I Built an AI Reading Companion with Tree-Structured Conversations

A developer built pi-tree, a self-hosted AI reading companion that uses tree-structured conversations to allow branching and backtracking during reading sessions. Unlike typical RAG-based tools, pi-tree gives the AI precise, on-demand access to content via tools like process_book and search_papers, and supports customization through skills, session profiles, and plugins.

AI makes you productive where you already understand. It confuses you where you don't. I've been reading non-fiction with AI assistants for a while, and I kept hitting the same wall: 30 messages into a conversation about a dense book chapter, the AI starts losing the thread. I'd branch into a tangent — "how does this connect to what Kahneman said about System 1?" — and suddenly the entire chat context is polluted. No way to get back to where I was. So I built pi-tree https://github.com/shuowu/pi-tree — a self-hosted AI reading companion where the conversation When you think through complex material, your mind doesn't work linearly. You branch — "wait, how does this relate to X?" — explore for a bit, then come back. But every AI chat tool forces you into a flat thread where everything piles up. Tree-structured conversations fix this at the architecture level: Here's what a reading session looks like: 📖 Reading: Thinking, Fast and Slow Kahneman Root ├── What is System 1 vs System 2? │ ├── How does this relate to cognitive biases? │ │ └── Anchoring bias deep-dive │ └── Real-world examples in decision making ├── Chapter 3: The Lazy Controller │ └── Why do we avoid effortful thinking? └── Comparison with Nassim Taleb's ideas ├── Black Swan connection └── Antifragility and heuristics And here's the actual UI — tree sidebar on the left, conversation in the center, table of contents on the right: Most "chat with your documents" tools use RAG — chunk your content into embeddings, then retrieve what seems relevant. The problem: retrieval is approximate. The AI gets semantically similar chunks, not necessarily the right context. Pi-tree takes an agentic approach: the AI has tools that give it precise, on-demand access to your content — more like grep than vector search. It can look up a specific chapter, fetch a paper's methodology section, or scan today's RSS feeds. The context is exact, structural, and requested when needed — not pre-computed and hoped for. Each source type gets purpose-built tools: process book parses EPUB/MOBI/PDF, extracts chapter structure, builds a navigable outline get latest rss , search rss crawl your feeds, find trends across sources search papers , get paper info query arXiv, fetch and contextualize research get youtube transcript extracts transcripts for segment-level discussionThe AI's behavior is then shaped by skills — markdown instruction files that define how to read, not just what to retrieve. Here's a news session — the AI scanned RSS feeds and produced a digest with trends: Everything is customizable at three levels: 1. Skills Markdown files — Change how the AI reads by editing a .md file. No code. 2. Session Profiles YAML — Map source types to different skills, extensions, and models: name: book.reading skills: - interactive-reading extensions: - book exclude tools: - bash - edit 3. Full Plugins TypeScript — Build new source types with the plugin SDK: js import { definePiTreeExtension } from "@pi-tree/plugin-sdk"; export default definePiTreeExtension pi, services = { pi.registerTool { name: "my custom tool", description: "Does something useful", execute: async args = { const source = await services.sources.get args.sourceId ; // your logic here } } ; } ; There's also an MCP bridge — connect external MCP servers web search, academic databases, translation APIs by dropping a JSON config file. Same format as Claude Desktop. cp .env.example .env add your API key docker run -d --name pi-tree \ --env-file .env \ -p 3847:3847 \ -v ~/.local/share/pi-tree:/data \ ghcr.io/shuowu/pi-tree:latest Open http://localhost:3847 http://localhost:3847 . That's it. Works with any OpenAI-compatible API — cloud providers DeepSeek, Gemini, Claude, OpenAI or fully offline with Ollama / LM Studio. Reading doesn't need frontier models — a 12B parameter model works well. | Pi-tree | ChatGPT / Claude | NotebookLM | Obsidian + AI | | |---|---|---|---|---| Focus | Comprehension & exploration | General-purpose Q&A | Document Q&A | Note-taking | Conversations | 🌳 Tree — branch, explore, return | Linear chat | Linear chat | Linear chat | AI approach | Agentic — tools & skills over local data | Prompt + context window | RAG over uploads | Plugins over local vault | Sources | Books, papers, news feeds, YouTube | File uploads, web | Multi-doc notebooks | Markdown vault | Extensibility | Skills, plugins, MCP bridge | GPTs cloud-hosted | None | Community plugins | Model choice | BYOK — any provider or local | Vendor-locked | Google only | Plugin-dependent | Data | Local-first, self-hosted | Cloud | Cloud | Local | License: AGPL-3.0 — fully open source. I'd love feedback on: Built on the Pi SDK https://pi.dev/docs/latest/sdk for tree-structured agent sessions.