axoviq-ai/synthadoc

Health v2 · maintenance only

Flags: young

Adoption not part of the score

1116 stars · 123 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Synthadoc is an open-source, domain-agnostic LLM knowledge compilation engine that transforms raw documents into structured, human-readable local wikis. It positions itself as a transparent, self-managed alternative to traditional RAG pipelines, with an Obsidian plugin and MCP tooling.

Use cases

• turn raw documents into a structured wiki with an LLM
• find a transparent alternative to RAG for knowledge retrieval
• build a local-first knowledge base for personal knowledge management
• compile enterprise documentation into an LLM-friendly knowledge graph
• integrate a knowledge base with Claude via MCP
• manage an Obsidian vault generated from documents
• adapt an LLM to a specific domain without fine-tuning

When to choose

• you want auditable, human-readable knowledge output instead of opaque vector embeddings
• you need a local-first, self-hosted knowledge pipeline you can inspect and improve manually
• you already use Obsidian or MCP-compatible agents like Claude
• you want domain adaptation via curated knowledge rather than model training

When to avoid

• you need high-scale, low-latency semantic search over millions of chunks, where classic vector RAG excels
• you want a fully automated pipeline with no human curation
• you cannot accept the AGPL-3.0 license in your product
• you need a hosted turnkey solution rather than a self-managed CLI workflow

Facets

cli-tool · maturity active

rag llm-inference agent-framework mcp documentation cli plugin-system large-language-models developer-tools documentation python cli cross-platform self-hosted rag-alternative obsidian-plugin knowledge-graph local-first pkm synthetic-data agentic-ai wiki-generation retrieval-augmented-generation knowledge-management

Member repositories

For agents

markdown · JSON · MCP: product_card(name="axoviq-ai/synthadoc")