Sieme

DevCraftXCoder/Sieme
★ 0 stars TypeScript AI/LLM Updated today
Security-focused AI data layer on Cloudflare Workers. KV cache, Vectorize semantic search over findings/CVEs/controls, per-engagement agent memory, semantic LLM triage cache, and built-in MCP server. TypeScript + Hono, zero cold starts.
View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "sieme": {
      "command": "npx",
      "args": [
        "-y",
        "DevCraftXCoder/Sieme"
      ]
    }
  }
}

README Excerpt

Security AI data layer on Cloudflare Workers. Purpose-built for AI security agents — combines fast KV scratch cache, semantic vector search over findings, per-engagement agent memory, and a similarity-based LLM triage cache. Exposes both a REST API and a built-in MCP server so Claude/AI agents can read, write, and search security data directly.

Tools (11)

cache_statsengagement_listengagement_openengagement_recallengagement_rememberengagement_reportfinding_searchfinding_storesec_cache_getsec_cache_setsemantic_triage