# axoviq-ai/synthadoc

Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

Repository: https://github.com/axoviq-ai/synthadoc
Canonical: https://ross.abutalabs.com/products/synthadoc
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: agent-skills, agentic-ai, cli-tool, domain-adaptation, enterprise, enterprise-solutions, knowledge-graph, local-llm, obsidian-md, obsidian-plugin, personal-knowledge-management, pkm, rag-alternative, synthetic, synthetic-data
Last push: 2026-09-02T19:37:53+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 100, longevity 10
- inputs: {"age_days": 144, "days_push": 0, "days_rel": 0, "gap_med": 6.0, "n_releases_24m": 23}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1116, forks 123 (observed 2026-09-03T02:15:09.472060+00:00)

## What it is
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
- artifact type: cli-tool
- maturity: active
- function: rag, llm-inference, agent-framework, mcp, documentation, cli, plugin-system
- domain: large-language-models, developer-tools, documentation
- platform: python, cli, cross-platform, self-hosted
- tags: rag-alternative, obsidian-plugin, knowledge-graph, local-first, pkm, synthetic-data, agentic-ai, wiki-generation, retrieval-augmented-generation, knowledge-management

## Member repositories
- axoviq-ai/synthadoc (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:09.472060+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:41:52.501455+00:00, confidence not recorded.
  - readme: https://github.com/axoviq-ai/synthadoc (fetched 2026-09-03T02:15:09.472060+00:00, sha 219f30ef3eac)
  - registry_pypi: https://pypi.org/pypi/synthadoc/json (fetched 2026-08-29T12:45:41.823749+00:00, sha c6d856d2e5e9)
- Data as of 2026-08-30T08:39:29.467469+00:00.