Slowave
Local shared memory layer letting coding agents retain and reuse context across sessions.
Tested on Linux
Use it
Linux x86_64
You need first
- Runtimes:
python 3.11+
install slowave via pipx
pipx install slowave
Check that it works
slowave --helpThe output should contain “Usage: slowave”.
First thing to try
slowave setup --dry-runAdd it to your agent
claude mcp add slowave -- slowave-mcpJSON for Claude Desktop, Cursor and other clients
{
"mcpServers": {
"slowave": {
"command": "slowave-mcp",
"args": []
}
}
}Run slowave setup --dry-run to see how Slowave will connect to your coding agents, then use its tools (activate, remember, recall, feedback, commit) from your MCP client.
What it does
- Share memory across coding agentsNot shown working
- Save and recall memories for a taskNot shown working
- Mark useful memories with feedbackNot tested
- View memories in a local dashboardNot tested
How far pickfit got
Linux x86_64
- Installs
- Connects
- 0 of 4 features work
- Works offline
macOS and Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- reuse recorded decisions and constraints across tasks
- save facts, decisions and preferences for agents
- look up relevant memories during a task
- inspect saved memories and retrievals in dashboard
- review reusable procedures captured from previous work
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
An MCP client called one of its tools
- Replayed from scratch
- Works offline
- Checked on 1 Nov 2026
- Version 0.22.3
An MCP client handshake over stdio listed 5 tools, and a call to slowave_activate returned a result.
Differences the test machine hit
- README: slowave status --services
In the test: fails in sandbox without systemctl: Service manager unavailable