Agents et multi-agents

Alith

0xlazai/alith

A simple, composable, and high-performance AI agent framework designed for Web3 and Crypto, enabling developers to build, deploy, and manage on-chain AI agents with multi-language support and LazAI Gateway integration.

★ 44Étoiles
⑂ 31Forks
34Problèmes ouverts
RustLangue
Apache-2.0Licence
Q@project.QualityScoreScore éditorial

Captures d'écran du projet

Capture d’écran de Alith Capture d’écran de Alith

Vue d’ensemble

Alith is an AI agent framework tailored for Web3 and decentralized applications. It integrates blockchain technology, machine learning models, and developer tools to provide a modular and extensible platform. The framework supports multi-chain interactions, smart contract operations, real-time data processing, and high-performance inference. It is built to harness the capabilities of the LazAI decentralized AI platform, supporting features like verified computing, iDAO, and DAT within a TEE-based environment.

Fonctionnalités clés

  • LazAI Gateway integration for wallet management, transactions, and verified computing
  • Multiple Model Support including Llama, Grok, OpenAI, and Anthropic
  • Highly Extensible architecture with customizable prompts and low-level API access
  • Workflow Support for sequential, hierarchical, and custom orchestration patterns
  • Cross-Language SDKs for Rust, Python, and Node.js
  • High-Performance AI Training and Inference using Rust and GPU coprocessors
  • Web3 Friendly and Secure with TEE-based AI agent framework integration

Prérequis, installation et démarrage rapide

Follow the installation or quick-start section in the repository README and run its dependency setup commands. Repository: https://github.com/0xLazAI/alith

Utilisation

Run the examples documented in the repository README and adapt the parameters to the project APIs. More usage: https://github.com/0xLazAI/alith

Compatibilité des modèles et cas d’usage

Supports small models and large language models such as Llama, Grok, OpenAI, and Anthropic.

Licence et notes sur les risques

Apache-2.0

Editorial verification 2026-08-02: repository URL, owner, description, license and repository statistics were reviewed. License metadata: Apache-2.0. README was fetched for the channel draft; re-check repository dependencies, releases and model terms before production use.

Publication et maintenance

Not stated in the repository metadata

Firecrawl

firecrawl/firecrawl

★ 161,1KTypeScript

LangChain

langchain-ai/langchain

★ 143,6KPython

RAGFlow

infiniflow/ragflow

★ 86,7KGo