Engraph

engraph — Vault Intelligence for AI Agents

Turn your Obsidian vault into a knowledge API. 5-lane hybrid search, MCP server, HTTP REST API, ChatGPT Actions — all local, all offline.

[](https://github.com/devwhodevs/engraph/actions/workflows/ci.yml) [](LICENSE) [](https://github.com/devwhodevs/engraph/releases)

engraph turns your markdown vault into a searchable knowledge graph that any AI agent can query — Claude Code via MCP, ChatGPT via Actions, or any tool via REST API. It combines semantic embeddings, full-text search, wikilink graph traversal, temporal awareness, and LLM-powered reranking into a single local binary. Same model stack as qmd. No API keys, no cloud — everything runs on your machine.

Why engraph?

Plain vector search treats your notes as isolated documents. But knowledge isn't flat — your notes link to each other, share tags, reference the same people and projects. engraph understands these connections.

• 5-lane hybrid search — semantic embeddings + BM25 full-text + graph expansion + cross-encoder reranking + temporal scoring, fused via Reciprocal Rank Fusion. An LLM orchestrator classifies queries and adapts lane weights per intent. Time-aware queries like "what happened last week" or "March 2026 notes" activate the temporal lane automatically.
• MCP server for AI agents — engraph serve exposes 25 tools (search, read, section-level editing, frontmatter mutations, vault health, context bundles, note creation, PARA migration, identity) that Claude, Cursor, or any MCP client can call directly.
• HTTP REST API — engraph serve --http adds an axum-based HTTP server alongside MCP with 26 REST endpoints, API key authentication, rate limiting, and CORS. Web-based agents and scripts can query your vault with simple curl calls.
• Section-level editing — AI agents can read, replace, prepend, or append to specific sections by heading. Full note rewriting with frontmatter preservation. Granular frontmatter mutations (set/remove fields, add/remove tags and aliases).
• Vault health diagnostics — detect orphan notes, broken wikilinks, stale content, and tag hygiene issues. Available as MCP tool and CLI command.
• Obsidian CLI integration — auto-detects running Obsidian and delegates compatible operations. Circuit breaker (Closed/Degraded/Open) ensures graceful fallback.
• Real-time sync — file watcher keeps the index fresh as you edit in Obsidian. No manual re-indexing needed.
• Smart write pipeline — AI agents can create, edit, rewrite, and delete notes with automatic tag resolution, wikilink discovery, and folder placement based on semantic similarity.
• Fully local — llama.cpp inference with GGUF models (~300MB mandatory, ~1.3GB optional for intelligence). Metal GPU-accelerated on macOS (88 files indexed in 70s). No API keys, no cloud.

What problem it solves

You have hundreds of markdown notes. You want your AI coding assistant to understand what you've written — not just search keywords, but follow the connections between notes, understand context, and write new notes that fit your vault's structure.

Existing options are either cloud-dependent (Notion AI, Mem), limited to keyword search (Obsidian's built-in), or require you to copy-paste context manually. engraph gives AI agents direct, structured access to your entire vault through a standard protocol.

How it works

Your vault (markdown files)
        │
        ▼
┌─────────────────────────────────────────────┐
│              engraph index                   │
│                                             │
│  Walk → Chunk → Embed (llama.cpp) → Store   │
│                                             │
│  SQLite: files, chunks, FTS5, vectors,      │
│          edges, centroids, tags, LLM cache  │
└─────────────────────────────────────────────┘
        │
        ▼
┌─────────────────────────────────────────────┐
│              engraph serve                   │
│                                             │
│  MCP Server (stdio) + File Watcher          │
│  + HTTP REST API (--http, optional)         │
│                                             │
│  Search: Orchestrator → 4-lane retrieval    │
│          → Reranker → Two-pass RRF fusion   │
│                                             │
│  25 MCP tools + 26 REST endpoints           │
└─────────────────────────────────────────────┘
        │
        ▼
  Claude / Cursor / any MCP client / curl / web agents

1. Index — walks your vault, chunks markdown by headings, embeds with a local GGUF model via llama.cpp (Metal GPU on macOS), stores everything in SQLite with FTS5 + sqlite-vec + a wikilink graph
2. Search — an orchestrator classifies the query and sets lane weights, then runs up to five lanes (semantic KNN, BM25 keyword, graph expansion, cross-encoder reranking, temporal scoring), fused via RRF
3. Serve — starts an MCP server that AI agents connect to, with a file watcher that re-indexes changes in real time

Quick start

Install:

# Homebrew (macOS)
brew install devwhodevs/tap/engraph

# Pre-built binaries (macOS arm64, Linux x86_64)
# → https://github.com/devwhodevs/engraph/releases

# From source (requires CMake for llama.cpp)
cargo install --git https://github.com/devwhodevs/engraph

Index your vault:

engraph index ~/path/to/vault
# Downloads embedding model on first run (~300MB)
# Incremental — only re-embeds changed files on subsequent runs

Search:

engraph search "how does the auth system work"

 1. [97%] 02-Areas/Development/Auth-Architecture.md > # Auth Architecture  #6e1b70
    OAuth 2.0 with PKCE for all client types. Session tokens stored in HTTP-only cookies...

