# llmwiki

> llmwiki compiles raw sources into persistent, citation-traceable markdown wikis that agents and humans can browse, query, lint, export, import, and reuse.

- [llmwiki: Compile Raw Sources into an Interlinked Wiki](https://llmwiki.atomicstrata.ai/introduction.md): llmwiki turns URLs, files, and session exports into a persistent, citation-traced markdown wiki with configurable domain profiles, semantic search, and MCP agent integration.
- [llmwiki Quickstart: Compile Your First Wiki in Minutes](https://llmwiki.atomicstrata.ai/quickstart.md): Install llmwiki, set your API key, and run llmwiki quickstart to compile a URL or local file into a browsable, interlinked wiki in minutes.
- [Installing llmwiki: npm Setup and Provider Configuration](https://llmwiki.atomicstrata.ai/installation.md): Install llmwiki globally with npm and configure Anthropic, OpenAI-compatible, Ollama, GitHub Copilot, Claude Agent SDK, or Codex CLI.
- [Upgrading from 0.11 to 1.0](https://llmwiki.atomicstrata.ai/upgrading-to-1-0.md): Upgrade an existing llmwiki project to 1.0 without changing its default profile, and complete the one-time embedding index transition.
- [Open Knowledge Format Round Trip](https://llmwiki.atomicstrata.ai/guides/open-knowledge-format.md): Export llmwiki projects as Open Knowledge Format bundles, import external OKF bundles safely, and preserve provenance through re-export.
- [Karpathy's LLM Wiki Pattern and llmwiki](https://llmwiki.atomicstrata.ai/concepts/karpathy-pattern.md): How llmwiki implements Andrej Karpathy's LLM Wiki pattern: compile raw sources into durable, interlinked, citation-traceable knowledge before agents query it.
- [How llmwiki's Two-Phase Pipeline Compiles Your Sources](https://llmwiki.atomicstrata.ai/concepts/how-it-works.md): Understand llmwiki's two-phase LLM pipeline: concept extraction, page generation, incremental change detection, and hybrid retrieval.
- [llmwiki Output Model: Wiki, State, and Activity Journal](https://llmwiki.atomicstrata.ai/concepts/wiki-model.md): Learn how llmwiki organizes compiled wiki pages, wikilinks, the activity journal, and the .llmwiki directory for embeddings and state.
- [Configurable Lifecycle Profiles (CLP)](https://llmwiki.atomicstrata.ai/concepts/configurable-lifecycle-profiles.md): Understand how Configurable Lifecycle Profiles turn llmwiki from a two-directory compiler into a typed, workflow-aware knowledge substrate.
- [Wiki Page Kinds: concept, entity, comparison, overview](https://llmwiki.atomicstrata.ai/concepts/page-types.md): Learn the four page kinds - concept, entity, comparison, overview - their lint expectations, and the epistemic metadata every compiled page can carry.
- [Source Citations and Provenance Tracking in llmwiki](https://llmwiki.atomicstrata.ai/concepts/citations.md): llmwiki traces every paragraph and claim back to the source file and line range. Learn how paragraph and claim-level citations work.
- [llmwiki ingest - Add Sources to Your Wiki Project](https://llmwiki.atomicstrata.ai/cli/ingest.md): llmwiki ingest fetches a URL or copies a local file into sources/. Also covers ingest-session for AI session exports and quickstart for one-step setup.
- [llmwiki compile - Generate Wiki Pages from Sources](https://llmwiki.atomicstrata.ai/cli/compile.md): llmwiki compile runs the incremental two-phase LLM pipeline to extract concepts and generate wiki pages. Key flags: --review and --lang.
- [llmwiki rm - Delete a Source and Its Derived Pages](https://llmwiki.atomicstrata.ai/cli/rm.md): llmwiki rm deletes a source file and the concept pages derived exclusively from it, leaving pages shared with other sources untouched. Preview with --dry-run.
- [llmwiki query - Ask Questions Against Your Compiled Wiki](https://llmwiki.atomicstrata.ai/cli/query.md): llmwiki query answers questions using hybrid semantic search and BM25 reranking over compiled wiki pages. Use --save to persist answers as new pages.
- [llmwiki view - Browse Your Wiki in a Local Web Viewer](https://llmwiki.atomicstrata.ai/cli/view.md): llmwiki view starts a private local web server for browsing, searching, and inspecting your compiled wiki with provenance chips and a graph view.
- [llmwiki status - Inspect Project Health at a Glance](https://llmwiki.atomicstrata.ai/cli/status.md): llmwiki status reports page and source counts, stale and orphaned pages, pending changes, the review queue, and state-file health. Add --json for scripts.
- [llmwiki lint and eval - Wiki Quality Checks and Metrics](https://llmwiki.atomicstrata.ai/cli/lint-eval.md): llmwiki lint finds broken links, stale pages, and citation errors. llmwiki eval measures health scores and citation quality with CI-gateable thresholds.
- [llmwiki export - Export Your Wiki to Portable Formats](https://llmwiki.atomicstrata.ai/cli/export.md): llmwiki export converts your compiled wiki to llms.txt, JSON, JSON-LD, GraphML, Marp slides, or an Open Knowledge Format bundle.
- [llmwiki import - Import Open Knowledge Format Bundles](https://llmwiki.atomicstrata.ai/cli/import.md): llmwiki import --okf reads an Open Knowledge Format bundle and stages its documents for review by default. Use --trusted only for bundles you already trust.
- [profile](https://llmwiki.atomicstrata.ai/cli/profile.md): Create, inspect, and validate the active wiki profile.
- [workflow](https://llmwiki.atomicstrata.ai/cli/workflow.md): Run and inspect declarative profile workflows.
