{"data":{"slug":"axoviq-ai-synthadoc","name":"synthadoc","tagline":"An open-source LLM knowledge compilation engine turning raw documents into structured wikis","github_url":"https://github.com/axoviq-ai/synthadoc","owner":"axoviq-ai","repo":"synthadoc","owner_avatar_url":"https://avatars.githubusercontent.com/u/275206488?v=4","primary_language":"Python","stars":1226,"forks":123,"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"],"archived":false,"github_pushed_at":"2026-09-20T04:13:27+00:00","maintenance_label":"Very active","stars_delta_30d":256,"url":"https://www.graphcanon.com/tools/axoviq-ai-synthadoc","markdown_url":"https://www.graphcanon.com/tools/axoviq-ai-synthadoc.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/axoviq-ai-synthadoc","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=axoviq-ai-synthadoc","description":"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.","homepage_url":null,"license":"AGPL-3.0","open_issues":6,"watchers":16,"ai_summary":"Synthadoc aims to convert raw document data into organized and readily accessible wiki structures without relying on traditional RAG techniques.","readme_excerpt":"### Install a wiki and start the engine\n\nA **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).\n\n```bash\n\n---\n\n### 1. Pick a template and install\n\nBrowse the 30 available templates across 9 categories and pick the one closest to your domain:\n\n```bash\nsynthadoc templates list\n```\n\nInstall with a template (example: consumer and competitive market research):\n\n```bash\nsynthadoc install my-market-wiki --target ~/wikis --template research/market-research\nsynthadoc use my-market-wiki   # set as default — no -w needed from here on\n```\n\nIf none of the 30 templates fits, install without one and provide a `--domain` description instead:\n\n```bash\nsynthadoc install my-wiki --target ~/wikis --domain \"Your domain description\"\n```\n\n→ Full template catalog and per-category install commands: [synthadoc/templates/README.md](synthadoc/templates/README.md)\n\n---\n\n# Install the demo (includes pre-built pages and raw sources — no LLM call needed)\nsynthadoc install history-of-computing --target ~/wikis --demo\n\n---\n\n# Install with a domain template — pre-configured guidelines, routing, and starter pages\nsynthadoc install my-finance-wiki --target ~/wikis --template finance/investment\n\n---\n\n# Reinstall the Obsidian plugin into a wiki's vault — normally done automatically by synthadoc install\nsynthadoc plugin install history-of-computing\n\n---\n\n# Ingest history: timestamp, source file, wiki page, tokens, cost\nsynthadoc audit history -w my-wiki                    # last 50 records (shows total)\nsynthadoc audit history -n 100 -w my-wiki             # last 100 records\nsynthadoc audit history -n 50 --offset 50 -w my-wiki  # page 2 (records 51-100)\nsynthadoc audit history --json -w my-wiki             # raw JSON for scripting\n\n---\n\n# Query history: question, sub-questions, tokens, cost\nsynthadoc audit queries -w my-wiki                    # last 50 records (shows total)\nsynthadoc audit queries -n 100 -w my-wiki             # last 100 records\nsynthadoc audit queries -n 50 --offset 50 -w my-wiki  # page 2 (records 51-100)\nsynthadoc audit queries --json -w my-wiki             # raw JSON for scripting\n\n---\n\n# Audit events: contradictions found, auto-resolutions, cost gate triggers\nsynthadoc audit events -w my-wiki                      # last 100 events (shows total)\nsynthadoc audit events -n 100 --offset 100 -w my-wiki  # page 2 (events 101-200)\nsynthadoc audit events --json -w my-wiki               # raw JSON for scripting\n\n---\n\n# Agent-ready JSON with provenance, lifecycle history, and compilation cost\nsynthadoc export --format json --output exports/wiki.json -w my-wiki","github_created_at":"2026-04-11T03:50:12+00:00","created_at":"2026-07-15T10:59:14.427667+00:00","updated_at":"2026-09-20T05:02:04.931102+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"enterprise-solutions","name":"enterprise-solutions"},{"slug":"knowledge-graph","name":"knowledge-graph"},{"slug":"local-llm","name":"local-llm"},{"slug":"personal-knowledge-management","name":"personal-knowledge-management"},{"slug":"synthetic-data","name":"synthetic-data"}],"trust":{"provenance":{"is_fork":false,"github_id":1207529559,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:02:02.263Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":16,"days_since_push":0,"last_release_at":"2026-09-17T19:27:47Z","stars_delta_30d":256,"open_issues_delta_30d":-1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:59:15.582Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:02:03.289Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-20T05:02:03.289Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T05:02:03.289Z"},"license_spdx":{"value":"AGPL-3.0","source":"github.license","observed_at":"2026-09-20T05:02:03.289Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Use Synthadoc when seeking transparency in the transformation of raw document data to a human-readable wiki format, offering local-first management and self-improvement capabilities.","Consider it if your organization values an enterprise-level solution for personal knowledge management (PKM) that can adapt specifically to your domain needs without requiring external dependencies."],"when_not_to_use":["Do not use Synthadoc if you require traditional RAG techniques in handling document compilation, as this tool explicitly avoids them.","Avoid it when an integrated solution with third-party tools is needed since it focuses on being a standalone, self-managed and self-improved system."],"source":"enrich:decision_facts","observed_at":"2026-07-16T18:49:14.311Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Synthadoc is an open-source compilation engine that turns raw documents into structured wikis locally without using RAG techniques."}]}}