@wsl8297: If you have a bunch of PDFs, documents, project materials to feed to AI, Synthadoc is a direction worth looking at. GitHub: https://github.com/axoviq-ai/synthadoc… It compiles raw materials into a structured wiki at ingestion time, automatically...

If you have a pile of PDFs, documents, or project files to feed into AI, Synthadoc is a direction well worth looking into. GitHub: https://github.com/axoviq-ai/synthadoc… It compiles raw source materials into a structured wiki at ingestion time, automatically building cross-references, detecting contradictions, flagging orphan pages, and outputting plain Markdown files that you can use directly in Obsidian.
Use cases:
• Independent developers who need to organize personal research into a knowledge base
• Small teams that want to unify internal documentation into a traceable wiki
• Compliance-sensitive enterprises that cannot put data in the cloud
• Knowledge management that requires offline access and no tool lock-in

More reliable than RAG’s query-time synthesis — contradictions don’t get blended together, and knowledge doesn’t scatter into fragments.

Watch the Synthadoc demo (https://www.youtube.com/watch?v=rIGO6zi9XQE) ▶
Watch the demo on YouTube (https://www.youtube.com/watch?v=rIGO6zi9XQE)

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:

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 (https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f)

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

1. RAG conflates contradictions; Synthadoc surfaces them

When two sources disagree, vector search returns both and the LLM silently blends them. Synthadoc detects the conflict during ingest, flags the page with status: contradicted, preserves both claims with citations, and either auto-resolves (if confidence ≥ threshold) or queues the conflict for human review.

2. Knowledge fragments; Synthadoc links it

RAG chunks are isolated. Synthadoc builds [[wikilinks]] between related pages during every ingest pass. The resulting graph is visible in Obsidian’s Graph view and queryable with Dataview.

3. Orphan knowledge has no address; Synthadoc finds it

Pages that exist but are referenced by nothing are surfaced by the lint system, with ready-to-paste index entries so you can quickly integrate them.

4. LLM-compiled content can be overconfident; Synthadoc audits it

An LLM synthesising source documents naturally produces confident prose — but may overstate claims, omit caveats, or accept a source’s framing uncritically. The adversarial lint pass runs a concurrent second-LLM review of every page: it plays devil’s advocate to surface issues the primary model accepted too readily — contested estimates, unsupported superlatives, and claims that contradict well-established facts. Warnings are stored in page frontmatter and surfaced in both the CLI report and the Obsidian lint modal. The reviewer is calibrated to flag only high-confidence issues, producing a useful signal without noise. For the strongest signal, point the adversarial pass at a different model family: a distinct model is far more likely to challenge assumptions than the same model reviewing its own output.

Claim-Level Provenance

Every substantive claim in the wiki is annotated with ^[filename:L-L] — a citation pointing to the exact line range in the source file it came from. Click the citation chip in Obsidian to open a Source Viewer showing the highlighted passage; for PDF sources, Synthadoc resolves the PDF page number automatically via a pagemap sidecar. A global Provenance modal shows all citations across the wiki, sortable and filterable. Broken citations are caught by the lint system and logged in the audit trail. Run synthadoc audit citations to query citations from the CLI.

5. Re-synthesis is expensive; Synthadoc caches it

A 3-layer cache (embedding, LLM response, provider prompt cache) means repeated lint runs on unchanged pages cost near-zero tokens.

6. Knowledge is locked in tools; Synthadoc escapes it

Every page is a plain Markdown file with YAML frontmatter. No proprietary format. Open the folder in any editor, put it in git, sync it with any cloud drive.

7. Wiki structure decays as content grows; Synthadoc regenerates it

As the wiki accumulates pages the index.md table of contents, domain scope (purpose.md), and LLM behaviour guidelines (AGENTS.md) can drift out of sync with actual content. The scaffold command re-generates all three from the current wiki state using the LLM — creating category-aware index entries, refreshed scope boundaries, and updated terminology guidelines — without touching pages already linked in the index. Run it once after initial install to get a rich scaffold, then schedule it weekly as the wiki grows.

Business values

Why Synthadoc?

Competitive advantages

Key differentiators vs. RAG

RAG chunks documents and retrieves them at query time. Synthadoc compiles knowledge: every new source is synthesized into the existing wiki graph at ingest time.

• Contradictions are caught, not blended. When two sources disagree, Synthadoc flags the page — RAG silently averages both claims.
• Knowledge is linked, not scattered. [[wikilinks]] connect related pages into a navigable graph visible in Obsidian and queryable with Dataview.
• The artifact outlives the tool. Close the server, open the wiki folder in any Markdown editor — the knowledge is all there, human-readable, no proprietary format.
• Cost-efficient at scale. Two-step ingest with cached analysis means repeated ingest of similar sources costs near-zero tokens. Three cache layers stack for lint and query too.
• Ingest is durable, not fragile. Every ingest request becomes a queued job with automatic retry and a persistent audit record. Batch a hundred documents and resume after a crash — no work is lost.

Architecture

Synthadoc 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

Prerequisites

LLM API key — at least one required (unless using Claude Code or Opencode — see the last two rows below):

Tavily API key (optional — enables web search): Get a free key at tavily.com (https://tavily.com). Without it, web search jobs will fail but all other features work normally.

