freshcrate
Skin:/
Home > Frameworks > anda

anda

🤖 An AI agent framework built with Rust.

Why this rank:Strong adoptionRelease freshnessHealthy release cadence

Description

🤖 An AI agent framework built with Rust.

README

Anda

🤖 An AI agent framework built with Rust, powered by ICP and TEEs.

🌍 README Translations

English readme | 中文说明 | 日本語の説明

🤖 Introduction

Anda is an AI agent framework built with Rust, featuring ICP blockchain integration and TEE support. It is designed to create a highly composable, autonomous, and perpetually memorizing network of AI agents. By connecting agents across various industries, Anda aims to create a super AGI system, advancing artificial intelligence to higher levels.

Anda Diagram

✨ Key Features

  1. Composability: Anda agents specialize in solving domain-specific problems and can flexibly combine with other agents to tackle complex tasks. When a single agent cannot solve a problem alone, it collaborates with others to form a robust problem-solving network. This modular design allows Anda to adapt to diverse needs.

  2. Simplicity: Anda emphasizes simplicity and ease of use, enabling developers to quickly build powerful and efficient agents. Non-developers can also create their own agents through simple configurations, lowering the technical barrier and inviting broader participation in agent development and application.

  3. Trustworthiness: Anda agents operate within a decentralized trusted execution environment (dTEE) based on Trusted Execution Environments (TEEs), ensuring security, privacy, and data integrity. This architecture provides a highly reliable infrastructure for agent operations, safeguarding data and computational processes.

  4. Autonomy: Anda agents derive permanent identities and cryptographic capabilities from the ICP blockchain, combined with the reasoning and decision-making abilities of large language models (LLMs). This allows agents to autonomously and efficiently solve problems based on their experiences and knowledge, adapting to dynamic environments and making effective decisions in complex scenarios.

  5. Perpetual Memory: The memory states of Anda agents are stored on the ICP blockchain and within the trusted storage network of dTEE, ensuring continuous algorithm upgrades, knowledge accumulation, and evolution. This perpetual memory mechanism enables agents to operate indefinitely, even achieving "immortality", laying the foundation for a super AGI system.

🧠 Vision and Goals

Anda's goal is to create and connect countless agents, building an open, secure, trustworthy, and highly collaborative network of agents, ultimately realizing a super AGI system. We believe Anda will bring revolutionary changes across industries, driving the widespread application of AI technology and creating greater value for human society.

🐼 About ICPanda DAO

ICPanda DAO is an SNS DAO established on the Internet Computer Protocol (ICP) blockchain, issuing the PANDA token. As the creator of the Anda framework, ICPanda DAO is dedicated to exploring the future of Web3 and AI integration.

🔎 Project

Documents:

Project Structure

anda/
├── anda_cli/              # Command line interface for Anda engine server
├── anda_core/             # Core library containing base types and interfaces
├── anda_engine/           # Engine implementation for agent runtime and management
├── anda_engine_server/    # HTTP server to serve multiple Anda engines
└── anda_web3_client/      # Rust SDK for Web3 integration in non-TEE environments

How to Use and Contribute

For Non-Developers:

The Anda framework provides a command-line interface in anda_cli for interacting with the Anda engine server.

For Developers:

  • Enhance the core engines anda_core and anda_engine;
  • Build custom agents and tools using the anda_core traits;
  • Contribute to the anda_engine_server HTTP server implementation.

Related Projects

  • IC-TEE: 🔐 Make Trusted Execution Environments (TEEs) work with the Internet Computer.
  • IC-COSE: ⚙️ A decentralized COnfiguration service with Signing and Encryption on the Internet Computer.

📝 License

Copyright © 2026 LDC Labs.

ldclabs/anda is licensed under the MIT License. See LICENSE for the full license text.

Release History

VersionChangesUrgencyDate
v0.12.0**Full Changelog**: https://github.com/ldclabs/anda/blob/main/CHANGELOG.md#0120--2026-05-07High5/7/2026
v0.8.0Latest release: v0.8.0Low9/2/2025
v0.4.7Release v0.4.7Low3/12/2025
v0.4.6Release v0.4.6Low3/9/2025
v0.4.5Release v0.4.5Low3/1/2025
v0.4.4Release v0.4.4Low3/1/2025
v0.4.3Release v0.4.3Low3/1/2025
v0.4.2Release v0.4.2Low2/21/2025
v0.4.1Release v0.4.1Low2/18/2025
v0.4.0Release v0.4.0Low2/15/2025
v0.3.8Release v0.3.8Low2/8/2025
v0.3.7Release v0.3.7Low2/7/2025
v0.3.6Release v0.3.6Low2/2/2025
v0.3.5Release v0.3.5Low1/29/2025
v0.3.4Release v0.3.4Low1/29/2025
v0.3.3Release v0.3.3Low1/26/2025
v0.3.2Release v0.3.2Low1/25/2025
v0.3.1Release v0.3.1Low1/24/2025
v0.3.0Release v0.3.0Low1/24/2025
v0.2.16Release v0.2.16Low1/23/2025
v0.2.15Release v0.2.15Low1/23/2025
v0.2.14Release v0.2.14Low1/23/2025
v0.2.13Release v0.2.13Low1/23/2025
v0.2.12Release v0.2.12Low1/23/2025
v0.2.11Release v0.2.11Low1/23/2025
v0.2.10Release v0.2.10Low1/23/2025
v0.2.9Release v0.2.9Low1/23/2025
v0.2.8Release v0.2.8Low1/21/2025
v0.2.7Release v0.2.7Low1/20/2025
v0.2.6Release v0.2.6Low1/20/2025
v0.2.5Release v0.2.5Low1/20/2025
v0.2.4Release v0.2.4Low1/20/2025
v0.2.3Release v0.2.3Low1/20/2025
v0.2.0Release v0.2.0Low1/20/2025

Dependencies & License Audit

Loading dependencies...

Similar Packages

agent-zeroAgent Zero AI frameworkv1.19
elizaAutonomous agents for everyonev2.0.3
AgentPinAgentPin agent pinning protocol, part of the Symbiont Agent Trust Stackv0.3.0
agencyA fast and minimal framework for building agentic systemsv1.6.3
deer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tamain@2026-06-06

More in Frameworks

langchainThe agent engineering platform
deer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of ta
tqdmFast, Extensible Progress Meter
simBuild, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.