LLM 开源工具 是 AI Skill Hub 本期精选AI工具之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
LLM 开源工具 是一款基于 Rust 开发的开源工具,专注于 LLM、Rust、Internet Computer 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
LLM 开源工具 是一款基于 Rust 开发的开源工具,专注于 LLM、Rust、Internet Computer 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:cargo install(推荐) cargo install llm # 方式二:从源码编译 git clone https://github.com/dfinity/llm cd llm cargo build --release # 二进制在 ./target/release/llm
# 查看帮助 llm --help # 基本运行 llm [options] <input> # 详细使用说明请查阅文档 # https://github.com/dfinity/llm
# llm 配置说明 # 查看配置选项 llm --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export LLM_CONFIG="/path/to/config.yml"
<div> <p> <a href="https://forum.dfinity.org"><img alt="Chat on the Forum" src="https://img.shields.io/badge/help-post%20on%20forum.dfinity.org-yellow"></a> </p> </div>
This repo contains libraries and examples of how to use the LLM canister on the IC.
This is a simple agent that simply relays whatever messages the user gives to the underlying models without any modification. It's meant to serve as a boilerplate project for those who want to get started building agents on the IC.
Rust and Motoko implementations are provided in the examples folder. - Rust Quickstart Agent - Motoko Quickstart Agent
Additionally, a live deployment of this agent can be accessed here.

Q: What models are supported? A: For now, only the Llama 3.1 8B is supported. More models, based on your feedback, will be made available.
Q: What is the cost of using the LLM canister? A: It’s free for now. As the system and use-cases mature we can evaluate and set the costs accordingly.
Q: Are there any limitations on the prompts I can make? A: Yes. We’ve added a few limitations on how big the prompts and answers can be, and will gradually improve these over time: - A chat request can have a maximum of 10 messages. - The prompt length, across all the messages, must not exceed 10KiB. - The output is limited to 1000 tokens.
Q: Are my prompts private? A: Yes and no. The Internet Computer as a whole doesn’t yet guarantee confidentiality, and the same is true for the AI workers. Someone who has an AI worker running can in theory see the prompts, but cannot identify who made the prompt. For DFINITY specifically, we do not log these prompts, but do log aggregated metrics like the number of requests, number of input/output tokens, etc.
Q: What is the principal of the LLM canister? A: w36hm-eqaaa-aaaal-qr76a-cai
Q: Where is the source-code of the LLM canister? A: It is not yet open-source, as the current implementation is mostly a throw-away prototype, but it will be open-sourced eventually as this work matures.
高质量的AI工具,提供了LLM容器的库和示例
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,LLM 开源工具 在AI工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | llm |
| 原始描述 | 开源AI工具:Libraries and examples on how to use the LLM canister on the Internet Computer.。⭐22 · Rust |
| Topics | LLMRustInternet Computer |
| GitHub | https://github.com/dfinity/llm |
| License | Apache-2.0 |
| 语言 | Rust |
收录时间:2026-05-28 · 更新时间:2026-05-30 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。