PyPI Python PyPI Status License: AGPL-3.0-or-later

Slowave

A living local memory layer across your AI tools.

  • Slowave keeps useful decisions, preferences, context, procedures, while lets stale memories fade.
  • Slowave evolves over time, following your experience and decisions.
  • Slowave is 100% local. Inspectable through a local dashboard.
  • No LLM API key required.

How it feels

You work daily with your AI tools:

  • Day 1 — cold start: Slowave bootstraps memory, initializing the embedding-based memory state.
  • Week 1 — emerging patterns: new interactions begin reinforcing relevant signals, forming stable associations.
  • Month 1 — context consolidates: frequently reinforced information becomes consistently retrievable, low-signal data fades.

Multiple AI clients continuously build and reuse the same evolving memory over time:

  • no markdown management
  • no static RAG
  • no LLM extra calls

What you gain over time

Slowave becomes more useful the more you use it.

  • Continuity — pick up projects where you left off
  • Clarity — your AI understands you without repeated explanation
  • Consistency — keep your context across AI tools
  • Retention — retain decisions, patterns, and preferences over time
  • Focus — spend time creating instead of managing context

Slowave does not just store information — it compounds it into usable context.

The result is a continuous working context that follows you across tools and time.

Installation

Setup all clients in one go

Install Slowave and configure every detected client in one go:

pipx install slowave

Then wire everything up:

slowave setup --dry-run   # preview what will change
slowave setup             # apply: MCP configs, lifecycle instructions, hooks, services
slowave doctor            # verify: daemon health, client detection

slowave setup is idempotent and safe to run multiple times. The HTTP MCP daemon and background consolidation worker start automatically as system services.

[!IMPORTANT] Public beta. APIs and the storage schema may change, and migrations are not guaranteed before a stable release. Your memory lives in a local plaintext SQLite database by default; protect it with OS permissions or full-disk encryption.

Per-client setup

To configure a single client, or to find client-specific details:

Client Integration doc
Claude Code integrations/claude-code/README.md
Claude Desktop ¹ integrations/claude-desktop/README.md
Cline integrations/cline/README.md
Cursor ¹ integrations/cursor/README.md
OpenCode integrations/opencode/README.md
Windsurf integrations/windsurf/README.md
Codex integrations/codex/README.md
Gemini CLI coming soon

¹ requires one manual paste after setup

See the complete install & setup reference: docs/install.md

Storage

The default embedding model downloads from Hugging Face on first use (~45 MB, cached locally). Subsequent runs work offline.

Memory is stored in a local SQLite database at ~/.slowave/slowave.db — fully inspectable, never leaves your machine. Not encrypted by default; protect sensitive data with OS permissions or full-disk encryption.

Why Slowave is different

Slowave is a local, feedback-driven long-term memory layer for AI agents — not a transcript replay, static RAG file, or LLM summarization pipeline.

  • Local and model-independent — memory stays in a local SQLite database; it needs no memory-service API key or internal LLM calls.
  • Shared across clients — one scoped store provides continuity across supported MCP tools.
  • Adaptive, not append-only — explicit feedback can reinforce useful memory, suppress noise, and record stale or superseded information with provenance.
  • Selective context — Slowave retrieves a compact, task-relevant brief instead of replaying conversation history.
  • Inspectable and controllable — you can inspect evidence, review retrievals, and suppress a memory; execution-backed procedures preserve reusable work patterns.

The architecture draws inspiration from episodic memory, offline consolidation, and associative recall. Read the design rationale or architecture guide for the full model.

Dashboard

Monitor Slowave’s memory health, incoming events and memory consolidation in real time.

Dashboard overview Memory detail Retrieval Memory graph

Supported clients

Work in progress — suggest more integrations or report broken ones with setup details.

✅ = manually verified · ⬜ = pending verification

Client macOS Linux Windows Setup
Claude Code ✅ ✅ ✅ slowave setup --client claude-code
Cline ✅ ✅ ✅ slowave setup --client cline
Cursor ✅ ✅ ✅ slowave setup --client cursor ¹
Windsurf (Devin) ✅ ✅ ✅ slowave setup --client windsurf
Claude Desktop ✅ ✅ ✅ slowave setup --client claude-desktop ¹
OpenCode ✅ ✅ ✅ slowave setup --client opencode
Codex ✅ ✅ ✅ slowave setup --client codex
Gemini CLI ⬜ ⬜ ⬜ slowave setup --client gemini
All the above slowave setup

¹ requires one manual paste after setup

Honest limits

  • It recalls stored information; it does not infer missing preferences.
  • It retrieves relevant memories; it does not perform reasoning.
  • Memory quality (definition, feedback, classification, etc) depend on your agent capabilities.