 2. [95%] 01-Projects/API-Design.md > # API Design  #e3e350
    All endpoints require Bearer token authentication. Tokens are issued by the OAuth 2.0...

 3. [91%] 03-Resources/People/Sarah-Chen.md > # Sarah Chen  #4adb39
    Senior Backend Engineer. Tech lead for authentication and security systems...

Note how result #3 was found via graph expansion — Sarah's note doesn't mention "auth system" directly, but she's linked from the auth architecture doc via [[Sarah Chen]].

Claude Code — Install the plugin (recommended):

claude plugin marketplace add devwhodevs/engraph
claude plugin install engraph@engraph

Connect to Claude Code:

Or configure MCP manually in ~/.claude/settings.json:

{
  "mcpServers": {
    "engraph": {
      "command": "engraph",
      "args": ["serve"]
    }
  }
}

Now Claude can search your vault, read notes, build context bundles, and create new notes — all through structured tool calls.

AI Agent Skills — Install the Engraph skills using the skills CLI (recommended):

npx skills add devwhodevs/engraph

Enable HTTP REST API:

# Start MCP + HTTP server on port 3000
engraph serve --http

# Custom port and host
engraph serve --http --port 8080 --host 0.0.0.0

# Local development without API keys (127.0.0.1 only)
engraph serve --http --no-auth

API key management:

# Add a new API key (read or write permission)
engraph configure --add-api-key

# List existing keys
engraph configure --list-api-keys

# Revoke a key
engraph configure --revoke-api-key eg_abc123...

Enable intelligence (optional, ~1.3GB download):

engraph configure --enable-intelligence
# Downloads Qwen3-0.6B (orchestrator) + Qwen3-Reranker (cross-encoder)
# Adds LLM query expansion + 4th reranker lane to search

Example usage

4-lane search with intent classification:

engraph search "how does authentication work" --explain

 1. [97%] 01-Projects/API-Design.md > # API Design  #e3e350
    All endpoints require Bearer token authentication...

Intent: Conceptual

--- Explain ---
01-Projects/API-Design.md
  RRF: 0.0387
    semantic: rank #2, raw 0.38, +0.0194
    rerank: rank #2, raw 0.01, +0.0194
02-Areas/Development/Auth-Architecture.md
  RRF: 0.0384
    semantic: rank #1, raw 0.51, +0.0197
    rerank: rank #4, raw 0.00, +0.0187

The orchestrator classified the query as Conceptual (boosting semantic lane weight). The reranker scored each result for relevance as the 4th RRF lane.

Rich context for AI agents:

engraph context topic "authentication" --budget 8000

Returns a token-budgeted context bundle: relevant notes, connected people, related projects — ready to paste into a prompt or serve via MCP.

Person context:

engraph context who "Sarah Chen"

Returns Sarah's note, all mentions across the vault, connected notes via wikilinks, and recent activity.

Vault structure overview:

engraph context vault-map

Returns folder counts, top tags, recent files — gives an AI agent orientation before it starts searching.

Create a note via the write pipeline:

engraph write create --content "# Meeting Notes\n\nDiscussed auth timeline with Sarah." --tags meeting,auth

engraph resolves tags against the registry (fuzzy matching), discovers potential wikilinks ([[Sarah Chen]]), suggests the best folder based on semantic similarity to existing notes, and writes atomically.

Edit a specific section:

engraph write edit --file "Meeting Notes" --heading "Action Items" --mode append --content "- [ ] Follow up with Sarah"

Targets the "Action Items" section by heading, appends content without touching the rest of the note.

Rewrite a note (preserves frontmatter):

engraph write rewrite --file "Meeting Notes" --content "# Meeting Notes\n\nRevised content here."

Replaces the entire body while keeping existing frontmatter (tags, dates, metadata) intact.

Edit frontmatter:

engraph write edit-frontmatter --file "Meeting Notes" --op add_tag --value "actionable"

Granular frontmatter mutations: set, remove, add_tag, remove_tag, add_alias, remove_alias.

Delete a note:

engraph write delete --file "Old Draft" --mode soft   # moves to archive
engraph write delete --file "Old Draft" --mode hard   # permanent removal

Check vault health:

engraph context health

Returns orphan notes (no links in or out), broken wikilinks, stale notes, and tag hygiene issues.

HTTP REST API

engraph serve --http adds a full REST API alongside the MCP server, exposing the same capabilities over HTTP for web agents, scripts, and integrations.

