智能图书馆
智能图书馆 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。
📚 深度解析
**为什么要使用开源工具而非商业 SaaS？**
对于个人开发者和有隐私需求的用户，本地部署的开源工具意味着数据不离本机，不受第三方服务商的数据政策约束。同时，开源工具通常没有使用次数限制和月度费用，一次安装即可长期使用，对于高频使用场景的总拥有成本（TCO）远低于订阅制商业工具。
**安装与环境准备**
智能图书馆 依赖 TypeScript 运行环境。建议通过 pyenv（Python）或 nvm（Node.js）管理 TypeScript 版本，避免全局环境污染。对于新手用户，推荐先创建虚拟环境（python -m venv venv && source venv/bin/activate），再安装依赖，这样即使出现问题也可以随时删除虚拟环境重新开始，不影响系统稳定性。
**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues（已关闭的问题），大多数常见问题都已有解答。遇到 Bug 时，提供 pip list 的输出、完整错误堆栈和最小可复现示例，能显著提高开发者响应速度。AI Skill Hub 将持续追踪 智能图书馆 的版本更新，及时通知重要功能变化。
📋 工具概览
智能图书馆 是一款基于 TypeScript 开发的开源工具，专注于 ai、ai-safety、education 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。
📖 中文文档
智能图书馆 是一款基于 TypeScript 开发的开源工具，专注于 ai、ai-safety、education 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。
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
# 方式一：npm 全局安装 npm install -g agoracosmica # 方式二：npx 直接运行（无需安装） npx agoracosmica --help # 方式三：项目依赖安装 npm install agoracosmica # 方式四：从源码运行 git clone https://github.com/chipmates/agoracosmica cd agoracosmica npm install npm start
- 访问 GitHub 仓库页面
- 按照 README 文档完成依赖安装
- 根据系统环境完成初始化配置
- 参考官方示例或文档开始使用
- 遇到问题可在 GitHub Issues 中查找解答
# 命令行使用
agoracosmica --help
# 基本用法
agoracosmica [options] <input>
# Node.js 代码中使用
const agoracosmica = require('agoracosmica');
const result = await agoracosmica.run(options);
console.log(result);
# agoracosmica 配置说明 # 查看配置选项 agoracosmica --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 AGORACOSMICA_CONFIG="/path/to/config.yml"
简介
<p align="center"> <img src=".github/assets/logo.svg" alt="Agora Cosmica" width="160" /> </p>
Agora Cosmica
<p align="center"> <strong>A Living Library You Can Talk To</strong><br/> <sub>Nonprofit · Open Source · No tracking cookies, no profiling</sub> </p>
<p align="center"> <a href="LICENSE"><img src="https://img.shields.io/badge/License-AGPL--3.0-blue?style=flat-square" alt="License: AGPL-3.0" /></a> <a href="#"><img src="https://img.shields.io/badge/TypeScript-strict-3178C6?style=flat-square&logo=typescript&logoColor=white" alt="TypeScript: strict" /></a> <a href="docs/ACCESSIBILITY.md"><img src="https://img.shields.io/badge/WCAG-2.2%20AA-green?style=flat-square" alt="WCAG 2.2 AA" /></a> <a href="docs/COMPLIANCE.md"><img src="https://img.shields.io/badge/EU-Compliant-blue?style=flat-square" alt="EU Compliant" /></a> <a href="https://securityheaders.com/?q=https%3A%2F%2Fagoracosmica.org&followRedirects=on"><img src="https://img.shields.io/badge/Security%20Headers-A%2B-brightgreen?style=flat-square" alt="Security Headers: A+" /></a> <a href="docs/SELF-HOSTING.md"><img src="https://img.shields.io/badge/Self--host-Docker-2496ED?style=flat-square&logo=docker&logoColor=white" alt="Self-host with Docker" /></a> </p>
<p align="center"> <a href="https://agoracosmica.org">Live App</a> · <a href="#quick-start">Quick Start</a> · <a href="#architecture">Architecture</a> · <a href="CONTRIBUTING.md">Contribute</a> · <a href="CHANGELOG.md">Changelog</a> </p>
<p align="center"> <sub>⭐ If you find this interesting, a star is the simplest way to help us reach more people.</sub> </p>
---
Agora Cosmica is a Living Library for wisdom from history. Learn from thirty figures, from Marcus Aurelius to Ada Lovelace, Rumi to Frida Kahlo, each with their own researched voice and twelve wisdom teachings. The platform pairs hundreds of pre-recorded narrative episodes and multi-figure dialogues with live AI conversation. Live speech (text-to-speech and speech-to-text) runs on our own GPU servers in Germany. See all 30 figures →
30 free messages a day, no signup required. Bilingual English and German. On the path to community-driven development: anyone can vote on what gets added next, right inside the app.
