GitHub - OthersideAI/self-operating-computer: A framework to enable multimodal models to operate a computer.
The AI engineering framework
Marvin is a lightweight AI engineering framework for building natural language interfaces that are reliable, scalable, and easy to trust.
Sometimes the most challenging part of working with generative AI is remembering that it's not magic; it's software. It's new, it's nondeterministic, and it's incredibly powerful - but... See more
Marvin is a lightweight AI engineering framework for building natural language interfaces that are reliable, scalable, and easy to trust.
Sometimes the most challenging part of working with generative AI is remembering that it's not magic; it's software. It's new, it's nondeterministic, and it's incredibly powerful - but... See more
PrefectHQ • GitHub - PrefectHQ/marvin: ✨ Build AI interfaces that spark joy
emerging of LLMs not as a chatbot, but the kernel process of a new Operating System. E.g. today it orchestrates:
- Input & Output across modalities (text, audio, vision)
- Code interpreter, ability to write & run programs
- Browser / internet access
- Embeddings database for files and internal memory storage & retrieval
- Input & Output across modalities (text, audio, vision)
- Code interpreter, ability to write & run programs
- Browser / internet access
- Embeddings database for files and internal memory storage & retrieval
Andrej Karpathy • Tweet
Overview
AIConfig saves prompts, models and model parameters as source control friendly configs. This allows you to iterate on prompts and model parameters separately from your application code .
AIConfig saves prompts, models and model parameters as source control friendly configs. This allows you to iterate on prompts and model parameters separately from your application code .
- Prompts as configs : a standardized JSON format to store generative AI model settings, prompt inputs/outputs, and flexible metadata.
- Model-agnostic SDK :
lastmile-ai • GitHub - lastmile-ai/aiconfig: aiconfig -- config-driven, source control friendly AI application development
Agent Protocol
The AI agent space is young. Most developers are building agents in their own way. This creates a challenge: It's hard to communicate with different agents since the interface is often different every time. Because we struggle with communicating with different agents, it's also hard to compare them easily. Additionally, if we had a s... See more
The AI agent space is young. Most developers are building agents in their own way. This creates a challenge: It's hard to communicate with different agents since the interface is often different every time. Because we struggle with communicating with different agents, it's also hard to compare them easily. Additionally, if we had a s... See more