synthadoc

Synthadoc

      .-+###############+-.
    .##                   ##.
   ##    .----.   .----.    ##
  ##    /######\ /######\    ##
  ##    |######| |######|    ##
  ##    | [SD] | | wiki |    ##
  ##    |######| |######|    ##
  ##    \######/ \######/    ##
   ##    '----'   '----'    ##
    '##                   ##'
      '-+###############+-'

       S Y N T H A D O C
    Community Edition  v1.5.1
  ────────────────────────────────
  Domain-agnostic LLM wiki engine

Document version: v1.5.1

Engineered for solo users and enterprises alike, providing a domain-specific knowledge base that scales seamlessly while maintaining accuracy through autonomous self-optimization.

Built for individuals, small teams, and large organizations who need a knowledge base that stays accurate as documents accumulate.

Documentation, FAQ and articles: https://axoviq.com/resources/synthadoc

Synthadoc reads your raw source documents — PDFs, spreadsheets, PPTs, web pages, images, videos, Word files, TXTs, and AI session transcripts (.jsonl) — and uses an LLM to synthesize them into a persistent, structured wiki. Cross-references are built automatically, contradictions are detected and surfaced, orphan pages are flagged, and every answer cites its sources. Outputs are stored as local Markdown files, ensuring seamless integration and autonomous management within Obsidian or any wiki-compliant ecosystem.

▶ From Documents to Wiki

▶ Four Interfaces: CLI, Obsidian, Web UI & MCP

▶ Agentic Maintenance Workflow

📝 Blogs & Media — YouTube · Coderlegion · DEV.to · Medium

📂 End-to-end Example — AquaFlow Capital M&A due diligence walkthrough

Table of Contents

• Who Is It For?
• Inspiration and Vision
• Problems Addressed
• Why Synthadoc?
• Architecture
• What’s Included
• Installation
• Quick-Start Guide
• Creating Your Own Wiki
• Configuration
• Command Reference by Use Case
• Administrative Reference
• Understanding Logs and the Audit Trail
• Customization
• Links

Who Is It For?

Synthadoc scales from a single researcher to a company-wide knowledge platform:

Built for large wikis. Measured on wikis of thousands of pages: keyword search finds the pages for an answer in about 20 ms at 2,000 pages; semantic search, on by default for new wikis when installed, puts the right page in the top 5 for 70% of questions asked in your own words, up from 48%; and the knowledge graph opens a 5,000-page wiki as a clickable overview of named topic clusters in about 6 seconds.

The web UI’s Graph tab on a 5,000-page test wiki: 100,801 links summarised as 24 named clusters. Click a cluster to see its pages. How it works

No cloud account. No vendor lock-in. The wiki is plain Markdown — open it in any editor, back it up with git, sync it with any cloud drive.

Inspiration and Vision

“The LLM should be able to maintain a wiki for you.” — Andrej Karpathy, LLM Wiki gist

Most knowledge-management tools retrieve and summarize at query time. Synthadoc inverts this: it compiles knowledge at ingest time. Every new source enriches and cross-links the entire corpus, not just appends a new chunk. The wiki is the artifact — readable, editable, and browsable without any tool running.

Long-term alignment:

Problems Addressed

RAG retrieves document chunks at query time. Synthadoc compiles knowledge at ingest — synthesising sources into a linked, audited wiki graph so contradictions are caught, claims are traced to sources, and the artifact survives outside the tool.

Citation quality: Generated pages include inline citations linking every claim to its source lines. Pages without citations trigger a model-compatibility warning — use Gemini 2.5 Flash or higher for reliable citation annotation.

Active page protection: Pages promoted to active status are protected — sources that contradict them are flagged for review rather than overwriting the human-reviewed content.

Why Synthadoc?

Every Yes below is a built-in feature — no add-ons or upgrades required.

Knowledge Quality

Knowledge Structure

Search & Query

Interfaces & Integration

Content Sources

Operations & Trust

Business value

Architecture

For full architecture details, data models, API reference, and plugin development guide see docs/design.md.

