentiev/agent-memory) [](LICENSE)

Persistent memory for AI coding agents. Single binary. Zero setup. Instant search.

AI agents forget everything between sessions. You repeat context, re-explain decisions, re-describe architecture. agent-memory fixes this -- it gives your agent a persistent, searchable memory backed by a single SQLite file.

go install github.com/dklymentiev/agent-memory@latest

Every time you start a new Claude Code session, your agent starts from scratch:

• "We decided to use PostgreSQL for this" -- you've said it 5 times
• "Don't deploy on Fridays" -- the agent doesn't know
• "The auth flow uses JWT refresh tokens" -- explained it last week, gone today

# Save a decision once
agent-memory add "Auth uses JWT refresh tokens, 15min access / 7d refresh" \
  -t type:decision -t topic:auth

# Agent finds it when relevant
agent-memory search "authentication tokens"

# Or get smart context automatically at session start
agent-memory context

One binary. One SQLite file. No Docker. No external database. No configuration required.

Search that works -- FTS5 full-text search with BM25 ranking. Optional hybrid search with OpenAI embeddings (30% keyword + 70% semantic). Finds what you need even with different wording.

Workspaces -- isolate memories per project. agent-memory focus backend-api and everything stays separate.

MCP server -- 14 tools for Claude Code, Cursor, or any MCP-compatible agent. One command to set up: claude mcp add agent-memory -- agent-memory mcp

Auto-capture hooks