slowave 0.1.13

Brain-inspired long-term memory for AI agents — zero LLM during ingest or retrieval

Slowave

A second brain for your AI, shared across every tool you use.

Slowave gives your AI private, local memory that persists across sessions, evolves over time, and costs nothing to run — no API key, no LLM calls, no data leaving your machine.

Why Slowave?

👊 One memory for every AI tool.
Claude Code, Cline, Claude Desktop, chatbots, and other MCP-compatible clients can all read from the same local memory store. Your context follows you across tools, sessions, and workflows instead of being trapped inside one chat.

🌱 Memory that evolves with you.
Slowave does not just pile up notes. Frequently recalled memories become stronger, stale information fades, and contradicted facts can be superseded. The result is a memory system that stays useful over time without constant manual cleanup.

💰 Save tokens instead of replaying history.
Slowave replaces unbounded chat-history replay with a compact working-memory brief. In a 10-session test, raw history grew from 93 → 962 tokens, while Slowave stayed constant at around 103 tokens — roughly 80% fewer tokens. Measured, not claimed. See the test →

🔒 Zero LLM calls in the memory loop.
Ingestion, consolidation, and recall run locally using embeddings, FAISS, SQLite, and deterministic geometry — not an LLM. No API key is required, and no cloud memory backend is needed by default.

Install

pipx install slowave
slowave setup

slowave setup detects your platform, wires every client it finds, injects lifecycle hooks, and starts the background worker. Safe to re-run.

[!IMPORTANT] Claude Desktop: after setup, paste the lifecycle block into Settings → General → Instructions for Claude. slowave setup prints the exact text and settings path.

slowave doctor   # verify installation
slowave stats    # memory snapshot

Memory is stored at ~/.slowave/slowave.db. No Ollama, no vector database, no cloud service required.

Full install guide →

What Slowave remembers

Anything that should survive across sessions: preferences, decisions, constraints, lessons learned, open questions, and reusable workflows — for work, research, or personal use. Each memory carries a timestamp, decays if never recalled, and strengthens when it proves useful. Contradictions are detected geometrically and old facts are superseded automatically — no LLM required.

Memory is scoped flexibly: project:my-app, domain:cooking, relationship:alex — or unscoped for universal context.

Benchmarks

Alpha-stage numbers. Internal runs, not independently verified. See docs/benchmarks.md for per-category results, run conditions, and known gaps.

Benchmark	n	Score	LLM calls
LongMemEval	500	70.0%	0
LoCoMo	1 986	81.87%	0
DMR (MSC Self-Instruct)	500	90.2%	0

Keyword hit-rate metric. Local Mac M-series CPU. No API key.

Documentation

docs/install.md	Install, setup, per-client wiring, troubleshooting
docs/architecture.md	How memory consolidation works
docs/benchmarks.md	Per-category results, known gaps, reproducibility
docs/token_efficiency.md	Token efficiency vs. history replay and static knowledge files
docs/limitations.md	Honest limits: scale, language, unsolved categories
docs/cli.md	CLI reference
docs/dashboard.md	Local web UI (slowave dashboard)

Contributing

Slowave is open source under AGPL-3.0-or-later. Bug reports, install feedback, and focused improvements are welcome — read CONTRIBUTING.md before opening a PR. Commercial licensing terms may be offered in the future.