Documentation

  • design.md — design rationale, boundaries, and positioning
  • architecture.md — brain-inspired memory model and lifecycle
  • install.md — install & setup reference, lifecycle block, files modified

Contributing

Slowave is open source under the AGPL-3.0-or-later license.

Contributions are welcome, especially in:

  • client integrations
  • recall quality improvements
  • evaluation datasets
  • performance optimization

See CONTRIBUTING.md before submitting a pull request.

License

Slowave is open source under the GNU AGPL-3.0-or-later license.

Project links

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.18.1)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for mrsalty from gravatar.com mrsalty

Credits

Author: mrsalty

License

AGPL-3.0-or-later

Requires

Python >=3.11

Provides Extra

test http dev

Tags

memory agent ai mcp neuroscience rag llm

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

slowave-0.17.0.tar.gz (366.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

slowave-0.17.0-py3-none-any.whl (385.8 kB view details)

Uploaded Python 3

File details

Details for the file slowave-0.17.0.tar.gz.

File metadata

  • Download URL: slowave-0.17.0.tar.gz
  • Upload date:
  • Size: 366.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.14

File hashes

Hashes for slowave-0.17.0.tar.gz
Algorithm Hash digest
SHA256 97ce816e0cdfb02eeddd5413c946af78f71d92be2676c341be72cd69c3b44c11
MD5 f1d338aeaddd7a5fa66d84c6ce568137
BLAKE2b-256 339274091833a354b55ab29c1d75cf3c02a365c6e75b028e4d01df94698a9689

See more details on using hashes here.

File details

Details for the file slowave-0.17.0-py3-none-any.whl.

File metadata

  • Download URL: slowave-0.17.0-py3-none-any.whl
  • Upload date:
  • Size: 385.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.14

File hashes

Hashes for slowave-0.17.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f1f480bffe686f0c692322325864d12b0d0970221ef9d1f6d176df73cab23b18
MD5 265d05e1ba2211af1e5a62d099a34ae5
BLAKE2b-256 30765d65bb7bfe46efec9d542797bd42d243500434a3f864605211dd6565d4e0

See more details on using hashes here.

Release history Release notifications | RSS feed

0.18.1

2 files

0.18.0

2 files

0.17.5

2 files

0.17.4

2 files

0.17.3

2 files

0.17.2

2 files

0.17.1

2 files

This release

0.17.0 This release

2 files

0.16.4

2 files

0.16.3

2 files

0.16.2

2 files

0.16.1

2 files

0.16.0

2 files

0.15.6

2 files

0.15.5

2 files

0.15.4

2 files

0.15.3

2 files

0.15.2

2 files

0.15.1

2 files

0.14.4

2 files

0.14.3

2 files

0.14.2

2 files

0.14.1

2 files

0.14.0

2 files

0.13.1

2 files

0.13.0

2 files

0.12.1

2 files

0.12.0

2 files

0.11.1

2 files

0.11.0

2 files

0.10.0

2 files

0.9.4

2 files

0.9.3

2 files

0.9.2

2 files

0.9.1

2 files

0.9.0

2 files

0.8.2

2 files

0.8.1

2 files

0.8.0

2 files

0.7.0

2 files

0.6.1

2 files

0.6.0

2 files

0.5.11

2 files

0.5.10

2 files

0.5.9

2 files

0.5.8

2 files

0.5.7

2 files

0.5.6

2 files

0.5.4

2 files

0.5.3

2 files

0.5.2

2 files

0.5.1

2 files

0.4.9

2 files

0.4.8

2 files

0.4.7

2 files

0.4.6

2 files

0.4.5

2 files

0.4.4

2 files

0.4.2

2 files

0.4.1

2 files

0.4.0

2 files

0.3.0

2 files

0.2.0

2 files

0.1.18

2 files

0.1.17

2 files

0.1.16

2 files

0.1.15

2 files

0.1.14

2 files

0.1.13

2 files

0.1.12

2 files

0.1.11

2 files

0.1.10

2 files

0.1.9

2 files

0.1.8

2 files

0.1.7

2 files

0.1.6

2 files

0.1.5

2 files

0.1.3

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page