Step 1 — Clone and install

``bash
git clone https://github.com/paul(Note: The README continues beyond this point, but the user’s input cut off at “git clone https://github.com/paul…”. I will include the rest as provided in the user’s message. Since the input ends mid-sentence, I’ll output only what was given, after the translated Chinese part.)

The user’s original message ends with “git clone https://github.com/paul” — I will include that exactly as given, as part of the English README. So the final output will be the translated Chinese paragraph, then the horizontal rule, then the entire English README content from the user’s message, including the truncated last line.If you have a pile of PDFs, documents, or project files to feed into AI, Synthadoc is a direction well worth looking into. GitHub: https://github.com/axoviq-ai/synthadoc… It compiles raw source materials into a structured wiki at ingestion time, automatically building cross-references, detecting contradictions, flagging orphan pages, and outputting plain Markdown files that you can use directly in Obsidian.
Use cases:
• Independent developers who need to organize personal research into a knowledge base
• Small teams that want to unify internal documentation into a traceable wiki
• Compliance-sensitive enterprises that cannot put data in the cloud
• Knowledge management that requires offline access and no tool lock-in

More reliable than RAG’s query-time synthesis — contradictions don’t get blended together, and knowledge doesn’t scatter into fragments.

Watch the Synthadoc demo (https://www.youtube.com/watch?v=rIGO6zi9XQE) ▶
Watch the demo on YouTube (https://www.youtube.com/watch?v=rIGO6zi9XQE)

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:

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 (https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f)

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

1. RAG conflates contradictions; Synthadoc surfaces them

When two sources disagree, vector search returns both and the LLM silently blends them. Synthadoc detects the conflict during ingest, flags the page with status: contradicted, preserves both claims with citations, and either auto-resolves (if confidence ≥ threshold) or queues the conflict for human review.

2. Knowledge fragments; Synthadoc links it

RAG chunks are isolated. Synthadoc builds [[wikilinks]] between related pages during every ingest pass. The resulting graph is visible in Obsidian’s Graph view and queryable with Dataview.

3. Orphan knowledge has no address; Synthadoc finds it

Pages that exist but are referenced by nothing are surfaced by the lint system, with ready-to-paste index entries so you can quickly integrate them.

4. LLM-compiled content can be overconfident; Synthadoc audits it

An LLM synthesising source documents naturally produces confident prose — but may overstate claims, omit caveats, or accept a source’s framing uncritically. The adversarial lint pass runs a concurrent second-LLM review of every page: it plays devil’s advocate to surface issues the primary model accepted too readily — contested estimates, unsupported superlatives, and claims that contradict well-established facts. Warnings are stored in page frontmatter and surfaced in both the CLI report and the Obsidian lint modal. The reviewer is calibrated to flag only high-confidence issues, producing a useful signal without noise. For the strongest signal, point the adversarial pass at a different model family: a distinct model is far more likely to challenge assumptions than the same model reviewing its own output.

Claim-Level Provenance

Every substantive claim in the wiki is annotated with ^[filename:L-L] — a citation pointing to the exact line range in the source file it came from. Click the citation chip in Obsidian to open a Source Viewer showing the highlighted passage; for PDF sources, Synthadoc resolves the PDF page number automatically via a pagemap sidecar. A global Provenance modal shows all citations across the wiki, sortable and filterable. Broken citations are caught by the lint system and logged in the audit trail. Run synthadoc audit citations to query citations from the CLI.

5. Re-synthesis is expensive; Synthadoc caches it

A 3-layer cache (embedding, LLM response, provider prompt cache) means repeated lint runs on unchanged pages cost near-zero tokens.

6. Knowledge is locked in tools; Synthadoc escapes it

Every page is a plain Markdown file with YAML frontmatter. No proprietary format. Open the folder in any editor, put it in git, sync it with any cloud drive.

7. Wiki structure decays as content grows; Synthadoc regenerates it

As the wiki accumulates pages the index.md table of contents, domain scope (purpose.md), and LLM behaviour guidelines (AGENTS.md) can drift out of sync with actual content. The scaffold command re-generates all three from the current wiki state using the LLM — creating category-aware index entries, refreshed scope boundaries, and updated terminology guidelines — without touching pages already linked in the index. Run it once after initial install to get a rich scaffold, then schedule it weekly as the wiki grows.

Business values

Why Synthadoc?

Competitive advantages

Key differentiators vs. RAG

RAG chunks documents and retrieves them at query time. Synthadoc compiles knowledge: every new source is synthesized into the existing wiki graph at ingest time.

• Contradictions are caught, not blended. When two sources disagree, Synthadoc flags the page — RAG silently averages both claims.
• Knowledge is linked, not scattered. [[wikilinks]] connect related pages into a navigable graph visible in Obsidian and queryable with Dataview.
• The artifact outlives the tool. Close the server, open the wiki folder in any Markdown editor — the knowledge is all there, human-readable, no proprietary format.
• Cost-efficient at scale. Two-step ingest with cached analysis means repeated