Project Memory runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 14 Sep 2026.
Local decisions, evidence, outcomes and reviewed lessons with bounded retrieval and an HTML viewer.
We read the source, 22 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
run=subprocess.run(python_args('memory_module.cli')+['serve','--db',str(path)],input=''.join(json.dumps(r)+'\n' for r in requests),text=True,encoding='utf-8',capture_output=True,timeout=20)
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.
run=subprocess.run(python_args('memory_module.cli')+['serve','--db',str(path)],input=''.join(json.dumps(r)+'\n' for r in requests),text=True,encoding='utf-8',capture_output=True,timeout=20)
insert = 'INSERT INTO usage_records (' + ','.join(columns) + ',recorded_at) VALUES (' + placeholders + ')'
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 project-memory -- uvx project-memory-mcp
{
"mcpServers": {
"project-memory": {
"args": [
"project-memory-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.project-memory]
command = "uvx"
args = ["project-memory-mcp"]
{
"mcpServers": {
"project-memory": {
"args": [
"project-memory-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"project-memory": {
"args": [
"project-memory-mcp"
],
"command": "uvx"
}
}
}
Read-only project readiness, dependency, evidence, and bounded local activity views.
Guarded local Charles Proxy automation and bounded XML session evidence
Dijin is a Memory Layer: recall notes, decisions, and evidence-backed answers across every AI.
Hand a project over with the reasons attached. Local-first cross-agent memory MCP + drift detection.
Local-first durable AI memory with policy-bound recall and a typed project graph.
Local-first Ownly evidence and repeatable Planner visits with preview-before-commit writes.
Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1
SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.
Answers built from our own checks of this server.