slowave

Living memory layer across your AI tools.

AI agents have large context windows, but that context ends with your current session. Open a new session, switch from Claude Code to Codex, and you reconstruct the same decisions, constraints, and failed attempts.

Slowave gives your agents one local, shared memory. The agent decides what is worth preserving. Slowave keeps it scoped, retrievable, auditable over time.

Keep context across tasks: Your agents can reuse recorded decisions, preferences, constraints, and lessons instead of making you repeat them.
Improves with use: Useful memories strengthen, irrelevant ones lose priority, stale knowledge can be suppressed or superseded.
Learns from experience: Decisions, outcomes, and multi-step solutions can become reusable memories and procedures.
Runs locally: Slowave stores memory in SQLite and does not send it to a hosted memory service.
No LLM API key: The memory core performs maintenance and retrieval without LLM calls or an LLM API key.
Inspectable: Review memories, retrievals, feedback, procedures, and system activity in the local dashboard.

Supported integrations include Claude Code, Codex, Cursor, Cline, Windsurf / Devin Desktop, OpenCode, and Claude Desktop. See platform coverage and manual steps.

Why Slowave?

Every new agent session has the codebase but not necessarily the full context behind it: your previous interactions with your agent, your decisions, your thinking process.

The missing context is what makes an agent repeat a rejected design, miss an operational constraint, or make you explain (again and again) the project principles.

Slowave turns those durable judgments into a shared project memory.

It is not a markdown-transcript-replay system and it is not another LLM layer on top of your agent.

Slowave maintains your memory locally with brain-inspired algorithms without LLM calls.

It returns a bounded working set, keeps it within scope, and records feedback about whether it was useful or out of date. Your LLM agent remains responsible for reasoning.

Install Slowave if you feel you're missing the continuity in your daily work with your LLM agent.

The first useful payoff is simply not having to repeat the same constraint in the next task.

Over time, the way you work becomes reusable context for your agent.

Installation

Quick start

pipx install slowave
slowave setup --dry-run
slowave setup

The quick start configures every detected client. To configure just one client at a time, see the installation reference.

[!IMPORTANT] No LLM API key required.

To remove Slowave, see the removal guide.

What changes in your workflow?

Slowave is transparent to your work.

You still ask your agent to do normal work: fix a regression, add a migration, review a pull request. When it encounters a durable fact or decision, the installed lifecycle instructs your agent to preserve that claim. On a later task, Slowave can return a compact, scoped set of relevant recorded memories to your agent, so that it can act upon its own memories.

What you will see while working with your agent:

your agent activating Slowave for the current task and goal,
Slowave retrieving relevant context to your agent,
your agent sending feedback to Slowave on what was retrieved.
your agent committing a Slowave session.

Optionally you will see:

your agent invoking Slowave to remember durable facts.
your agent invoking Slowave to recall something critical for the current task or goal.

Slowave does not decide whether a claim is true or important. Your agent makes that judgment and reports whether retrieved memory helped, was irrelevant, or became stale. Slowave maintains the resulting local memory.

Dashboard

Start the local dashboard with:

slowave dashboard

Opens the dashboard in your browser, where you can inspect:

Memories: browse saved decisions, constraints, and lessons.
Procedures: review reusable step-by-step methods from past work.
Retrievals: see what memory Slowave returned for each task.
Activity: follow recent sessions, memory updates, and feedback.
Memory graph: explore connections between related memories.
System health: check the database, worker, backups, and local services.

Supported clients

Client coverage is actively expanding. 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	✅	✅	✅	`slowave setup --client windsurf`
Claude Desktop	✅	✅	✅	`slowave setup --client claude-desktop` ¹
OpenCode	✅	✅	✅	`slowave setup --client opencode`
Codex	✅	✅	✅	`slowave setup --client codex`
All the above				`slowave setup`

¹ requires one manual paste after setup

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

Memory is stored in plaintext in the current OS user's application-data directory. Slowave does not send it to a hosted memory service. See runtime data and migration.

How Slowave memory works

Slowave works through 5 simple MCP tools:

Activate: start a task and load relevant memory.
Remember: save a fact, decision, preference, or instruction.
Recall: search memory during a task.
Feedback: mark retrieved memory as useful, irrelevant, or stale.
Commit: save the task outcome and any reusable procedure.

A background worker consolidates relevant memories and procedures.

See architecture.md and design.md for more details.

Slowave MCP lifecycle

flowchart LR
    A[Agent task] --> B[1. <i>activate</i><br/>start session]
    B --> C[Scoped retrieval<br/>and session]
    C --> D[Agent reasoning]
    D --> E[2. <i>remember</i><br/>durable claims]
    D --> F[3. <i>recall</i><br/>mid-task lookup]
    C --> G[4. <i>feedback</i><br/>target assessments]
    F --> G
    E --> H[5. <i>commit</i><br/>outcome and verification]
    G --> H
    H --> I[(Local SQLite<br/>raw events and evidence)]
    I --> J[Offline consolidation]
    J --> K[(Episodes, prototypes,<br/>schemas, relations)]
    K --> C

See architecture.md and design.md for details.

Boundaries

Slowave is a memory layer, not a reasoning engine.
It cannot recall information that was never recorded.
It supplies relevant context, but the connected agent decides how to interpret and use it.
Memory quality depends on the client agent and the feedback it provides.
Scopes reduce accidental context leakage; use separate stores when hard isolation is required.
Slowave adds token overhead from tool calls and retrieved context.
The local SQLite database is plaintext by default; protect it with OS permissions or full-disk encryption.
Slowave is public beta software. APIs, configuration, and storage schema may change, and migrations are not guaranteed before stable release.

Evaluation

The current evaluation notes report preliminary retrieval-evidence results, methodology, limitations, and commands for running new evaluations. They do not claim end-to-end agent accuracy or a comparison against other memory systems. See benchmarks.md before treating any result as a production-quality claim.

Documentation

Mintlify: full auto-generated documentation
design.md: design rationale, boundaries, and positioning
architecture.md: brain-inspired memory model and lifecycle
install.md: installation, setup, lifecycle instructions, modified files, and removal
benchmarks.md: benchmark results, methodology, and reproduction
troubleshooting.md: daemon, worker, dashboard, client integration, database, backup/restore

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.

Release files for slowave 0.19.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for slowave 0.19.1
File	Size	Uploaded
slowave-0.19.1.tar.gz	631.2 kB	Sep 10, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for slowave 0.19.1
File	Interpreter	ABI	Platform	Reset
slowave-0.19.1-py3-none-any.whl 649.1 kB Sep 10, 2026	Python 3	none	any	Details

Total release size: 1.3 MB

Release files / slowave-0.19.1.tar.gz

Download URL	slowave-0.19.1.tar.gz
Size	631.2 kB
Tags	Source
SHA-256 checksum How to use checksums	`ecf843b496b2982675741b5eeca3adb49be16356aa5ba00ed88f856022d452f7`
BLAKE2b-256 checksum How to use checksums	`f8bc3cef09fc193f4e33f74fe36772dae95c2807f2d3678eecba37c6d2d337da`
Upload date	Sep 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.14`

Release files / slowave-0.19.1-py3-none-any.whl

Download URL	slowave-0.19.1-py3-none-any.whl
Size	649.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`6b90afd00a27fbc20717a56fe076a35ce98da52fdb0df9a453836298a73217d5`
BLAKE2b-256 checksum How to use checksums	`7367a824683e2cb63ac3df256b0ea8e2732215ba5690685bef7b7a08296ab1b3`
Upload date	Sep 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.14`