0xLazAI/alith
0xLazAI/alith has 44 GitHub stars and 32 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-09 13:34 UTC. Last push 2026-11-01.
Simple, Composable, High-Performance, Safe and Web3 Friendly AI Agents and LazAI Gateway for Everyone
What you can do
- LazAI Gateway: Support the most basic wallet management, transfer, sending transactions, as well as LazAI's privacy data, iDAO, DAT, verified computing and other core features.
- Multiple Model Support: Support for small models and large language models e.g., Llama, Grok, OpenAI, Anthropic, etc.
- Highly Extensible: From covering internal prompts to accessing low-level APIs. Customize roles, goals, tools, actions and behaviors while maintaining a clean abstraction.
- Workflow Support: Implementing any workflow pattern through processes - from simple sequential and hierarchical processes to complex custom orchestration patterns with conditional branching and parallel execution.
Measured star growth
- in 24h
- 0
- in 7 days
- 0
- in 15 days
- Collecting history
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
README.md
Original
Simple, Composable, High-Performance, Safe and Web3 Friendly AI Agents for Everyone
Introduction
Alith is an AI agent framework designed for the Web3 and Crypto, empowering developers to quickly build, deploy, and manage on-chain AI agents. By integrating blockchain technology, AI/ML models, and developer-friendly tools, Alith provides a modular and extensible platform that supports AI bots, multi-chain interactions, smart contract operations, real-time data processing, and high-performance inference. Whether you're building DeFi trading bots, NFT analyzers, or DAO governance tools, Alith offers robust support for your projects.
Besides, Alith is a decentralized AI agent framework tailored to harness the capabilities of the LazAI - a decentralized AI platform dedicated to building an open, transparent, high-performance, secure, and inclusive AI ecosystem. For more introduction and comparison, see our website.
Features
- LazAI Gateway: Support the most basic wallet management, transfer, sending transactions, as well as LazAI's privacy data, iDAO, DAT, verified computing and other core features.
- Multiple Model Support: Support for small models and large language models e.g., Llama, Grok, OpenAI, Anthropic, etc.
- Highly Extensible: From covering internal prompts to accessing low-level APIs. Customize roles, goals, tools, actions and behaviors while maintaining a clean abstraction.
- Workflow Support: Implementing any workflow pattern through processes - from simple sequential and hierarchical processes to complex custom orchestration patterns with conditional branching and parallel execution.
- Cross-Language Support: Provides SDKs for Rust, Python and Node.js, making it easily accessible to different developers.
- High-Performance AI Training and Inference: Leverage the performance advantages of Rust and quick model training and inference technologies including graph optimization, model compression, JIT/AOT compilation with GPU coprocessors, etc.
- Web3 Friendly and Secure: Out-of-the-box Web3 plugin allows developers to easily and securely integrate blockchain capabilities into TEE-based AI agent frameworks and their applications with privacy data.
Architecture
Quick Start
See documents here.
Contributing
We warmly welcome contributions to Alith! Whether you're a developer, a user reporting a bug, or someone eager to enhance our documentation, your participation is highly valued!
Contact
Follow our X/Twitter and join our Telegram.
License
Apache 2.0
Explore related projects
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
300,216 starsNousResearch/hermes-agent
The agent that grows with you
262,061 starsmultica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
231,346 starsfirecrawl/firecrawl
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
199,847 stars