OpenLore
Deterministic local-first knowledge graph and guardrails for AI coding agents to orient tasks and certify changes without LLM in hot path.
Tested on LinuxKnown vulnerabilities
Use it
Before you install: known vulnerabilities
pickfit found 3 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.
npm:sharp 0.33.5sharp inherited vulnerabilities in libvips: CVE-2026-33327, CVE-2026-33328, CVE-2026-35590, CVE-2026-35591 (GHSA-f88m-g3jw-g9cj, high, fixed in 0.35.0)
See 2 more
npm:sharp 0.33.5— GHSA-rgj7-g3m4-5g8c (high), fixed in 0.35.4npm:sharp 0.33.5— GHSA-wq5f-xc86-pv6w (high), fixed in 0.35.5
Linux x86_64
You need first
- Runtimes:
node >=22.22
npm install -g openlore
npm install -g openlore
Check that it works
openlore --versionThe output should contain “3.5.0”.
Add it to your agent
claude mcp add openlore -- openlore mcpJSON for Claude Desktop, Cursor and other clients
{
"mcpServers": {
"openlore": {
"command": "openlore",
"args": [
"mcp"
]
}
}
}What it does
Good for
- orient coding agent to relevant functions and callers for a task
- certify breaking changes and impact of a diff before merge
How far pickfit got
Linux x86_64
- Installs
- Connects
- A tool call works
- Works offline
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 2 Nov 2026
- Version 3.5.0
An MCP client handshake over stdio listed 15 tools, and a call to search_code returned a result.