memo

memo

Your coding agent starts every session with amnesia. memo fixes that — 100% on your own machine.

Persistent, searchable memory for Claude Code, Codex, Cursor, Cline, Devin, and OpenCode. No cloud, no API keys, no Ollama, no vector DB to run. And it spends fewer tokens, not more.

---

Install

curl -fsSL https://raw.githubusercontent.com/jagoff/memo/v4.15.0/install.sh | bash

Prefer a package manager? uv tool install mlx-memo · pipx install mlx-memo · brew tap jagoff/memo && brew install mlx-memo

Then:

memo doctor                                   # self-check
memo save 'we use Postgres, not Mongo'        # save a decision
memo search 'what database did we pick?'      # search by meaning

That's it. Your agents pick it up over MCP automatically — the installer wires every client it finds.

New Mac:

curl -fsSL https://raw.githubusercontent.com/jagoff/memo/v4.15.0/install.sh | bash
memo sync bootstrap git@github.com:yourname/memo-sync.git

Agent-managed setup:

curl -fsSL https://raw.githubusercontent.com/jagoff/memo/v4.15.0/install.sh | bash
memo doctor --strict-runtime

On Linux or just want to look around first?

docker run --rm ghcr.io/jagoff/memo:latest memo doctor

---

Why this saves you money

Most memory servers add context. memo is built to remove it.

Profile	Tools	Schema tokens
agent (default)	43	~9.7k
core / slim	60	~13.2k
full / default	165	~30.6k

The default MCP surface is 43 tools, not 165 — 74% fewer tools, and about 68% less schema context: 43 tools / ~9.7k schema tokens versus 165 tools / ~30.6k tokens on the full surface — overhead paid every session, in every client.

Ambient recall injects one relevant memory before the model answers. The bundled Claude Code hook caps that injection at ~160 tokens. memo roi reports the real grounding and re-ask counts — the estimated-savings figure it used to print was removed in 4.14.0, because multiplying those counts by hardcoded constants was a savings claim memo could not support. For measured savings, memo tokens reads the provider's own usage counters through the context-compression proxy.

memo roi       # value from grounded recalls and avoided re-asks
memo tokens    # usage-savings ledger

---

Three things nothing else does

🕰️ Time-machine — query your knowledge as it was

memo as-of ask "what was the deploy strategy?" --date 2026-02-01
memo diff --from 2026-01-01 --to 2026-03-01

Full historical reconstruction by reverse-replaying history.db. Useful when you need to know why past-you made a call, not just what past-you decided.

⚡ Contradiction radar — memory that notices when you change your mind

memo contradict scan      # find conflicting facts corpus-wide
memo contradict triage    # resolve: fuse / newer-wins / dismiss

Change a decision and memo flags the now-stale version, so the agent stops reintroducing what you already threw out.

🔮 Dream — it optimizes itself while you sleep

memo dream run

A 7-phase nightly pipeline: inventory → mine signals → resolve conflicts → prune stale → synthesize cross-cluster insights → optimize → pre-warm the top-100 query embeddings so tomorrow's recall stays under 200 ms. Every run writes a receipt you can audit. Zero intervention.

---

How it works

Hybrid retrieval. A vector leg (MLX on Apple Silicon, sentence-transformers on CPU) and a BM25 leg (FTS5, diacritic-folding for Spanish) run in parallel, fuse via Reciprocal Rank Fusion, then go through an optional MLX cross-encoder rerank.

Markdown is the source of truth. Every memory is a plain .md file you can read, grep, and version-control. SQLite is a derived index that rebuilds from the files at any time — hand-edit in Obsidian and your edit wins on the next memo reindex. Nothing is locked in a database you can't open.