<p align="center"> <strong>Try it, no signup: <a href="https://agoracosmica.org">agoracosmica.org</a></strong> </p>
<p align="center"> <a href="https://agoracosmica.org"><img src=".github/assets/demo.webp" alt="Agora Cosmica in action: choose a figure, move through Story and Wisdom, listen to a narrated chapter, and convene a council of four" width="100%" /></a> </p>
<p align="center"> <sub>🔊 <strong>Hear the self-hosted Echo voices</strong> (AI Echoes, about 10 seconds each)</sub><br/> <sub>German, Qwen3-TTS: <a href=".github/assets/audio/echo-nietzsche-de.mp3">Nietzsche (Solaris)</a> · <a href=".github/assets/audio/echo-hildegard-de.mp3">Hildegard von Bingen (Lyra)</a></sub><br/> <sub>English, Kokoro: <a href=".github/assets/audio/echo-shakespeare-en.mp3">Shakespeare (Orion blend)</a> · <a href=".github/assets/audio/echo-lovelace-en.mp3">Ada Lovelace (Stella)</a></sub> </p>
---
Features
Content - Six ways to engage: 4 educational chapters (Story, Wisdom, Prism, Quest) plus Free Talk and Council. How they work - Crafted catalog: 360 stories, 360 prism dialogues, 110 four-figure council debates (55 questions, two depth levels each), all with time-synced audio. - 30 figures · 12 teachings each: 360 wisdom teachings spanning 2,500 years of human thought. Browse the figures - Fully bilingual: English and German across all content, UI, and audio.
Honest by design - Echo framing: every figure is presented as an AI Echo (an AI-rendered portrayal), never claimed to be a real recording or to speak for the actual person. Why we call them Echoes - Factcheck transparency: each figure has a per-figure factcheck listing what's historically verified versus what's recreated for narrative. - Open source under AGPL-3.0: the privacy and architecture claims are verifiable by reading the code. - Built on learning science: the 4-chapter arc is informed by Kolb's experiential cycle, Bloom's taxonomy, and retrieval practice.
Privacy by design - BYOK encryption: bring your own OpenRouter key, encrypted locally with AES-256-GCM, never stored on our servers. - Free tier without signup: 30 messages a day via our Cloudflare Worker, no account required. - No behavioral tracking: no tracking cookies, no third-party analytics, no per-request access logs of our own, no IP retention in analytics, no cross-session profiles. We do collect anonymous aggregate counters to keep the service running and improve it. docs/MEASUREMENT.md lists exactly what gets counted, what never does, and the one exception we name upfront: for visitors who arrive from one of our free nonprofit Google Ad Grants ads and opt in, we forward the Google click ID (gclid) to Google Ads so that ad can be credited with the visit. - Self-hosted speech: live text-to-speech and speech-to-text run on our own GPU servers in Germany. - EU-first hosting: live audio in Germany, pre-recorded audio on Cloudflare R2.
Built for everyone - WCAG 2.2 AA: keyboard navigation, screen reader support, 44 px touch targets. Accessibility - Content safety: multi-layer screening, crisis resources, jailbreak detection, PII protection. Safety - EU compliance: GDPR, EU AI Act Article 50, German youth protection (JMStV). Compliance
---
Building this with you
We're early in this journey and we'll make mistakes. When we oversimplify, misrepresent, or miss the mark, tell us at agoracosmica@chipmates.ai. We're not building for you, but with you.
---
Quick Start
git clone https://github.com/chipmates/agoracosmica.git
cd agoracosmica/client
pnpm install && pnpm setup:assets && pnpm devBoots the React app at localhost:5173. UI and static content load against the production CDN. Live AI chat and audio require running the workers locally or pointing them at production via env vars. See CONTRIBUTING.md for the full setup.
Requirements: Node.js 20+, pnpm 8+.
Or run everything locally: Local Mode (v1.1.1) lets you point the app at any OpenAI-compatible LLM endpoint (LM Studio, Ollama, vLLM) and runs the audio stack (Kokoro EN, Qwen3-TTS DE, Whisper STT) in our published docker images. With both Local Mode and docker self-host, no conversation, voice, or text data leaves your machine. See SELF-HOSTING.md.
---
高质量开源AI教育平台，值得关注
- 需要 agoracosmica 解决具体问题的开发者与运营人员
- 先在测试环境跑通最小用例，再接入生产数据
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 需要 agoracosmica 解决具体问题的开发者与运营人员
- 先在测试环境跑通最小用例，再接入生产数据
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
👥 适合人群
🎯 使用场景
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
⚖️ 优点与不足
- +完全开源免费，无授权费用
- +本地部署，数据完全自主可控
- +开发者社区支持，遇问题可查可问
- −安装和初始配置可能需要一定技术基础
- −功能完整性通常不如成熟商业产品
- −技术支持主要依赖开源社区，响应速度不稳定
该工具使用 AGPL-3.0 协议，商用场景请仔细阅读协议条款，必要时咨询法律意见。
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。
⚠️ AGPL 3.0 — 最严格的 Copyleft，网络服务端使用也需开源，SaaS 使用受限。
🔗 相关工具推荐
❓ 常见问题 FAQ
经综合评估，智能图书馆 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 | agoracosmica |
| 原始描述 | 开源AI工具：A Living Library You Can Talk To. Open-source educational platform with 30 histo。⭐65 · TypeScript |
| Topics | aiai-safetyeducationtypescript |
| GitHub | https://github.com/chipmates/agoracosmica |
| License | AGPL-3.0 |
| 语言 | TypeScript |
收录时间：2026-06-11 · 更新时间：2026-06-11 · License：AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。