MCP Directory
Back

OpenLore

by clay-good · TypeScript · ★ 178

Deterministic, local-first memory & governance for AI coding agents.

#adr#agentic-workflows#ai-agents#call-graph#code-navigation#codebase-analysis#coding-agents#dead-code-detection#developer-tools#infrastructure-as-code#knowledge-graph#living-documentation#llm-tools#mcp-server#model-context-protocol#scip#software-architecture#static-analysis#test-impact-analysis#tree-sitter

Install

npx -y github:clay-good/OpenLore

Auto-generated from the repo's primary language — check the repo's own README for its exact install instructions.

Claude Desktop config

A starting point for your claude_desktop_config.json (auto-generated — the repo's README may specify a published package name or required env vars):

{
  "mcpServers": {
    "openlore": {
      "command": "npx",
      "args": [
        "-y",
        "github:clay-good/OpenLore"
      ]
    }
  }
}

From the README

OpenLore Deterministic, local-first memory & governance for AI coding agents. Stop your agent re-reading the same files every task — one call returns the code a task touches and the risk of changing it. No API key, no LLM in the hot path. =22.5"> The whole lifecycle on a real repo, straight from the terminal — no edits, no narration. Set up in one command (openlore install, no API key); then memory — orient finds the code a task touches; governance — blast-radius flags a risky change before you commit; proof — prove projects the payoff on your own…
Read full README on GitHub →

Related ai & ml servers