Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
npx -y [email protected]Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
claude mcp add llm-wiki-compiler -- npx -y llm-wiki-compiler@1.5.0รันในเทอร์มินัล
{ "mcpServers": { "llm-wiki-compiler": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิด1.5.0 is the stable release on npm latest: npm install --global llm-wiki-compiler.
llmwiki compile --no-pages-limit drops the fixed concept count.llmwiki view refreshes after a compile without a restart and reads its port from LLMWIKI_VIEW_PORT.Review generated answers and their citations before they become pages, approve a batch of pages in one operation, and trace an answer back to the pages that informed it. Release notes · Upgrade guide
Meet Scientific Clay, with soft surfaces and rounded typography, and Minimal, which follows your system’s light or dark setting. Switch instantly between four themes, including Nebula Light and Dark.
The same page in a demonstration wiki. Click either screenshot for a closer look.
Recursive source folders, path exclusions, project-specific compile instructions, and storage for larger embedding indexes.
Browse profile-defined categories, declared fields, connected records, provenance, and supporting source passages in the local viewer.
Create signed template distributions, discover them through explicitly trusted catalogs, and install or update them with compatibility checks.
Build a knowledge system around the way you work. Define your records, relationships, review gates, and workflows in one validated profile. Start with AutoSci for research or Newsroom for editorial work, or create your own.
Compile raw sources into an interlinked, citation-traceable markdown wiki that agents and humans can browse, query, lint, export, and reuse. The default profile preserves the classic concepts-and-queries layout; optional profiles add domain-specific types and workflows without adding domain branches to the compiler.
llmwiki implements the LLM Wiki pattern: instead of re-discovering knowledge from raw files at query time, compile it once into durable pages that accumulate structure, provenance, review state, and retrieval metadata over time.
Use llmwiki when you need a persistent knowledge base from raw material:
llms.txt.Do not use llmwiki as a general static-site generator, a heavy ontology database, or a replacement for ad-hoc search over fast-changing raw logs. It is strongest when source knowledge is worth compiling, reviewing, and reusing.
concept, entity, comparison, and overview..llmwiki/profile.json can declare entity schemas, typed relations, lifecycle state machines, transition requirements, workflows, artifacts, connectors, content tiers, and retrieval policy.llmwiki template init autosci creates a research project with papers, ideas, experiments, manuscripts, evidence artifacts, workflows, and Crossref import. newsroom demonstrates the same machinery for editorial work.llmwiki lint validates the links.llmwiki view opens a read-only browser UI with search, page metadata, graph exploration, source-freshness badges, and citation chips.llmwiki lint and llmwiki next surface stale/orphaned pages; llmwiki refresh --stale repairs changed knowledge without compiling unrelated new sources.llmwiki eval reports health score, a per-page health distribution that flags the worst pages, wikilink-graph health, citation coverage/precision, corpus stats, regression deltas, and optional judge-model citation support.llmwiki serve exposes ingest, compile, query, lint, read, status, eval, context-pack, and OKF exchange tools to MCP-compatible agents.createWiki({ root }) drives ingest, compile, query, context, status, export, eval, and OKF import/export from TypeScript without shelling out.llms.txt for downstream systems.CLP turns llmwiki's knowledge compiler into a reusable substrate for domain-specific knowledge systems. A validated .llmwiki/profile.json is the single contract for:
These rules are enforced by the runtime, not left as prompt conventions. The CLI, SDK, MCP server, viewer, context builder, lint, status, export, and OKF exchange surfaces all operate from the same profile contract. Invalid profiles and writes that bypass a declared gate fail closed.
CLP is backward-compatible by construction: a project without .llmwiki/profile.json uses the built-in default concepts-and-queries profile and preserves the pre-1.0 behavior. You can start three ways — scaffold your own profile, install a built-in or local template, or install a signed template from a trusted tap:
# author your own profile, one entity type at a time
llmwiki profile init research --entity paper
# or install a built-in or local declarative template
llmwiki template list
llmwiki template inspect autosci
llmwiki template init autosci
llmwiki profile validate
llmwiki workflow list
autosci is a practical research system with papers, ideas, experiments, manuscripts, evidence artifacts, workflows, and Crossref ingestion. newsroom applies the same generic machinery to articles, desks, bylines, and editorial workflows. Templates contain configuration and examples, never executable plugin code.
Templates can also be distributed securely. Publishers build signed, offline distributions with llmwiki template publish — Ed25519 signing, key rotation, and package revocation — and verify them with template publish verify. Consumers add explicitly trusted taps, discover and inspect signed catalogs, and install or update templates with continuity, revocation, and compatibility checks enforced under lock.
Read the CLP concept guide, follow the AutoSci research workflow, or explore the Newsroom editorial workflow.
Andrej Karpathy described the LLM Wiki pattern as a way to turn raw material into compiled knowledge that future agents can reuse. llmwiki is a concrete compiler for that pattern.
