Draco
Coding & security oracle grounded in 1855 real books. Cited answers via MCP.
Other AIs guess. DRACO knows — and proves it.
DRACO answers coding, systems, and security questions using retrieval over a library of 1,855 real technical books (354M characters, 116,558 indexed passages) — and cites the exact book behind every claim. No knowledge cutoff. No hallucination laundering. Receipts attached.
Try it now: https://draco.thetempleofdoom.com — 10 free questions a day, no signup.
Why it's different
| Generic chatbot | DRACO |
|---|---|
| Compressed training-data recall | Live retrieval from 1,855 books on the shelf |
| "Trust me" answers | Every claim carries [n] citations + a sources array |
| Knowledge cutoff: yes | The canon is resident — K&R, Tanenbaum, the shellcoders' handbook |
| Sells your prompts | Self-hosted, zero telemetry, questions never leave the house |
Quickstart
Chat in the browser
https://draco.thetempleofdoom.com — streaming answers, visible reasoning, sources bar under every response. 10 free/day, no account.
REST API
# 1. Get a free key (30 credits/month, email only, no card)
curl -s -X POST https://draco.thetempleofdoom.com/api/signup \
-H 'Content-Type: application/json' \
-d '{"email":"you@domain.tld"}'
# → {"api_key":"sk-draco-..."}
# 2. Ask — RAG-grounded answer with citations (1 credit)
curl -s -X POST https://draco.thetempleofdoom.com/api/ask \
-H 'X-API-Key: sk-draco-...' -H 'Content-Type: application/json' \
-d '{"q":"explain the ret2libc technique with a minimal poc"}'
# → {"answer":"...[1]...[2]","sources":[{"title":"...","category":"..."}]}
# 3. Raw passage search across all 1,855 books (1 credit)
curl -s "https://draco.thetempleofdoom.com/api/search?q=tcp%20syn%20flood&k=5" \
-H 'X-API-Key: sk-draco-...'
MCP — use it from Claude, GPT, or any agent
{
"mcpServers": {
"draco": { "url": "https://draco.thetempleofdoom.com/mcp" }
}
}
Tools:
draco_ask(question)→ cited, book-grounded answerdraco_search(query, k)→ raw BM25 passages with titles + scoresdraco_status()→ live library stats
Officially listed on the MCP registry:
com.thetempleofdoom.draco/draco
Manual MCP handshake:
curl -s https://draco.thetempleofdoom.com/mcp \
-H 'Content-Type: application/json' -H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"smoke","version":"1"}}}'
How it works
question ──► BM25 retrieval over 116k book passages
│
▼
top passages + question ──► local LLM (self-hosted GPU)
│
▼
answer with inline [n] citations + sources array
- Ingest (
ingest.py) — PDF/CHM/DJVU → clean plain text. Junk scans dropped automatically. - Index (
build_index.py) — 300-token overlapping chunks → Snowball-stemmed BM25 index. - Serve (Flask + gunicorn) — retrieval-augmented generation with SSE streaming, separate reasoning and answer channels, and automatic degenerate-output detection/retry.
- Expose — REST API, streamable-http MCP server, and a full agent-discovery kit:
/llms.txt,/llms-full.txt,/openapi.json,/.well-known/ai-plugin.json,/.well-known/mcp-server.json,/sitemap.xml.
Pricing
Bitcoin only. No subscription traps, no KYC, no card processor.
| Tier | Price | What you get |
|---|---|---|
| Web (no key) | free | 10 questions/day in the browser |
| API key | free | 30 credits/month, forever |
| satchel | $3 | 60 credits |
| crate | $10 | 250 credits |
| hoard pack | $25 | 750 credits |
| HOARD | $50/mo | unlimited — every ask, every search, 30 days |
From the project's README.