Prompts and memories stay on your machine. Embedder, reranker, and LLM all run in-process. No telemetry. Memory travels only if you point memo sync at a git remote you own. Normal startup is fully offline; remote update checks and auto-update require an explicit opt-in. → Privacy and network policy

Also in the box: cross-agent memo resume (reopen any session from any agent), cross-Mac git sync, a knowledge graph with optional codegraph symbol edges, encrypted secret storage, OCR/audio ingestion, evidence packs, outcome learning, signed federation, and a local chat UI over your memory (memo chat serve). → Full feature reference

---

How it compares

Verified July 2026 against each project's own docs. Corrections welcome — open an issue and I'll fix the table.

	memo	mem0	letta	cognee	basic-memory	cipher
100% local, no cloud API	✅	⚠️	⚠️	⚠️	✅	⚠️
Time-machine (rewind to any date)	✅	❌	⚠️	❌	⚠️	⚠️
Contradiction detection + resolution	✅	⚠️	⚠️	❌	❌	❌
Autonomous nightly maintenance	✅	❌	❌	❌	❌	❌
Token-economy MCP profiles	✅	❌	❌	⚠️	✅	❌
Markdown / Obsidian as source of truth	✅	❌	⚠️	❌	✅	❌

✅ first-class · ⚠️ partial, config-gated, or add-on · ❌ absent

Closest comparators are basic-memory (local-first + Obsidian + MCP — same thesis) and cipher (memory for coding agents).

---

Requirements

	Support
macOS, Apple Silicon (M1–M4)	Full — MLX embedder + reranker + ask/synthesize/dream
Linux / Ubuntu	Standalone CPU backend — search, recall, save. pipx install "mlx-memo[cpu]" · docs/ubuntu.md
Intel Mac	Unsupported — current PyTorch releases do not ship Python 3.13 wheels for this platform
Docker	Cross-platform, CPU backend · docs/docker.md

Python ≥ 3.13 (the installer handles this via uv if you don't have it). First install pulls ~8 GB of models, 5–15 min. Optional: an Obsidian vault — without one, memo uses ~/Documents/memo/.

---

Docs

Install detail, installer knobs, new-Mac migration	reference.md › Install
Per-client MCP setup (Claude Desktop, Cursor, Cline, Continue)	reference.md › MCP setup
Ambient recall, capture, and tuning	reference.md › Ambient memory
Full CLI reference (145 commands) + memo tui	reference.md › CLI
All MEMO_* flags and model profiles	reference.md › Configuration
Architecture and design notes	reference.md › Design
Privacy and network policy	PRIVACY.md

All 145 top-level CLI commands

Core: save search ask get edit rename delete list

Recall & Hooks: recall recall-hook context briefing continuity prewarm capture-tick capture-stop interject ask-gaps guard digest

Session & History: history as-of diff record-history session chat-session resume reflect mine-history episodes chronicle

Maintenance: reindex maintain review dream consolidate synthesize dedupe cross-dedup retier contradict coordinate terminal invalidate temporal compress-context ops

Analysis & Quality: health stats doctor journey-check lint drift analytics eval roi tokens token-savings usefulness gaps outcome profile confidence graduation hype definitive evidence

Knowledge Graph: graph entities entity extract-entities links version related

Advanced Search: embed rerank contextual retrieve context-pack chat chat-ask repo

Import / Export / Sync: import export backup restore sync ingest federation

Visualization: tui dashboard map logs hook-log

Setup & Config: init setup config install-mcp install-watcher uninstall-watcher install-slash install-statusline install-recall-hook install-shell-wrapper install-shims startup-banner migrate migrate-vault migrate-independence update upgrade self-update watch release onboard

Daemons: daemons recall-daemon ingest-daemon maint-daemon embed-daemon idle-daemon

Other: backend-native collaborative events feedback query mandate drift sleep-cycle operational ocr-image provenance secret verbatim mcp-command codex-badge debug-recall http-api proxy mine-git token-gate fix undo code-facts code-nudge code-health

---

Contributing

git clone https://github.com/jagoff/memo && cd memo
uv pip install -e '.[dev]'

Issues and PRs welcome — see CONTRIBUTING.md. If memo is useful to you, a ⭐ genuinely helps other people find it.

MIT licensed. Built on Apple MLX, sqlite-vec, and codegraph.