Build a lasting Markdown knowledge base for project decisions, architecture, and session discoveries. Search pages by keywords and tags, use results to answer with citations, and check for outdated content, broken links, and structural problems.
LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)
Review the instructions the agent will receive before you install.
Persistent, self-maintained markdown knowledge base for project and session knowledge. Inspired by Karpathy's LLM Wiki concept.
Process knowledge into wiki pages. A single ingest can touch multiple pages.
wiki_ingest({ title: "Auth Architecture", content: "...", tags: ["auth", "architecture"], category: "architecture" })
Search across all wiki pages by keywords and tags. Returns matching pages with snippets — YOU (the LLM) synthesize answers with citations from the results.
wiki_query({ query: "authentication", tags: ["auth"], category: "architecture" })
Run health checks on the wiki. Detects orphan pages, stale content, broken cross-references, oversized pages, and structural contradictions.
wiki_lint()
Add a single page quickly (simpler than ingest).
wiki_add({ title: "Page Title", content: "...", tags: ["tag1"], category: "decision" })
wiki_list() # Show all pages (reads index.md)
wiki_read({ page: "auth-architecture" }) # Read specific page
wiki_delete({ page: "outdated-page" }) # Delete a page
View wiki operation history by reading .omc/wiki/log.md.
Pages are organized by category: architecture, decision, pattern, debugging, environment, session-log
.omc/wiki/*.md (markdown with YAML frontmatter).omc/wiki/index.md (auto-maintained catalog).omc/wiki/log.md (append-only operation chronicle)Use [[page-name]] wiki-link syntax to create cross-references between pages.
At session end, significant discoveries are automatically captured as session-log pages. Configure via wiki.autoCapture in .omc-config.json (default: enabled).
.omc/wiki/ is project-local)haiku — quick lookups, lightweight inspection, narrow docs worksonnet — standard implementation, debugging, and reviewopus — architecture, deep analysis, consensus planning, and high-risk reviewfable — Claude Fable 5 (above Opus); pass it explicitly on the Task call or pin it per agent with agents.<name>.model/model applies to the main loop only. Delegated agents run on their pinned tier unless the Task call passes model explicitly or the agent is overridden via agents.<name>.model. To run delegated work on Fable, use one of those two surfaces; selecting Fable in /model alone does not change delegation.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Write or revise instructions, specifications, tickets, and skill files so an agent can act without prior chat history. Make rules checkable, explain their reasons, define completion criteria, and keep authoritative information in one place.
Simplify bloated AI-generated code by removing dead code, duplicated logic, and unnecessary layers while checking that existing behavior stays intact. Use a limited cleanup scope, verify changes with relevant checks, or request a review without edits.
Review module relationships and change history to identify structural improvements in a codebase. Receive ranked candidates with file references, suggested changes, and risks, plus a recommendation for where to start, without modifying code.
Send questions, review requests, or implementation tasks to a supported local AI command-line tool through one shared command. The wrapper handles provider-specific options and saves the result as a Markdown file for later reference.
Turn an unclear idea into linked decision tickets on a repository’s issue tracker. Work through one decision per session, record outcomes and dependencies, and prepare a brief defining the objective, scope, and exclusions for delivery.
Turn a short product idea into working code through requirements analysis, technical planning, implementation, testing, and review. It coordinates agents across these stages, fixes detected problems, and reports assumptions that still need a human decision.