Heartwood Memory — governed memory for AI agents runs on your own machine — the client starts it, so there is no endpoint to ping. 209 installs a week from pypi. Last commit 22 Oct 2026.
Heartwood Memory — governed AI agent memory; signed provenance. BUSL-1.1; not OSI open source.
We read the source, 2 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
proc = subprocess.run(
_VALID_BUCKET = "valid_ed25519"
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add heartwood-memory -e 'HEARTWOOD_DB_PATH=<HEARTWOOD_DB_PATH>' -- uvx heartwood-memory
{
"mcpServers": {
"heartwood-memory": {
"command": "uvx",
"args": [
"heartwood-memory"
],
"env": {
"HEARTWOOD_DB_PATH": "<HEARTWOOD_DB_PATH>"
}
}
}
}
[mcp_servers.heartwood-memory]
command = "uvx"
args = ["heartwood-memory"]
env = { HEARTWOOD_DB_PATH = "<HEARTWOOD_DB_PATH>" }
{
"mcpServers": {
"heartwood-memory": {
"command": "uvx",
"args": [
"heartwood-memory"
],
"env": {
"HEARTWOOD_DB_PATH": "<HEARTWOOD_DB_PATH>"
}
}
}
}
{
"servers": {
"heartwood-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"heartwood-memory"
],
"env": {
"HEARTWOOD_DB_PATH": "<HEARTWOOD_DB_PATH>"
}
}
}
}
Put your own value in place of
<HEARTWOOD_DB_PATH> (Path to the local Heartwood SQLite database).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
HEARTWOOD_TENANT (Tenant identifier used to isolate memories), HEARTWOOD_MCP_ALLOWED_TOOLS (Comma-separated MCP tool allowlist; the default is read-only).
Shared, governed memory for fleets of AI agents: judged contributions, provenance, operator control
Governance runtime for AI agents with signed provenance, compliance audits, and OSINT.
Provenance-aware memory format for AI agents: every claim carries its source, age and boundary.
Signed, hash-chained provenance receipts for AI agent actions.
Open-source causal memory for AI agents: persistent, explainable, MCP-native memory (13 tools).
Open-source governance for MCP agents: useful autonomy without unlimited authority
Trust OS for AI agents: governed memory, payments, reputation, approvals, and audit evidence.
Find real, verifiable businesses with provenance and source URLs - for AI agents.
Answers built from our own checks of this server.