The key shift is moving work from query time to compile time. Traditional RAG repeatedly retrieves raw chunks and asks the model to reconstruct relationships for each question. llmwiki first turns sources into typed, interlinked pages with citations, metadata, and review state. Queries, context packs, exports, and MCP tools then operate over that compiled artifact.
That makes llmwiki useful when knowledge should compound: concepts shared across sources become one page, saved answers become future context, stale pages can be detected and repaired, and agents can consume a stable evidence pack instead of re-reading the same raw files from scratch.
See docs/concepts/karpathy-pattern.mdx for the deeper explanation.
Use llmwiki for a reusable corpus of documents, research, or project knowledge.
Start with wiki_status and get_context_pack when you need evidence for your
own reasoning. A one-off file read or live web search does not need a wiki.
The npm package includes an Agent Skill. See the
MCP setup guide for installation.
The MCP Registry identifier is io.github.atomicstrata/llmwiki; the npm package
is llm-wiki-compiler and the executable is llmwiki.
Choose the entry point that matches the task:
npm install -g llm-wiki-compiler
export ANTHROPIC_API_KEY=sk-...
# or choose another provider:
# export LLMWIKI_PROVIDER=openai
# export OPENAI_API_KEY=sk-...
llmwiki quickstart ./notes.md
llmwiki query "what are the key ideas?"
llmwiki view --open
quickstart ingests one source, compiles pages, and opens the viewer. Inside an existing project, run llmwiki next when you want the safest next action.
To start with a domain model instead of the default concepts-and-queries layout:
mkdir research-wiki && cd research-wiki
llmwiki template inspect autosci
llmwiki template init autosci
llmwiki profile validate
llmwiki workflow list
Template installation is for a new or empty typed project. It materializes the chosen profile into .llmwiki/profile.json; normal project loading never depends on a template registry or lockfile.
Try it on any article or document:
mkdir my-wiki && cd my-wiki
llmwiki quickstart https://en.wikipedia.org/wiki/Andrej_Karpathy
llmwiki query "What terms did Andrej coin?"
The examples/basic/ directory includes a small pre-generated wiki you can inspect without an API key.
Full command docs live in docs/cli/.
llmwiki is an Open Knowledge Format (OKF) producer and consumer. OKF is a Google Cloud initiative for sharing compiled knowledge as portable markdown files with structured frontmatter.
llmwiki export --target okf --out ./dist/okf
llmwiki import --okf ./dist/okf --dry-run
llmwiki import --okf ./dist/okf
OKF import is intentionally review-first: untrusted bundles become review candidates, not live wiki pages. The importer preserves foreign OKF metadata, stores llmwiki provenance under x-llmwiki, and re-exports imported pages honestly after local edits, including safe original nested paths.
A project has raw inputs in sources/, compiled markdown in wiki/, and compiler state under .llmwiki/:
sources/
raw source files
wiki/
concepts/ compiled pages
queries/ saved answers
<entity>/ profile-declared typed pages
graph/ typed relation and audit-event stores
outputs/ derived workflow projections
index.md generated TOC
.llmwiki/
profile.json active domain contract
template-lock.json advisory install provenance
config.json review policy and source selection
schema.json page-kind/cross-link policy
state.json source hashes and ownership
candidates/ held review candidates
workflows/ signed workflow run state
eval/ quality history and thresholds
artifacts/ hash-pinned profile-declared files and manifests
log.md activity journal
Compiled pages are plain markdown with YAML frontmatter, plus enough metadata for agents to reason about citations, freshness, confidence, contradictions, and review state. See docs/concepts/wiki-model.mdx.
Sources are top-level Markdown files by default. Opt into nested source folders and exclusions in project config. Excluding a compiled source retires its contribution on the next ordinary compile without deleting the source file.
Run:
llmwiki serve --root /path/to/wiki-project
MCP clients can ingest sources, compile, query, search pages, read pages, lint, run eval, inspect status, request context packs, and exchange OKF bundles. Read-only tools work without provider credentials; LLM-backed tools validate provider credentials at call time. The run_eval tool runs its fast suite without a provider; its full suite (which LLM-judges citation support) requires one.
import { createWiki } from "llm-wiki-compiler";
const wiki = createWiki({ root: "/path/to/wiki-project" });
await wiki.ingest({ source: "./notes.md" });
await wiki.compile();
const answer = await wiki.query({ question: "What changed?" });
See docs/guides/sdk.mdx. llm-wiki-compiler is the
supported entry point; its scoped supporting packages are implementation
dependencies. The local workflow engine and an application's own coordinator
are two tiers, not a migration path: llmwiki workflow runs a profile-declared
workflow through local invocations with persisted state between sessions.
An external coordinator calls the same SDK without using local workflow
execution methods; the supporting engine dependency remains installed. See
SDK package selection,
SDK upgrade notes, and
When to use the local engine.
Minimum requirement: Node.js 24 or newer.
The default provider is Anthropic:
export ANTHROPIC_API_KEY=sk-...