What’s Included

See docs/design.md — Appendix A: Release Feature Index for a full feature list by version.

Installation

Choose one way to run Synthadoc:

Production

Prerequisites: Python 3.11+. No Node.js, no Git, no build steps.

pip install "synthadoc[vectors]"   # recommended — includes semantic search
pip install synthadoc              # lightweight install, no semantic search
synthadoc --version                # confirm it works

The Obsidian plugin is bundled inside the package. New wikis created with synthadoc install have it installed automatically. If you are upgrading an existing Synthadoc installation, run synthadoc plugin upgrade to push the updated plugin binary to all registered wikis.

Docker

Prerequisites: a container runtime only (Docker Engine or Desktop, Apple container, or wslc). No Python, pip, or synthadoc install on the host: every command, including creating the wiki, runs in a container.

For server deployments, team wikis, CI/CD pipelines, and isolated personal use, Synthadoc ships an OCI image, chenp/synthadoc, for linux/amd64 and linux/arm64. It works with Docker Engine and Docker Desktop, the Apple container tool (macOS 26+ Apple Silicon), and WSL Containers (wslc, Windows 11). One container serves one wiki. The HTTP API, Web UI (/app), and MCP over HTTP (/mcp) all share the wiki’s port, and the wiki files stay on the host so Obsidian keeps working unchanged.

Commands are shown for Linux / macOS. On Windows, expand the Windows (Command Prompt) block for single-line cmd.exe versions: \ line continuation and ~ in -v paths don’t work there. (In PowerShell, replace %USERPROFILE% with $env:USERPROFILE.)

1. Create the wiki in a one-off container. It lands in ~/wikis/history-of-computing; note the port it prints, e.g. 7070. docker run downloads the image on first use. Run docker pull chenp/synthadoc:latest later to update a cached image.

mkdir -p ~/wikis
docker run --rm -v ~/wikis:/wikis chenp/synthadoc:latest \
  synthadoc install history-of-computing --target /wikis --demo

if not exist "%USERPROFILE%\wikis" mkdir "%USERPROFILE%\wikis"
docker run --rm -v "%USERPROFILE%\wikis:/wikis" chenp/synthadoc:latest synthadoc install history-of-computing --target /wikis --demo

2. Put your LLM API key in ~/wikis/.env, never on the command line. Create it with any text editor (Windows: notepad "%USERPROFILE%\wikis\.env"). For example, to use MiniMax:

# ~/wikis/.env
MINIMAX_API_KEY=sk-...
# optional — enables web search ingest
TAVILY_API_KEY=tvly-...

Keep comments on their own line; --env-file does not strip a trailing # … from a value.

Then select the same provider in ~/wikis/history-of-computing/.synthadoc/config.toml. Under [agents], comment out the active default = line and uncomment the matching one:

[agents]
default = { provider = "minimax", model = "MiniMax-M3", thinking = "disabled" }

3. Run the server in a container, using the same port on both sides of -p:

docker run -d --name history-of-computing \
  -v ~/wikis/history-of-computing:/wiki \
  -p 7070:7070 \
  --env-file ~/wikis/.env \
  chenp/synthadoc:latest

docker run -d --name history-of-computing -v "%USERPROFILE%\wikis\history-of-computing:/wiki" -p 7070:7070 --env-file "%USERPROFILE%\wikis\.env" chenp/synthadoc:latest

4. Use it. Open the Web UI at http://localhost:7070/app, or run the CLI inside the container (same on every platform):

docker exec history-of-computing synthadoc query "Who was Alan Turing?"
docker exec history-of-computing synthadoc lint run --wait

After editing config.toml, run docker restart history-of-computing. After changing .env, remove and re-create the container (docker rm -f history-of-computing, then step 3 again), because restart does not re-read .env.

