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

Update README.md
All checks were successful
ci/woodpecker/push/woodpecker Pipeline was successful
Details

Browse source
This commit is contained in:
tobi 2026-07-02 18:17:16 +00:00
parent d74b36e563
commit 28f5f897d5
1 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
README.md
View file

@ -21,13 +21,13 @@ Every codebase has unwritten conventions like the order tasks appear in Ansible
When an LLM agent needs to follow these conventions, it usually has two bad options: When an LLM agent needs to follow these conventions, it usually has two bad options:
1. **Stuff every existing file into context** — 15 Ansible roles = 5,000 tokens. You'll hit the context window by the third example. 1. **Stuff every existing file into context** - You'll hit the context window by the third example.
2. **Guess from one or two examples** — the LLM infers a pattern and often gets it wrong. 2. **Guess from one or two examples** - the LLM infers a pattern and often gets it wrong.
Dervish replaces both with a **one-call MCP tool**: pass your sequences, get back a ~60-token grammar. Dervish replaces both with a **one-call MCP tool**: pass your sequences, get back a ~60-token grammar.
By leveraging **Minimum Description Length (MDL) scoring**, Dervish treats the grammar discovery problem as an optimal compression task. the resulting rule is optimized to consume as few tokens as possible without losing the pattern. By leveraging **Minimum Description Length (MDL) scoring**, Dervish treats the grammar discovery problem as an optimal compression task. the resulting rule is optimized to consume as few tokens as possible without losing the pattern.
**Without Dervish:** token cost scales linearly with examples. **With Dervish:** one compact grammar describes them all — a ~60–200 token rule instead of thousands of tokens of raw examples. Try it out and you too will say: **Without Dervish:** token cost scales linearly with examples. **With Dervish:** one compact grammar describes them all In a ~60–200 token rule instead of thousands of tokens of raw examples. Try it out and you too will say:
<p align="center"><img src="dervish.gif" alt="Dervish animation" width="65%"></p> <p align="center"><img src="dervish.gif" alt="Dervish animation" width="65%"></p>
@ -60,7 +60,7 @@ The primary interface is a **Model Context Protocol (MCP)** server. Connect any
### Agent workflow ### Agent workflow
An LLM agent uses the MCP to discover an unwritten convention from existing examples — compressing hundreds of files into a single ~60-token rule: An LLM agent uses the MCP to discover an schema from existing examples, thereby compressing hundreds of files into a single ~60-token rule:
```text ```text
User: Generate a new Ansible role for installing PostgreSQL. User: Generate a new Ansible role for installing PostgreSQL.