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 guidance language for controlling large language models.
| Date | Stars |
|---|---|
| 2026-07-31 | 21698 |
| 2026-08-01 | 21698 |
| 2026-08-02 | 21700 |
| 2026-08-06 | 21700 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="right"> <a href="https://discord.gg/cjPfAK43dz"><img src="https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white" alt="Discord"></a> <a href="mailto:[email protected]"><img src="https://img.shields.io/badge/Email-guidanceai%40microsoft.com-0078D4?logo=microsoft-outlook&logoColor=white" alt="Email"></a> <img src="https://img.shields.io/badge/Hours-10am--2pm%20Pacific-gray" alt="Hours"> </div> <div align="center"><picture> <source media="(prefers-color-scheme: dark)" srcset="docs/figures/guidance_logo_blue_dark.svg"> <img alt="guidance" src="docs/figures/guidance_logo_blue.svg" width=300"> </picture></div> <br/> **Guidance is an efficient programming paradigm for steering language models.** With Guidance, you can control how output is structured and get high-quality output for your use case—*while reducing latency and cost vs. conventional prompting or fine-tuning.* It allows users to constrain generation (e.g. with regex and CFGs) as well as to interleave control (conditionals, loops, tool use) and generation seamlessly. * [Install](#install) * [Features](#features) ## Install Guidance is available through PyPI and supports a variety of backends (Transformers, llama.cpp, OpenAI, etc.). If you already have the backend required for your model, you can simply run ```bash pip install guidance ``` ## Features ### A Pythonic interface for language models When using Guidance, you can work with large language models using common Python idioms: ```python from guidance import system, user, assistant, gen from guidance.models import Transformers # Could also do LlamaCpp or many other models phi_lm = Transformers("microsoft/Phi-4-mini-instruct") # Model objects are immutable, so this is a copy lm = phi_lm with system(): lm += "You are a helpful assistant" with user(): lm += "Hello. What is your name?" with assistant(): lm += gen(max_tokens=20) print(lm) ``` If run at the command line, this will produce output like: ``` <|system|>You are a helpful assistant<|end|><|user|>Hello. What is your name?<|end|><|assistant|>I am Phi, an AI developed by Microsoft. How can I help you today? ``` However, if running in a Jupyter notebook, then Guidance provides a widget for a richer user experience: <img src="docs/figures/widget_basic_example_20250703.png" alt="Guidance widget showing HTML generation" /> With Guidance, it's really easy to capture generated text: ```python # Get a new copy of the Model lm = phi_lm with system(): lm += "You are a helpful assistant" with user(): lm += "Hello. What is your name?" with assistant(): lm += gen(name="lm_response", max_tokens=20) print(f"{lm['lm_response']=}") ``` ``` lm['lm_response']='I am Phi, an AI developed by Microsoft. How can I help you today?' ``` ### Guarantee output syntax with constrained generation Guidance provides an easy to use, yet immensely powerful syntax for constraining the output of a language model. For example, a `gen()` call can be constrained to match a regular expression: ```python lm = phi_lm with system(): lm += "You are a teenager" with user(): lm += "How old are you?" with assistant(): lm += gen("lm_age", regex=r"\d+", temperature=0.8) print(f"The language model is {lm['lm_age']} years old") ``` ``` The language model is 13 years old ``` Often, we know that the output has to be an item from a list we know in advance. Guidance provides a `select()` function for this scenario: ```python from guidance import select lm = phi_lm with system(): lm += "You are a geography expert" with user(): lm += """What is the capital of Sweden? Answer with the correct letter. A) Helsinki B) Reykjavík C) Stockholm D) Oslo """ with assistant(): lm += select(["A", "B", "C", "D"], name="model_selection") print(f"The model selected {lm['model_selection']}") ``` ``` The model selected C ``` The constraint system offered by Guidance is ext
Excerpt of 12,617 characters
Read on GitHub
Scott Lundberg · Microsoft AI · United States
872
Richard Edgar · @microsoft
271
Marco Tulio Correia Ribeiro
217
163
Microsoft Research
117
Paul Koch · @microsoft
63
Samuel Jenkins
29
25
Nicholas King · United States
25
Markus · hercules.ai · Germany
13
Michał Moskal · @OpenAI · United States
9
8
5
5
4
Mihai Chirculescu · Romania
4
3
3
Holden X · China
3
3
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:873f36f1bbcced68, llm:Description: 'A guidance language for controlling large language models.' Language: Jupyter Notebook. Repository name: guidance-ai/guidance — likely a DSL or framework to orchestrate LLM behavior and chains.
matched fp:873f36f1bbcced68, llm:Description: 'A guidance language for controlling large language models.' Language: Jupyter Notebook. Repository name: guidance-ai/guidance — likely a DSL or framework to orchestrate LLM behavior and chains.
matched fp:873f36f1bbcced68, llm:Description: 'A guidance language for controlling large language models.' Language: Jupyter Notebook. Repository name: guidance-ai/guidance — likely a DSL or framework to orchestrate LLM behavior and chains.