See docs/docker-deploy.md for the full deployment guide: architecture, API key setup, platform-native runtimes, Docker Compose (single wiki, multi-wiki with cross-wiki queries, Ollama sidecar), CI/CD, file permissions, security, and maintenance.

Docker users: the rest of this Installation section (Development, Set your API keys with shell exports, and Install a wiki and start the engine) is for the pip install. With Docker, API keys go in the .env file, and any synthadoc … command elsewhere in this README runs as docker exec <container> synthadoc … (no -w needed).

Development

For developers modifying the Python engine, running the test suite, or developing the Obsidian plugin TypeScript.

Additional prerequisites: Git (any). Node.js 18+ only if modifying the plugin TypeScript source.

Step 1 — Clone and install

git clone https://github.com/axoviq-ai/synthadoc.git
cd synthadoc
pip install -e ".[dev]"

[dev] adds pytest, respx, and the other test dependencies. Tests require a source checkout — they are not included in the pip wheel.

Step 2 — Run the test suite

pytest --ignore=tests/performance/ -q

Expected: all tests pass, 0 failures. Performance benchmarks (optional):

pytest tests/performance/ -v --benchmark-disable

Step 3 — Obsidian plugin development (optional)

The compiled plugin is bundled with the package and kept up to date by CI — no build step is needed to work on the Python side or run tests.

If you modify the TypeScript source under obsidian-plugin/src/, recompile and sync it into the Python package manually:

cd obsidian-plugin
npm install           # first time only, or after package.json changes
# edit src/main.ts or other source files
npm run build         # compile TypeScript → main.js (also syncs to synthadoc/data/obsidian-plugin/)
npm test              # run Vitest unit tests
cd ..

Set your API keys

At least one LLM API key is required — unless you use Claude Code or Opencode as your provider (no separate API key needed — see Coding tool CLI providers).

Synthadoc defaults to Gemini Flash — free tier, no credit card, 1 million tokens per day. Get a key at aistudio.google.com/app/apikey (click “Create API key”).

# macOS / Linux — add to ~/.bashrc or ~/.zshrc to persist
export GEMINI_API_KEY=AIza…          # default — free tier, 1M tokens/day
export GROQ_API_KEY=gsk_…            # alternative free tier — 100K tokens/day
export ANTHROPIC_API_KEY=sk-ant-…    # paid — highest quality
export OPENAI_API_KEY=sk-…           # paid
export MINIMAX_API_KEY=…             # paid — text rates (image support)
export DEEPSEEK_API_KEY=…            # paid — text rates (no image support)
export QWEN_API_KEY=…                # DashScope cloud — 1M free tokens trial (DASHSCOPE_API_KEY also accepted)
export KIMI_API_KEY=…                # Kimi (DashScope) — kimi-k3 flagship, kimi-k2.6 general (QWEN_API_KEY also accepted)
export TAVILY_API_KEY=tvly-…         # web search (optional)

# Windows cmd — current session only
set GEMINI_API_KEY=AIza…
set GROQ_API_KEY=gsk_…
set ANTHROPIC_API_KEY=sk-ant-…
set OPENAI_API_KEY=sk-…
set MINIMAX_API_KEY=…
set DEEPSEEK_API_KEY=…
set QWEN_API_KEY=…                   # DASHSCOPE_API_KEY also accepted
set KIMI_API_KEY=…                   # QWEN_API_KEY also accepted
set TAVILY_API_KEY=tvly-…

Web search uses Tavily (TAVILY_API_KEY) — optional, only needed for synthadoc ingest "search for: …" jobs. Get a free key at tavily.com.

Install a wiki and start the engine

A wiki is a self-contained knowledge base — a folder of Markdown pages maintained and cross-referenced automatically by Synthadoc. The fastest way to get started is the History of Computing demo (13 pre-built pages, no LLM API key required to browse).