- [artifact](https://llmwiki.atomicstrata.ai/cli/artifact.md): Write and verify profile-declared artifacts.
- [connector](https://llmwiki.atomicstrata.ai/cli/connector.md): Run first-party external-data connectors into review candidates.
- [template](https://llmwiki.atomicstrata.ai/cli/template.md): Install local templates and discover signed remote releases.
- [Review Queue - Inspect and Approve Generated Wiki Pages](https://llmwiki.atomicstrata.ai/cli/review.md): Use llmwiki compile --review and the review subcommands to inspect, approve, or reject generated pages before they land in your wiki.
- [llmwiki serve - MCP Server for AI Agent Integration](https://llmwiki.atomicstrata.ai/cli/serve.md): llmwiki serve starts an MCP server exposing the full compile pipeline to Claude Desktop, Cursor, Claude Code, and any MCP-compatible agent.
- [LLM Provider Setup and Configuration Guide for llmwiki](https://llmwiki.atomicstrata.ai/configuration/providers.md): Configure llmwiki to use Anthropic, OpenAI-compatible endpoints, Ollama, GitHub Copilot, Atlas Cloud, Claude Agent SDK, or OpenAI Codex CLI.
- [llmwiki Environment Variables: Full Reference Guide](https://llmwiki.atomicstrata.ai/configuration/environment-variables.md): Complete reference for all llmwiki environment variables: provider selection, API keys, model overrides, timeouts, output language, and debug flags.
- [Review Policy - Auto-Hold Risky Generated Pages](https://llmwiki.atomicstrata.ai/configuration/review-policy.md): Configure .llmwiki/config.json to automatically hold low-confidence, contradicted, or schema-violating pages for review instead of writing them live.
- [Wiki Schema: Typed Page Kinds and Cross-Link Policies](https://llmwiki.atomicstrata.ai/configuration/schema.md): Define .llmwiki/schema.json to enforce page kinds, minimum wikilinks per kind, and seed pages that compile materializes automatically.
- [Profiles](https://llmwiki.atomicstrata.ai/configuration/profiles.md): Configure typed entities, relations, lifecycles, artifacts, workflows, connectors, and content tiers.
- [AutoSci Profile](https://llmwiki.atomicstrata.ai/configuration/autosci-profile.md): Use AutoSci as a complete example of profiles-as-configuration.
- [Profile Templates](https://llmwiki.atomicstrata.ai/configuration/profile-templates.md): Install structured wiki profiles such as AutoSci and Newsroom without changing llmwiki's default behavior.
- [Connect llmwiki to Claude Desktop, Cursor, and Claude Code](https://llmwiki.atomicstrata.ai/guides/mcp-agent-integration.md): Set up the llmwiki MCP server to let Claude Desktop, Cursor, Claude Code, and other MCP agents ingest, compile, and query your wiki directly.
- [Create a viewer theme](https://llmwiki.atomicstrata.ai/guides/viewer-themes.md): Add a built-in viewer palette while preserving public viewer routes and layout.
- [Using the llmwiki SDK for Programmatic Wiki Control](https://llmwiki.atomicstrata.ai/guides/sdk.md): Use createWiki() to drive llmwiki in-process from TypeScript or JavaScript - ingest, compile, query, lint, and export without shelling out.
- [SDK packages and ownership](https://llmwiki.atomicstrata.ai/guides/sdk-packages.md): Choose the standard compiler, engine-free SDK, or explicit local workflow composition.
- [SDK upgrade notes](https://llmwiki.atomicstrata.ai/guides/sdk-upgrade.md): Compatibility boundaries when adopting the split-package release.
- [Export llmwiki Pages to Atomic Memory with the Bridge](https://llmwiki.atomicstrata.ai/guides/atomic-memory-bridge.md): Use llmwiki export --target json with @atomicmemory/llmwiki to import compiled wiki pages as durable Atomic Memory records with full metadata.
- [Gate CI on llmwiki Wiki Quality Scores and Thresholds](https://llmwiki.atomicstrata.ai/guides/ci-quality-gates.md): Use llmwiki eval with threshold configuration to fail CI when wiki health, citation coverage, or citation quality drops below your defined minimums.
- [Build your first profile](https://llmwiki.atomicstrata.ai/guides/clp/build-your-first-profile.md): Create a custom issue-tracker profile, add a valid page, and see llmwiki recognize it in about ten minutes.
- [AutoSci Research Workflow](https://llmwiki.atomicstrata.ai/guides/autosci-research-workflow.md): Use AutoSci to import papers, propose ideas, record experiment results, and gate completed research artifacts.
- [Newsroom Editorial Workflow](https://llmwiki.atomicstrata.ai/guides/newsroom-editorial-workflow.md): Use the Newsroom template to draft articles, file them under desks, and prove a non-research profile uses the same CLP machinery.
- [Publish a Signed Template Tap](https://llmwiki.atomicstrata.ai/guides/publish-template-tap.md): Package, sign, host, and verify declarative llmwiki profile templates.
- [llmwiki FAQ - Frequently Asked Questions and Answers](https://llmwiki.atomicstrata.ai/troubleshooting/faq.md): Answers to common llmwiki questions: provider setup, compilation errors, query quality, Obsidian compatibility, and scale considerations.
- [Detecting and Repairing Stale and Orphaned Wiki Pages](https://llmwiki.atomicstrata.ai/troubleshooting/stale-pages.md): llmwiki tracks source freshness and flags stale and orphaned pages. Learn how to detect them with lint and repair them with refresh --stale.
- [Recovering State Written by a Newer llmwiki Version](https://llmwiki.atomicstrata.ai/troubleshooting/state-recovery.md): When .llmwiki/state.json was written by a newer llmwiki version, commands fail closed. Use llmwiki state reset to back up and reset the file and continue.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.