LLM Wiki

Copy MarkdownOpen

wiki.json   # Configuration (read by /llms.txt)
schema.md   # LLM instructions (optional, free-form)
raw/        # Immutable source documents
raw/docs/   # Markdown converted from uploaded files
wiki/       # LLM-generated pages (one .md per page)

GET /v1/repos/:slug/wiki/pages

{
  "pages": [
    {
      "path": "wiki/transformers.md",
      "title": "Transformer Architecture",
      "summary": "The dominant architecture for sequence modeling since 2017",
      "tags": ["deep-learning"],
      "type": "concept",
      "updated": "2026-04-10",
      "word_count": 1250,
      "sources": ["raw/attention-paper.md"],
      "related": ["wiki/attention.md"]
    }
  ],
  "count": 1,
  "at_version": "main"
}

const { data } = await cg.wiki.listPages("my-research");

GET /v1/repos/:slug/wiki/pages/:path

{
  "path": "wiki/transformers.md",
  "frontmatter": {
    "title": "Transformer Architecture",
    "summary": "The dominant architecture for sequence modeling since 2017",
    "tags": ["deep-learning"],
    "type": "concept",
    "sources": ["raw/attention-paper.md"],
    "related": ["wiki/attention.md"],
    "updated": "2026-04-10"
  },
  "content": "---\ntitle: \"Transformer Architecture\"\n...\n---\n\n## Truth\n...",
  "compiled_truth": "## Truth\n\nA transformer is...",
  "timeline": "- **2026-04-10 (sync)**: refined attention section.\n",
  "has_dual_section": true,
  "word_count": 1250,
  "version_id": "9c3a1f...",
  "at_version": "main"
}

const { data } = await cg.wiki.getPage("my-research", "wiki/transformers.md");

GET /v1/repos/:slug/wiki/sources

{
  "sources": [
    { "path": "raw/attention-paper.md", "size": 0 }
  ],
  "count": 1,
  "at_version": "main"
}

const { data } = await cg.wiki.listSources("my-research");

GET /v1/repos/:slug/wiki/sources/:path

{
  "path": "raw/attention-paper.md",
  "content": "Attention Is All You Need\n\n...",
  "size": 8421,
  "version_id": "9c3a1f...",
  "at_version": "main"
}

const { data } = await cg.wiki.getSource("my-research", "raw/attention-paper.md");

GET /v1/repos/:slug/wiki/graph

{
  "nodes": [
    { "path": "wiki/transformers.md", "title": "Transformer Architecture", "tags": ["deep-learning"], "type": "concept", "word_count": 1250 },
    { "path": "raw/attention-paper.md", "title": "attention-paper.md", "tags": [], "type": "source", "word_count": 0 }
  ],
  "edges": [
    { "source": "wiki/transformers.md", "target": "wiki/attention.md", "type": "related" },
    { "source": "wiki/transformers.md", "target": "raw/attention-paper.md", "type": "source-ref" },
    { "source": "wiki/transformers.md", "target": "wiki/bert.md", "type": "shared-tag", "tag": "deep-learning" }
  ],
  "tag_clusters": {
    "deep-learning": ["wiki/transformers.md", "wiki/bert.md"]
  },
  "stats": { "pages": 42, "sources": 15, "links": 87, "orphans": 3 },
  "at_version": "main"
}

const { data } = await cg.wiki.graph("my-research");

GET /v1/repos/:slug/wiki/stats

{
  "pages": 42,
  "sources": 15,
  "words": 52500,
  "links": 87,
  "orphans": 3,
  "dual_section_pages": 28,
  "at_version": "main"
}

const { data } = await cg.wiki.stats("my-research");

GET /v1/repos/:slug/wiki/llms.txt

# AI Research Wiki
> Deep dive into transformer architectures

## Pages
- [Transformer Architecture](wiki/transformers.md): The dominant architecture for sequence modeling since 2017
- [Attention Mechanism](wiki/attention.md): Core mechanism enabling transformers to weigh input tokens