# Linux / macOS
synthadoc install history-of-computing --target ~/wikis --demo

# Windows (cmd.exe)
synthadoc install history-of-computing --target %USERPROFILE%\wikis --demo

Then start the engine:

# Foreground — logs stream to the console
synthadoc serve -w history-of-computing

# Background — releases the terminal
synthadoc serve -w history-of-computing --background

The server binds to http://localhost:7070 (localhost-only). Leave it running while you work — the Obsidian plugin, CLI ingest commands, and query commands all talk to it.

To switch LLM provider, edit [agents] in <wiki-root>/.synthadoc/config.toml and restart synthadoc serve. See Appendix — Switching LLM providers for step-by-step instructions.

To stop a background server:

synthadoc stop -w history-of-computing

Upgrading: after updating synthadoc (via pip install --upgrade "synthadoc[vectors]" or git pull), restart the server to pick up the new code, then run these to keep registered wikis in sync:

synthadoc plugin upgrade         # push updated Obsidian plugin binary to all registered wikis
synthadoc templates sync --force # demo and template wikis — refresh seeds, routing, agent files, and stubs

Neither command requires the server to be running.

Upgrading a Docker deployment: docker pull chenp/synthadoc:latest, then remove and re-create the container with the same docker run command; wiki data on the host is untouched. Then run inside the container to sync the plugin and templates:

docker exec <container> synthadoc plugin upgrade      # push updated plugin binary to the wiki vault
docker exec <container> synthadoc templates sync      # refresh seeds, routing, agent files, and stubs

See Docker Deployment Guide — Updating the image.

Quick-Start Guide

The History of Computing demo includes 13 pre-built pages, raw source files covering clean-merge, contradiction, and orphan scenarios, and a full walkthrough of key Synthadoc feature.

Full step-by-step walkthrough: docs/user-quick-start-guide.md

The guide covers:

1. Verify the demo server started (banner, health check)
2. Install the Synthadoc plugin (auto-installs Dataview) and open the vault
3. Review wiki structure and key files (index, purpose, AGENTS.md, dashboard)
4. Query the pre-built wiki — including knowledge gap detection
5. Batch ingest all demo source files
6. Run lint — auto-promote clean pages to active
7. Manage page lifecycle — 5-state machine (draft → active → stale/contradicted/archived), manual transitions, immutable audit trail
8. Resolve a contradiction
9. Fix an orphan page
10. Run the adversarial lint pass — flag overstated claims across all pages
11. Web search ingestion with automatic decomposition
12. Ingest a YouTube video
13. Enrich the wiki with scaffold (regenerate/update index, purpose, AGENTS.md)
14. Audit features (token cost, history, events)
15. Schedule recurring operations
16. Set up query-scoped routing with ROUTING.md
17. Stage and review candidate pages before promoting them
18. Build a context pack for grounded LLM prompts
19. Verify claim provenance — source-line citations, broken citation audit, global provenance table
20. Export your wiki — llms.txt, llms-full.txt, GraphML wikilink graph, agent-ready JSON with provenance and lifecycle history, OKF v0.2 bundle for zero-code agent consumption
21. Use the web chat UI — streaming answers, session-aware hint chips, citations in-browser
22. Query caching — understand how answers are cached and how to bypass with --no-cache
23. Backup and restore — create a portable wiki zip, restore on a different machine
24. Knowledge graph — weighted edges (wikilink + co-source signals), explore clusters in the web UI Graph tab, click a node to query it; large wikis open on a cluster overview
25. Ingest an AI session transcript — turn Claude Code, Codex, or chat conversations into structured wiki pages
26. Agentic maintenance workflows — nine conversational workflows via web UI or CLI: re-ingest stale pages (bulk or by slug), scan and fix broken wikilinks, run lint and view the full report, run scaffold and regenerate wiki files, resolve contradicted pages interactively (diff shown before every write, human approval required), resolve orphaned pages by inserting natural wikilinks into related content, fix broken source citation markers, detect and repair content quality issues (duplicate sections, thin/empty sections, broken markdown structure) with LLM-assisted analysis — agent confirms before touching anything, streams inline progress
27. Scan and retract sensitive data — dry-run to surface API keys, emails, SSNs, credit cards, and custom patterns; apply redactions with a single confirmation; incremental --changed-only mode for recurring runs; audit trail records pattern names only (never the values)

Creating Your Own Wiki

New to building your own wiki? Work through the AquaFlow Capital Workshop Walkthrough first — a complete end-to-end workshop using a real M&A due-diligence wiki with pre-built pages, evaluation queries, and benchmark results. Once you are comfortable with the flow, come back here to build your own wiki from scratch.

1. Pick a template and install

Browse the 30 available templates across 9 categories and pick the one closest to your domain:

synthadoc templates list

Install with a template (example: consumer and competitive market research):

synthadoc install my-market-wiki --target ~/wikis --template research/market-research
synthadoc use my-market-wiki   # set as default — no -w needed from here on

If none of the 30 templates fits, install without one and provide a --domain description instead:

synthadoc install my-wiki --target ~/wikis --domain "Your domain description"

→ Full template catalog and per-category install commands: synthadoc/templates/README.md

2. Configure your LLM provider and start the server

Open ~/.wikis/my-market-wiki/.synthadoc/config.toml and set your LLM provider, then start:

synthadoc serve
synthadoc status   # should show 0 pages and the scheduled jobs registered

→ Provider list and API key setup: Quick-Start Guide — Appendix C

synthadoc install copies the Synthadoc and Dataview plugins into the vault and pre-enables them. Open the wiki folder in Obsidian — both plugins are active immediately. A local web UI is also available at http://localhost:{port}/app via synthadoc web.

3. Add your sources and ingest

Start with seeds.md. Your installed wiki includes a seeds.md file at the wiki root — open it before anything else. It contains the complete getting-started guide for your domain: pre-vetted copy-paste ingest commands for curated public URLs, a domain-specific first-steps checklist, and topic hints for finding additional sources.

Open it in Obsidian (file pane → seeds.md) or in any editor:

<your-wiki-folder>/seeds.md

Once you have worked through seeds.md, drop your own documents into the raw_sources/ folder and ingest them. Subfolders are supported — organise by topic, date, or document type:

synthadoc ingest raw_sources/ --batch          # all local files at once
synthadoc ingest "https://example.com/report"  # a web URL
synthadoc ingest "search for: Bank of Canada rate outlook 2025"  # web search
synthadoc jobs list                            # watch progress

→ Supported formats, subfolder layout, and web search tips: templates/README.md — Adding your own content

4. Review and promote candidates

Template installs stage every new page in candidates/ for review before it enters the wiki. Promote what belongs, discard what doesn’t:

synthadoc candidates list
synthadoc candidates promote --all     # or promote individually by slug
synthadoc candidates discard <slug>

→ CLI commands and Obsidian plugin walkthrough: templates/README.md — Reviewing and promoting candidates

5. Query, lint, and scaffold

synthadoc query "What are the current consumer confidence trends in Canada?"
synthadoc lint run          # validates pages, promotes clean drafts to active
synthadoc lint report       # view issues and citation violations
synthadoc scaffold          # regenerates index.md with richer category links

Lint and scaffold run automatically on a weekly schedule (Sunday 2 AM and 3 AM). Your own content above the <!-- synthadoc:scaffold --> marker in index.md and purpose.md is never overwritten.

→ Schedule customisation and scaffold zone rules: templates/README.md — Scheduled maintenance

6. Context packs and MCP

Template installs include a pre-configured ROUTING.md that automatically scopes queries to the relevant topic branch — no setup needed. If you installed without a template, generate it once with synthadoc routing init.

Build a cited excerpt pack for use in an external agent prompt:

synthadoc context build "Canadian consumer confidence trends" --tokens 4000

Connect Claude Code

README 内容过长，已截取前 64 KB。完整内容请前往 GitHub 仓库查看。