BYO-LLM-WIKI

Build your own LLM-native WIKI (knowledge library). Search, extract, summarize, Q&A with contextual RAG, layered knowledge graph, and reinforced memory. Importa

What is BYO-LLM-WIKI?

Build your own LLM-native WIKI (knowledge library). Search, extract, summarize, Q&A with contextual RAG, layered knowledge graph, and reinforced memory. Importantly use selected context to automatically generate skills, empowered by Claude subagents + CodeAct pipeline and gated by human review. **Try Live Demo**: https://byo-wiki-demo.vercel.app

Overview of BYO-LLM-WIKI

What it is

BYO-LLM-WIKI is a Flask application that turns web pages, files, and loose notes into a personal wiki maintained by an LLM agent. It is local-first: all stores are plain JSON or SQLite under a data/ directory, and cloud services are opt-in. The project is inspired by LangChain's llm-wiki deep-agents example but builds a private, on-disk library instead of syncing to a hub.

Key features

  • Agentic knowledge graph: a deepagents agent saves passages, extracts entities and typed relations, canonicalizes duplicates, nests topics, and writes synthesis pages.
  • Contextual RAG: Anthropic-style contextual retrieval over a two-layer HNSW index (section summaries + chunks), with an LLM re-ranker (precision) or document-aware MMR (multi-doc recall). Answers are grounded and cited.
  • Memory: a cross-session store recalled before every answer and written back after (observations, 👍/👎, corrections that supersede stale notes); it improves from use, not just ingestion.
  • Agent skills: selected context can be turned into a reusable, evaluated skill via a sub-agent pipeline (understand → analyze → author → eval → gate → refine). Authored by the latest Claude in-process or via the Claude Code CLI as a subprocess, scored by a deterministic plus rubric panel, and gated behind human review.
  • MCP, both directions: connect agents to external MCP servers (Supabase, GitHub, …) and run BYO-WIKI as an MCP server. Reads join the agent; writes are deny-by-default.

Use cases

The application is designed for personal knowledge management: turning web content, files, and notes into a coherent, searchable wiki. It supports searching and summarizing pages, ingesting them into a contextual vector index for grounded, cited Q&A, and growing a layered knowledge graph that de-duplicates entities, builds topics, and writes synthesis pages. The skill generation feature allows users to automatically create reusable skills from selected context, gated by human review.

Getting started

bash python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt # add `ragas` for RAGAS metrics cp .env.example .env # set at least one provider key python app.py # → http://localhost:5000 Both app.py and runner.py auto-load .env. RAG needs OPENAI_API_KEY for embeddings (text-embedding-3-small) regardless of chat provider.

License and pricing

The license is not stated in the repository. The project is listed as open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/lyra-stellaibyo-llm-wiki.svg)](https://yunodb.com/tools/lyra-stellaibyo-llm-wiki?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/lyra-stellaibyo-llm-wiki?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/lyra-stellaibyo-llm-wiki.svg" alt="Featured on YunoDB" height="20"></a>