Kani

Visit Tool

kani is a lightweight and highly hackable microframework for tool-calling language models. It offers fine-grained customizability for NLP researchers, hobbyists, and developers.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is kani?

kani (カニ) is a lightweight and highly hackable microframework designed for chat-based language models with tool usage and function calling capabilities. Unlike more opinionated frameworks, kani offers extensive customizability over the control flow, making it an ideal choice for NLP researchers, hobbyists, and developers who require precise control. It supports a wide range of models out-of-the-box, including OpenAI, Anthropic, Google AI, Hugging Face transformers, llama.cpp, and vLLM, with a model-agnostic framework for easy integration of others. Key features include automatic chat memory management, robust function calling with model feedback and retry mechanisms, and support for multimodal inputs. The framework is built with an asynchronous design, allowing for scalable parallel chat sessions.

Best used for

Ideal for developers and data scientists who need to build custom language model applications, integrate various LLM backends, and implement advanced function calling. Especially valuable for NLP researchers and hobbyists seeking fine-grained control and hackability in their projects.

Common actions

build LLM applications

integrate language models

manage chat state

enable function calling

process multimodal inputs

face swappinggithub copilotopen-source"AI Agents"workflowsdeepfakelow-code/no-codecollaborationautomated workflow

Capabilities

Key features

Model-agnostic engine
Automatic chat memory
Robust function calling
Multimodal input support
Asynchronous design

Target Audience

developerdata scientiststartup founder

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What language models does kani support?

kani supports a wide range of language models out-of-the-box, including OpenAI Models, Anthropic Models, Google AI Models, Hugging Face transformers, llama.cpp, and vLLM. Its model-agnostic framework also allows for easy integration of additional models through community extensions.

How does kani handle function calling?

kani simplifies function calling by allowing developers to expose Python functions to the model using a simple decorator. It guarantees valid function calls, provides feedback on hallucinated parameters or errors, and enables the model to retry calls, streamlining tool integration.

Can kani process images and other media?

Yes, kani optionally supports multimodal inputs such as images, audio, and video for compatible language models. By installing the kani-multimodal-core extension, users can integrate various media types into their chat rounds, leveraging the full kani ecosystem benefits.

Trending

Subcategories trending in AI Agents & Automation

Chatbots & Conversational AI General-Purpose Agents Workflow Agents Personal Assistants RAG & Document AI Voice Agents

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce