Skip to main content

Raven — AI-assisted learning companion. Auto-detect materials, split by chapters, generate quizzes, organize notes.

Project description

Raven — AI Learning Companion

Huginn (思索) & Muninn (记忆) — the two ravens of Odin, now your study partners.

Raven is a CLI agent that helps you study. Drop it into any directory with learning materials, and it:

  • Reads PDFs, Word docs, PowerPoints
  • Splits materials into chapters (PDF slices or Markdown)
  • Summarizes content with AI
  • Quizzes you on what you've learned (✓/△/✗ grading)
  • Organizes your rough notes into polished documents

Installation

全局安装(推荐,所有目录都能用):

pip install raven-agent

安装后 Raven 命令全局可用。在任何包含学习资料的目录下直接运行即可。

API Key 配置

Raven 使用 DeepSeek API,三种配置方式任选:

方式一:什么都不做,首次运行自动引导(推荐)

Raven
# 首次运行没有 key 时,会自动提示:
#
#   DeepSeek API key not found. Set it now (one-time):
#     Or: $env:DEEPSEEK_API_KEY = "sk-..."
#     Paste your API key: █
#
# 粘贴一次,自动保存到 ~/.raven/config.toml,以后无需再配。

方式二:环境变量(临时会话)

# Windows PowerShell
$env:DEEPSEEK_API_KEY = "sk-..."

# macOS / Linux
export DEEPSEEK_API_KEY="sk-..."

方式三:手动写入配置文件

# ~/.raven/config.toml
api_key = "sk-..."

优先级:环境变量 > 配置文件 > 交互提示

获取 API key:https://platform.deepseek.com/api_keys

Quick Start

# 进入学习目录
cd ~/my-study-materials

# 启动 Raven
Raven

# Raven 自动:
# 1. 创建 huginn/(思索)和 muninn/(记忆)目录
# 2. 扫描当前目录中的 PDF、DOCX、PPTX、MD 文件
# 3. 列出找到的学习材料,等待你的指令

Directory Structure

Raven creates two directories in your working folder:

./
├── muninn/                  # Memory — structured knowledge
│   ├── chapters/            #   Chapter splits
│   ├── summaries/           #   AI-generated summaries
│   └── knowledge/           #   Extracted terminology
└── huginn/                  # Thought — active learning
    ├── 章节检测/             #   Chapter quizzes
    └── 学习笔记/             #   Study notes

Usage Examples

# 拆分教材
> 帮我把机器学习入门.pdf 拆分到 muninn

# 生成摘要
> 给第三章生成一个摘要

# 自测
> 考考我关于线性回归的知识

# 整理笔记
> 帮我整理 huginn/学习笔记/rough.md

Commands

Command Action
/help Show help
/mode read|yn|auto Change permission mode
/clear Reset conversation
/exit Quit
Ctrl+C Interrupt agent (then Continue/Discard/Quit)

Requirements

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

raven_agent-0.1.2-py3-none-any.whl (37.7 kB view details)

Uploaded Python 3

File details

Details for the file raven_agent-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: raven_agent-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 37.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for raven_agent-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 6d63112df7b64481a6030d40495c57950b1c3150fbc89af656ac05411588ab75
MD5 dfa0978b95d33bc4599b7de8410bb602
BLAKE2b-256 ea22a6c7800cafd4123dc9348735c8675aa9e93a83219b9a79d15718f2c5d9b1

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page