Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A language for constraint-guided and efficient LLM programming.
| Date | Stars |
|---|---|
| 2026-07-31 | 4202 |
| 2026-08-01 | 4202 |
| 2026-08-03 | 4202 |
| 2026-08-06 | 4202 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<a href="https://lmql.ai">
<img src="https://raw.githubusercontent.com/eth-sri/lmql/web/lmql.svg" alt="Logo" width="80" height="80">
</a>
<h3 align="center">LMQL</h3>
<p align="center">
A programming language for large language models.
<br />
<a href="https://lmql.ai/docs"><strong>Documentation »</strong></a>
<br />
<br />
<a href="https://lmql.ai">Explore Examples</a>
·
<a href="https://lmql.ai/playground">Playground IDE</a>
·
<a href="https://github.com/eth-sri/lmql/issues">Report Bug</a>
<br/>
<br/>
<a href="https://discord.gg/7eJP4fcyNT"><img src="https://img.shields.io/discord/1091288833997410414?style=plastic&logo=discord&color=blueviolet&logoColor=white" height=18/></a>
<a href="https://badge.fury.io/py/Lmql"><img src="https://badge.fury.io/py/Lmql.svg?cacheSeconds=3600" alt="PyPI version" height=18></a>
</p>
</div>
LMQL is a programming language for large language models (LLMs) based on a *superset of Python*. LMQL offers a novel way of interweaving traditional programming with the ability to call LLMs in your code. It goes beyond traditional templating languages by integrating LLM interaction natively at the level of your program code.
> <img width="200pt" alt="image" src="https://github.com/eth-sri/lmql/assets/17903049/bfa7ecf5-847b-47d0-9160-f8596aa47749"> <br/>Help us shape the next major version of LMQL by filling out the LMQL developer survey: https://forms.gle/pGvAicNpUhS1rAkK9
## Explore LMQL
An LMQL program reads like standard Python, but top-level strings are interpreted as query strings: They are passed to an LLM, where template variables like `[GREETINGS]` are automatically completed by the model:
```python
"Greet LMQL:[GREETINGS]\n" where stops_at(GREETINGS, ".") and not "\n" in GREETINGS
if "Hi there" in GREETINGS:
"Can you reformulate your greeting in the speech of \
victorian-era English: [VIC_GREETINGS]\n" where stops_at(VIC_GREETINGS, ".")
"Analyse what part of this response makes it typically victorian:\n"
for i in range(4):
"-[THOUGHT]\n" where stops_at(THOUGHT, ".")
"To summarize:[SUMMARY]"
```
Program Output:
<div align="center">
<img src="https://github.com/eth-sri/lmql/assets/17903049/243176f1-dfd4-4129-a59e-ca3dee068295"/>
<br/>
</div>
LMQL allows you to express programs that contain both, traditional algorithmic logic, and LLM calls.
At any point during execution, you can prompt an LLM on program variables in combination with standard natural language prompting, to leverage model reasoning capabilities in the context of your program.
To better control LLM behavior, you can use the `where` keyword to specify constraints and data types of the generated text. This enables guidance of the model's reasoning process, and constraining of intermediate outputs using an [expressive constraint language](https://lmql.ai/docs/language/constraints.html).
Beyond this linear form of scripting, LMQL also supports a number of decoding algorithms to execute your program, such as `argmax`, `sample` or even advanced branching decoders like [beam search and `best_k`](https://lmql.ai/docs/language/decoding.html).
Learn more about LMQL by exploring thne **[Example Showcase](https://lmql.ai)**, by running your own programs in our **[browser-based Playground IDE](https://lmql.ai/playground)** or by reading the **[documentation](https://lmql.ai/docs)**.
## Feature Overview
LMQL is designed to make working with language models like OpenAI and 🤗 Transformers more efficient and powerful through its advanced functionality, including multi-variable templates, conditional distributions, constraints, datatypes and control flow.
- [X] **Python Syntax**: Write your queries using [familiar Python syntax](https://lmql.ai/docs/language/overview.html), fully integrated with your Python environment (classes, variable captures, etc.)
- [X] **Rich Control-Flow**: LMQL offers full Python support, enabling Excerpt of 10,065 characters
Read on GitHub
Luca Beurer-Kellner · Switzerland
660
Marc Fischer · Snyk · Switzerland
32
20
8
7
5
4
EPFL · Switzerland
3
Markus · hercules.ai · Germany
2
United States
2
2
2
Göran Sandström · Sweden
2
Khush Chopra
2
bleugreen
2
2
1
Theodore Rolle · Google · United States
1
Robert Caulk · Emergent Methods
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1c8e68085d53592a, topic:language-model
matched fp:1c8e68085d53592a, topic:chatgpt