cd /news/ai-tools/ouija-compiler-talk-with-dead-langua… · home › topics › ai-tools › article
[ARTICLE · art-161847] src=dev.to ↗ pub= topic=ai-tools verified=true sentiment=↑ positive

Ouija Compiler: Talk with Dead Languages

A developer built Séance, a terminal app that answers questions about legacy programming languages such as COBOL, Fortran and Pascal using local open-weight models via Ollama, with a gate that rejects living languages and a retrieval step over compile-tested reference notes. Each generated program is compiled and run with the real toolchain before being shown, and failures trigger a retry-and-repair loop. The whole pipeline runs on an 8 GB Windows laptop under WSL2 with no GPU.

by read2 min views1 publishedNov 1, 2026

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine

Séance is a terminal app where you talk to the ghosts of dead programming languages. Ask how to loop in COBOL, read a file in Fortran, or build a record in Pascal, and the spirit answers in eerie prose plus a complete program. Ask about a living language and the veil stays closed: it refuses, in character.

For the theme, I wanted to honor the past: languages that people stopped teaching but whose code is still out there. A ghost that makes things up is useless, though, and small open models are shaky on obscure syntax. So every answer is checked: the code is compiled and run with a real compiler before you see it.

You > How do I loop 5 times in COBOL?

📜 Scrolls consulted (vector): Loops: PERFORM VARYING, PERFORM UNTIL, PERFORM TIMES, ...

👻 COBOL:
The candlelight flickers, casting elongated shadows across the ancient mainframes...

✅ Verified: compiled (free-format) and ran cleanly.
   Output:
   | Iteration: 00
   | Iteration: 01
   | Iteration: 02
   | Iteration: 03
   | Iteration: 04

A local AI medium that only answers questions about dead or legacy languages. It replies in spooky prose plus working code, and the code is compiled and run for real before you see it. Everything runs on your machine with open-weight models (Ollama).

question -> gate -> RAG (reference scrolls) -> local LLM -> compile & run -> (error -> retry) -> answer
File Job
gate.py Only dead languages pass. Alias match first, local-LLM classifier as fallback
rag.py Chunks knowledge/*.md , SQLite index, vector search (Ollama embeddings) with automatic offline BM25 fallback
verify.py Extracts the code block, compiles with the real toolchain, runs it with limits
seance.py The loop: retrieve, generate, verify, repair, print. Run this one
knowledge/ Reference "scrolls" for COBOL, Fortran, Pascal (every snippet is compile-tested)

… Everything runs locally on an 8 GB Windows laptop (WSL2, no GPU):

These languages are not really gone, only quiet. Summoning them felt right, and making each spirit prove its answer by actually running it felt even better.

── more in #ai-tools 4 stories · sorted by recency
── more on @séance 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ouija-compiler-talk-…] indexed:0 read:2min 2026-11-01 · —