dreamd
Local-first long-term memory for AI agents with auditable lessons and provenance.
Tested on macOS and LinuxKnown vulnerabilities
Use it
Before you install: known vulnerabilities
pickfit found 2 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.
crates:rmcp 1.7.0RMCP: Missing Resource Field Validation in OAuth Protected Resource Metadata Discovery (GHSA-33f5-2c5q-wgwj, high, fixed in 2.0.0)
See 1 more
crates:rmcp 1.7.0— GHSA-9pj6-vhgr-3mwh (high), fixed in 2.0.0
macOS arm64
install dreamd-mcp globally via npm
npm install -g dreamd-mcp
Where the README and reality differ
- README: npx -y dreamd-mcp setup works in any folder
What worked: requires project root sentinel (.git/, Cargo.toml, package.json or pyproject.toml); created git repo with git init
Check that it works
dreamd-mcp doctor 2>&1The output should contain “index_freshness:”.
First thing to try
pwd; cat package.json 2>&1 || echo no-package; git init 2>&1; ls -ladreamd-mcp setup --yes --harness none 2>&1dreamd-mcp doctor 2>&1Add it to your agent
claude mcp add dreamd -- dreamd-mcpJSON for Claude Desktop, Cursor and other clients
{
"mcpServers": {
"dreamd": {
"command": "dreamd-mcp",
"args": []
}
}
}Run dreamd-mcp setup --yes --harness none to set up the memory store, then add dreamd-mcp as an MCP server in your AI client.
Linux x86_64
install dreamd-mcp globally via npm
npm install -g dreamd-mcp
Check that it works
which dreamd-mcp; ls ~/.local/bin/dreamd* 2>&1; dreamd-mcp --help 2>&1The output should contain “dreamd-mcp — npx shim”.
First thing to try
cd /tmp/testproj && dreamd-mcp init 2>&1; echo "EXIT:$?"; ls -R .agent 2>&1 | head -n 100cd /tmp/testproj && dreamd-mcp doctor 2>&1Add it to your agent
claude mcp add dreamd -- dreamd-mcpJSON for Claude Desktop, Cursor and other clients
{
"mcpServers": {
"dreamd": {
"command": "dreamd-mcp",
"args": []
}
}
}Run dreamd-mcp setup --yes --harness none to set up the memory store, then add dreamd-mcp as an MCP server in your AI client.
What it does
- Search stored memories through MCPTested
How to use it
- Run
dreamd-mcp setup --yes --harness noneonce. - Connect your MCP client to
dreamd-mcp. - Call the
search_nodestool with aquerysuch as <your text>.
- Run
- Add new learnings through a single-writer daemonTested
How to use it
- Run
dreamd-mcp setup --yes --harness noneonce. - Connect your MCP client to
dreamd-mcp. - Call the
append_nodetool withcontent,source_harnessandskill_actionset to <your text>.
- Run
- Share one memory folder across agent harnessesNot tested
- Combine learnings into LESSONS.mdNot tested
How far pickfit got
macOS arm64
- Installs
- Connects
- 2 of 4 features work
- Works offline
Linux x86_64
- Installs
- Connects
- 2 of 4 features work
- Works offline
Other systems
Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- find which stored memories drove a recall
- remove a bad memory event and its lesson state
- verify provenance ledger consistency
- search prior agent context across sessions
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
macOS arm64
An MCP client called one of its tools
- Replayed from scratch
- Works offline
- Checked on 1 Nov 2026
- Version 1.2.0
An MCP client handshake over stdio listed 2 tools, and a call to append_node returned a result.
Differences the test machine hit
- README: npx -y dreamd-mcp setup with interactive harness prompt
In the test: in non-interactive shell use --yes --harness none to avoid TTY prompt
Linux x86_64
An MCP client called one of its tools
- Replayed from scratch
- Works offline
- Checked on 1 Nov 2026
- Version 1.2.0
An MCP client handshake over stdio listed 2 tools, and a call to append_node returned a result.
Differences the test machine hit
- README: npx -y dreamd-mcp init --yes and npx -y dreamd-mcp setup require sentinel .git/Cargo.toml/package.json/pyproject.toml
In the test: Must create sentinel project directory with git init before handshake/tools work reliably; otherwise server cannot locate project root - README: npx -y dreamd-mcp as launch command
In the test: Installed globally with npm install -g dreamd-mcp so launch is `dreamd-mcp` on PATH, avoiding npx fetch on each probe and satisfying offline replay