tobi/grammar-inference-engine
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

scale PNG logo to 150%

Browse source
This commit is contained in:
tobjend 2026-07-01 11:21:02 +02:00
parent 923ecfd231
commit c8a49f0149
3 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -1,6 +1,6 @@
# Dervish MCP
<p align="left"><img src="dervish-logo.png" alt="Dervish" width="120"></p>
<p align="left"><img src="dervish-logo.png" alt="Dervish" width="180"></p>
**Dervish** infers **regular expression grammars** from example sequences using the BEX family of algorithms. Given a set of example sequences (strings over some alphabet), it learns a compact regular expression that captures the general pattern.

2
SHOWCASE.md
View file

@ -1,6 +1,6 @@
# Dervish — Showcase
<p align="left"><img src="dervish-logo.png" alt="Dervish" width="120"></p>
<p align="left"><img src="dervish-logo.png" alt="Dervish" width="180"></p>
Infer the **unwritten convention** from existing examples. Given N example
sequences, produce a ~100-char grammar that captures the structural

2
blog_post.md
View file

@ -1,6 +1,6 @@
# Dervish: Discovering Unwritten Conventions with Grammar Inference
<p align="left"><img src="dervish-logo.png" alt="Dervish" width="120"></p>
<p align="left"><img src="dervish-logo.png" alt="Dervish" width="180"></p>
**How we turned 36 Ansible roles into a 200-character grammar — and why
it matters for LLM agents.**