## Sources
- raw/attention-paper.md

{
  "version": 1,
  "title": "AI Research Wiki",
  "description": "Deep dive into transformer architectures",
  "llms_txt": {
    "include_sources": false,
    "max_pages": 500,
    "sort": "updated"
  }
}

const { data } = await cg.wiki.llmsTxt("my-research", { format: "full" });

GET /v1/repos/:slug/wiki/pages/:path/history

{
  "path": "wiki/transformers.md",
  "activity": [
    {
      "version_id": "9c3a1f8b...",
      "changed_by": { "name": "Wiki Agent", "email": "agent@example.com" },
      "changed_at": "2026-04-10T08:00:00Z",
      "summary": "sync: refined attention section",
      "message": "sync: refined attention section\n\nApplied feedback from raw/transformer-review.md."
    }
  ],
  "count": 1
}

GET /v1/repos/:slug/wiki/pages/:path/as-of

{
  "path": "wiki/transformers.md",
  "frontmatter": { "title": "Transformer Architecture", "tags": ["deep-learning"] },
  "compiled_truth": "## Truth\n\nA transformer is...",
  "timeline": "- **2026-03-12 (sync)**: initial draft.\n",
  "version_id": "5e7a2c...",
  "as_of": "2026-03-15T00:00:00Z"
}

POST /v1/repos/:slug/wiki/pages/:path/restore

{ "version_id": "5e7a2c8b..." }

{
  "path": "wiki/transformers.md",
  "version_id": "a1b2c3d4...",
  "restored_from": "5e7a2c8b..."
}

POST /v1/repos/:slug/wiki/documents
Content-Type: multipart/form-data

{
  "path": "raw/docs/attention-paper.md",
  "original_filename": "attention-paper.pdf",
  "bytes": 8421334,
  "markdown_length": 65440,
  "run_id": "f8b2c1..."
}

GET /v1/repos/:slug/wiki/documents

{
  "documents": [
    {
      "path": "raw/docs/attention-paper.md",
      "name": "attention-paper.md",
      "sha": "9c3a1f..."
    }
  ]
}

POST /v1/repos/:slug/wiki/run

{
  "mode": "sync",
  "source_ids": ["raw/attention-paper.md"],
  "force": false,
  "model": "claude-sonnet-4-6",
  "max_tokens_budget": 200000
}

{ "run_id": "f8b2c1...", "status": "queued" }

GET /v1/repos/:slug/wiki/runs

{
  "runs": [
    {
      "id": "f8b2c1...",
      "orgId": "...",
      "repoSlug": "my-research",
      "namespace": null,
      "mode": "sync",
      "status": "running",
      "trigger": "manual",
      "model": "claude-sonnet-4-6",
      "sourceIds": ["raw/attention-paper.md"],
      "createdAt": "2026-04-10T08:00:00Z",
      "finishedAt": null
    }
  ],
  "count": 1
}

GET /v1/repos/:slug/wiki/runs/:id

POST /v1/repos/:slug/wiki/cancel

{ "run_id": "f8b2c1..." }

{ "ok": true }

POST /v1/repos/:slug/wiki/sandboxes

{ "name": "draft-attention-rewrite", "from": "main" }

{ "name": "draft-attention-rewrite", "version_id": "9c3a1f..." }

GET /v1/repos/:slug/wiki/sandboxes

{
  "sandboxes": [
    { "name": "draft-attention-rewrite", "version_id": "9c3a1f..." }
  ],
  "count": 1
}

POST /v1/repos/:slug/wiki/sandboxes/:name/promote

{ "name": "draft-attention-rewrite", "version_id": "a1b2c3..." }

DELETE /v1/repos/:slug/wiki/sandboxes/:name

{ "ok": true }

await cg.commits.create("my-research", {
  branch: "main",
  message: "ingest: Attention Is All You Need",
  author: { name: "wiki-agent", email: "agent@example.com" },
  changes: [
    {
      path: "wiki/transformers.md",
      content: `---
title: "Transformer Architecture"
summary: "The dominant architecture for sequence modeling since 2017"
tags: [deep-learning]
type: concept
sources: [raw/attention-paper.md]
updated: 2026-04-10
---

## Truth

A transformer is...

## Timeline

- **2026-04-10 (ingest)**: created from raw/attention-paper.md.
`,
    },
  ],
});