Open-源代码, end-to-end 平台为 evaluating, observing, 和 improving 大语言模型和 AI agent 应用 s. Tracing · Evals · Simulations · 数据集 s · 网关 · Guardrails. Self-ho 稳定. Apache 2.0.该项目在GitHub已获得1,192星标（262分叉），代码活跃度高。主要编程语言为Python，采用Apache-2.0开源协议。主要标签：ai,ai-gateway,evals,llm,observability。

项目简介

Open-源代码, end-to-end 平台为 evaluating, observing, 和 improving 大语言模型和 AI agent 应用 s. Tracing · Evals · Simulations · 数据集 s · 网关 · Guardrails. Self-ho 稳定. Apache 2.0.

核心功能

- Customer Support: Ship support AI customers actually trust - Voice Agents: Test, evaluate, 和 improve voice AI end-to-end - Internal 工具 s: AI copilots 你的 whole org 可以 rely on - 检索增强生成 & Search: 每个 answer grounded, 每个 citation verified - 自主智能体 Agents: Multi-step agents 你可以 actually trust 在生产 - Computer-Use Agents (CUA): Agents 命令行工具 ck 用 confidence

使用指南

Two ways, picked by how much you want to install: <table width="100%"> <tr> <th width="50%">Cloud (fastest)</th> <th width="50%">Self-host (Docker)</th> </tr> <tr valign="top"> <td width="50%"> No install. Free tier. ```

Sign up free:

app.futureagi.com

pip install ai-evaluation ``` <sub>SOC 2 Type II · HIPAA · data stays in your region.</sub> </td> <td width="50%"> One command, full stack. Published images, no source build. ```

macOS / Linux / WSL

git clone https://github.com/future-agi/future-agi.git cd future-agi ./bin/install

Windows (PowerShell)

git clone https://github.com/future-agi/future-agi.git cd future-agi .\bin\install.ps1 ``` <sub>For production, use `./deploy/setup.sh` to generate required secrets and pin the image version.</sub> </td> </tr> </table>

项目信息

项目	信息
Star数	1,192
Fork数	262
编程语言	Python
开源协议	Apache-2.0
创建时间	2026-04-23
最近更新	2026-06-19
主题标签	ai、ai-gateway、evals、llm、observability

来源：[future-agi/future-agi](https://github.com/future-agi/future-agi)