26 endpoints:

| Method | Endpoint | Permission | Description | |--------|----------|------------|-------------| | GET | /api/health-check | read | Server health check | | POST | /api/search | read | Hybrid search (semantic + FTS5 + graph + reranker + temporal) | | GET | /api/read/{file} | read | Read full note content + metadata | | GET | /api/read-section | read | Read a specific section by heading | | GET | /api/list | read | List notes with optional tag/folder/created_by filters | | GET | /api/vault-map | read | Vault structure overview (folders, tags, recent files) | | GET | /api/who/{name} | read | Person context bundle | | GET | /api/project/{name} | read | Project context bundle | | POST | /api/context | read | Rich topic context with token budget | | GET | /api/health | read | Vault health diagnostics | | POST | /api/create | write | Create a new note | | POST | /api/append | write | Append content to existing note | | POST | /api/edit | write | Section-level editing (replace/prepend/append) | | POST | /api/rewrite | write | Full note rewrite (preserves frontmatter) | | POST | /api/edit-frontmatter | write | Granular frontmatter mutations | | POST | /api/move | write | Move note to different folder | | POST | /api/archive | write | Soft-delete (archive) a note | | POST | /api/unarchive | write | Restore archived note | | POST | /api/update-metadata | write | Update note metadata | | POST | /api/delete | write | Delete note (soft or hard) | | GET | /api/identity | read | User identity (L0) and current context (L1) | | POST | /api/setup | write | First-time onboarding setup (detect/apply modes) | | POST | /api/reindex-file | write | Re-index a single file after external edits | | POST | /api/migrate/preview | write | Preview PARA migration (classify + suggest moves) | | POST | /api/migrate/apply | write | Apply PARA migration (move files) | | POST | /api/migrate/undo | write | Undo last PARA migration |

Authentication:

All requests require an API key via the Authorization header:

curl -H "Authorization: Bearer eg_abc123..." http://localhost:3000/api/vault-map

Keys have either read or write permission. Write keys can access all endpoints; read keys are restricted to read-only endpoints. Use --no-auth for local development without keys (127.0.0.1 only).

curl examples:

# Search
curl -X POST http://localhost:3000/api/search \
  -H "Authorization: Bearer eg_..." \
  -H "Content-Type: application/json" \
  -d '{"query": "authentication architecture", "top_n": 5}'

# Read a note
curl http://localhost:3000/api/read/01-Projects/API-Design.md \
  -H "Authorization: Bearer eg_..."

# Create a note
curl -X POST http://localhost:3000/api/create \
  -H "Authorization: Bearer eg_..." \
  -H "Content-Type: application/json" \
  -d '{"content": "# Meeting Notes\n\nDiscussed auth timeline.", "tags": ["meeting", "auth"]}'

Rate limiting: Configurable per-key token bucket (requests per minute). Defaults to 60 req/min. Returns 429 Too Many Requests when exceeded.

CORS: Configurable allowed origins in config.toml under [http]. Defaults to allow all origins for local development.

[http]
port = 3000
host = "127.0.0.1"
cors_origins = ["http://localhost:3000", "https://myapp.example.com"]
rate_limit = 60

[[http.api_keys]]
key = "eg_..."
permission = "write"

PARA Migration

engraph migrate para restructures your vault into the PARA method (Projects, Areas, Resources, Archive) using heuristic classification. The workflow is non-destructive: preview first, review the plan, then apply.

Workflow:

# 1. Preview — classify notes and generate a migration plan
engraph migrate para --preview
# Outputs: markdown summary + JSON plan saved to ~/.engraph/

# 2. Review the plan (edit if needed)
cat ~/.engraph/migration_preview.md

# 3. Apply — move files according to the plan
engraph migrate para --apply

# 4. Undo — reverse the last migration if something looks wrong
engraph migrate para --undo

Classification signals:

| Category | Detection signals | |----------|-------------------| | Projects | Open tasks (- [ ]), active/in-progress status in frontmatter, project tags | | Areas | Recurring topic keywords (health, finance, career, learning), area-related tags | | Resources | People notes (People folder, person-like content), reference material, articles, code snippets | | Archive | Done/completed/inactive status, no incoming or outgoing wikilinks, stale content |

Notes that don't match any signal with sufficient confidence stay in place. Daily notes (YYYY-MM-DD.md) and templates are always skipped.

MCP tools: migrate_preview, migrate_apply, migrate_undo — available in engraph serve for AI-assisted migration.

HTTP endpoints: POST /api/migrate/preview, /api/migrate/apply, /api/migrate/undo — available via engraph serve --http.

ChatGPT Actions

Connect your Obsidian vault to ChatGPT as a custom GPT Action. ChatGPT can search, read, create, and edit your notes through engraph's REST API.

Prerequisites

• engraph installed and indexed (engraph index ~/your-vault)
• A tunnel tool: [Cloudflare

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: devwhodevs
• Source: devwhodevs/engraph
• License: MIT

Install and usage instructions live in the source repository linked above.