v0.1 · open source · MIT

Local-first memory
for AI agents.

Dream auto-extracts your session history from Claude Code, Codex, and Cursor into a unified local SQLite store. Agents recall your past context over MCP and lifecycle hooks — you never have to say "remember that" again. Single static Go binary. No API key. No cloud.

How it works

Three primitives. Plug into any coding agent.

Auto-ingest from your agents

Watches Claude Code, Codex, and Cursor session files as they're written. Extracts conversations, tool calls, and code edits — no copy-paste, no manual annotation, no MCP server you have to manage. Just runs.

One unified SQLite store

All your agent history in one queryable file. Quantized ONNX all-MiniLM-L6-v2 embeddings live next to the rows; nothing leaves your machine. ~57 MiB of local assets, no network at query time.

Recall via MCP + hooks

Exposes recall as an MCP tool. Plugs into Claude Code lifecycle hooks so your past context surfaces automatically at session start. Drop-in for any agent that speaks MCP.

Retrieval quality

Measured on LongMemEval cleaned, 50 dev / 450 held-out, reproducible from the repo.

Metric Local only
(no API key)
+ LLM rerank
(top-10)
R@5 (held-out 450) 98.9% 98.9%
R@10 (held-out 450) 99.1% 99.1%
R@1 (held-out 450) 87.1% 93.3%

The 98.9% R@5 is the no-LLM result — what you get with make setup and no extra config. To our knowledge it sits at or above the highest published held-out R@5 for any local-first memory system on this dataset. Adding a Haiku rerank pass over the top-10 fused candidates lifts R@1 by +6.2pp without changing R@5 — useful when the consuming agent reads only the #1 hit.

Give your agent a memory you control.

Install in one command. Runs offline. Free and open source.