aka Emerging Stacks for Crypto Agent Applications
Name (site) | Description | Language | Github |
---|---|---|---|
LangChain/LangCahinJS | LangChain is a framework for developing applications powered by large language models (LLMs). Langchain has many useful features for buidling agents, such as model I/O, which includes prompt management and a generic interface for chat models, retrieval, which performs Retrieval Augmented Generation (RAG) involves loading data from a variety of sources, preparing it, then searching over (a.k.a. retrieving from) it for use in the generation step, and Agents, which makes decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. | Python / Typescript | |
Eliza | Eliza is a crypto native agent framework with rich features, such as Discord, Twitter and Telegram connectors, supports of many models (local Llama, OpenAI, Anthropic, Groq, etc.), multi-agent and room support, retrievable memory and document store. | Typescript | |
Rig | Rig is a Rust library for building scalable, modular, and ergonomic LLM-powered applications. It supporst high level features such as LLM completion and embedding workflows, common abstractions over LLM providers (e.g. OpenAI, Cohere) and vector stores (e.g. MongoDB, in-memory). | Rust |
Name (site) | Description | Language | Service Type | Github |
---|---|---|---|---|
EXO | EXO is a framework for runningAI cluster at home with everyday devices. | Python | Local | |
Hyperbolic | Hyperbolic is a open access AI cloud hosting open sourced large language models. | N.A. | Decentralized Hosting of Open Sourced Model | N.A. |
OpenAI Node/OpenAI Python | The OpenAI Python library provides convenient access to the OpenAI REST API from any Typescript/Javacript/Python applications. | Typescript/Python | API service for proprietary models. | |
Anthropic SDK | Libaries provides convenient access to the Anthropic REST API from server-side TypeScript/Python/Go/Java. | Typescript/Python/Go/Java | API service for proprietary models |