Provider selection is environment-driven:
llmwiki is designed for auditable generated knowledge:
compile --review or .llmwiki/config.json review policy to hold risky pages as candidates.fresh/stale/unverified); computed-orphaned pages (all sources deleted) surface only as lint and viewer signals and are dropped from the export.llmwiki lint and llmwiki eval can enforce quality thresholds.See docs/configuration/review-policy.mdx, docs/troubleshooting/stale-pages.mdx, and docs/guides/ci-quality-gates.mdx.
llmwiki is still early software, but it is no longer a toy pipeline for a handful of notes.
--concurrency / LLMWIKI_COMPILE_CONCURRENCY), cutting wall-clock on large compiles.eval --suite full runs cheaper.The current sweet spot is a durable project or domain wiki: research folders, codebase docs, team handbooks, standards, design notes, decision logs, or curated source packs. The less ideal fit is a high-churn firehose where raw search is enough and compiled structure would go stale faster than it can be reviewed.
The full docs site source is in docs/:
docs/introduction.mdxdocs/quickstart.mdxdocs/installation.mdxdocs/concepts/karpathy-pattern.mdxdocs/concepts/how-it-works.mdxdocs/concepts/wiki-model.mdxdocs/concepts/configurable-lifecycle-profiles.mdxdocs/guides/autosci-research-workflow.mdxdocs/guides/newsroom-editorial-workflow.mdxdocs/configuration/profile-templates.mdxdocs/cli/docs/guides/open-knowledge-format.mdxdocs/guides/mcp-agent-integration.mdxdocs/guides/sdk.mdxdocs/guides/sdk-packages.mdx, docs/guides/sdk-upgrade.mdxARCHITECTURE.mddocs/guides/atomic-memory-bridge.mdxPreview the docs locally with Node 24:
cd docs
volta run --node 24 npx mint dev --port 3001
Stable release 1.5.0: The current release on the npm latest dist-tag. It ships the same code as the 1.5.0-rc.1 candidate.
ARCHITECTURE.md.LLMWIKI_PROVIDER=converse connects to a bearer-authenticated endpoint speaking the Converse protocols, with streaming and structured extraction. Its AWS protocol packages are optional and load only when you select it. See provider setup.--no-pages-limit extraction. llmwiki compile --no-pages-limit removes the requested 3–8 concepts per source, so a source yields the pages it supports.llmwiki view rebuilds its snapshot in the background after a compile, stops refreshing cleanly on close, and reads LLMWIKI_VIEW_PORT when --port is not given.sources/ no longer hangs freshness checks.v7. Every newly generated page records prompt version v7, including pages from default runs. Unchanged sources are not recompiled by upgrading alone.npm install --global llm-wiki-compiler
The supporting packages are pinned to the same version and install with it. The MCP Registry entry io.github.atomicstrata/llmwiki is published for 1.5.0 after the npm release. Existing projects need no migration; read the upgrade notes for the prompt-version change and the opt-in Converse dependencies.
Released 1.4.2: Fixes llmwiki compile with the codex-agent provider and carries the 1.4.0 features: answer review before publishing, batch approval, extraction reuse, page-level answer citations, and the split-package SDK with matching supporting dependencies.
Experimental artifact types and workflow statuses can require source updates; read the SDK upgrade notes before upgrading from 1.3. See the 1.4.0 release summary and changelog for migration details, contributor credits, and limits.
Released 1.3.0:
See the 1.3.0 release summary and changelog for migration details, contributor credits, and limits.
Released 1.2.0:
Windows path fixes are included, but native Windows validation and CI remain outstanding. Full filesystem-confinement guarantees on Windows remain unverified. Use a supported Linux environment for untrusted projects; see #217.
Released 1.1.0:
template publish init | add | build | rotate | revoke (Ed25519 signing, key rotation, package revocation) and verify them with template publish verify.llmwiki status command: a readable snapshot of page and source counts, last compile, stale and orphaned pages, pending changes, the review queue, active profile, and state-file health.Released 1.0.0:
autosci and newsroom templates, typed workflows and actions, first-class artifacts, typed relations and runtime lifecycle gates, plus a hardened first-party connector substrate with Crossref.See CHANGELOG.md for release history.
llmwiki and Atomic Memory are complementary open context infrastructure:
Use them independently or together. The @atomicmemory/llmwiki bridge imports llmwiki export --target json --project-id <id> as durable memory records.
Contributions are welcome. If llmwiki is missing something you need, open an issue or PR and describe the workflow you are trying to support - need-driven improvements are often the best ones. If you want to contribute more generally, roadmap items are a good place to start. For larger changes to core compile, review, import/export, or retrieval semantics, please start with an issue or design discussion so we can align on the contract first.
Before committing code changes, run:
npx tsc --noEmit
npm run build
npm test
npm run fallow:ci
See CONTRIBUTING.md.
MIT
No LLMs were harmed in the making of this repo.
Compile documents into a persistent, cited knowledge wiki for AI agents. CLI, MCP server, and TypeScript SDK.
{ "mcpServers": { "llm-wiki-compiler": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Llm Wiki Compiler ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-16 Compile documents into a persistent, cited knowledge wiki for AI agents. CLI, MCP server, and TypeScript SDK.