Wyrm Docs
Everything you need to install, configure, and use Wyrm — persistent memory for AI agents.
Install Wyrm
$ npm install -g wyrm-mcp$ npx wyrm-mcp$ git clone https://github.com/ghosts-lk/Wyrm.git $ cd Wyrm $ npm install $ npm run build
Configure Your AI Client
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"wyrm": {
"command": "wyrm-mcp"
}
}
}GitHub Copilot (VS Code)
Add to your VS Code settings.json:
{
"github.copilot.chat.mcpServers": {
"wyrm": {
"command": "wyrm-mcp"
}
}
}Cursor
Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"wyrm": {
"command": "wyrm-mcp"
}
}
}Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"wyrm": {
"command": "wyrm-mcp"
}
}
}All 31 MCP Tools
Organized by category. Every tool is available in the Free tier.
Project
4 toolswyrm_create_projectCreate a new project with name, description, and tech stackwyrm_list_projectsList all projects with optional status filterwyrm_get_projectGet full project details by IDwyrm_update_projectUpdate project metadata, status, or tech stackSession
5 toolswyrm_create_sessionStart a new session linked to a projectwyrm_list_sessionsList sessions for a project with date range filterswyrm_get_sessionGet session details including summary and decisionswyrm_update_sessionUpdate session summary, status, or metadatawyrm_end_sessionEnd a session with final summary and outcomesQuest
4 toolswyrm_create_questCreate a task with priority, tags, and dependencieswyrm_list_questsList quests with status, priority, and tag filterswyrm_get_questGet quest details including progress and blockerswyrm_update_questUpdate quest status, priority, or assigneeContext & Skill
5 toolswyrm_save_contextSave a context entry (decision, preference, pattern)wyrm_list_contextsList context entries with category filterswyrm_save_skillStore a reusable skill or patternwyrm_list_skillsList all stored skills with optional category filterwyrm_get_skillGet full skill details and usage instructionsData Lake
5 toolswyrm_data_insertInsert structured data with category and tagswyrm_data_batch_insertBatch insert multiple data entries at oncewyrm_data_queryQuery data lake with filters, sorting, and paginationwyrm_data_updateUpdate existing data lake entrieswyrm_data_deleteDelete data lake entries by ID or filterSearch
3 toolswyrm_searchFull-text search across all data typeswyrm_search_contextSearch specifically within context entrieswyrm_search_sessionsSearch session summaries and contentStats & Usage
2 toolswyrm_usageGet token usage, cost estimation, and cache hit rateswyrm_statsGet database statistics — projects, sessions, storage sizeSystem
3 toolswyrm_syncBi-directional sync with .wyrm/ markdown fileswyrm_exportExport all data as JSON for backup or migrationwyrm_healthHealth check — DB status, version, feature flagsEnvironment Variables
WYRM_DB_PATHDefault: ~/.wyrm/wyrm.dbPath to the SQLite database file
WYRM_ENCRYPTION_KEYDefault: (none)AES-256 encryption key for data at rest. Set to enable encryption.
WYRM_VECTOR_PROVIDERDefault: (none)Vector embedding provider for semantic search (optional). Supports 'openai' or 'local'.
WYRM_LOG_LEVELDefault: infoLogging verbosity: debug, info, warn, error
WYRM_CACHE_SIZEDefault: 500Maximum entries in the in-memory read cache
WYRM_DB_PATH=~/.wyrm/wyrm.db \ WYRM_ENCRYPTION_KEY=your-32-byte-hex-key \ WYRM_LOG_LEVEL=debug \ wyrm-mcp
How Wyrm Works
Wyrm is built as a Model Context Protocol (MCP) server that any compatible AI client can connect to. It uses a local SQLite database as its storage engine, enhanced with FTS5 for full-text search.
┌─────────────────────────┐
│ AI Client (Claude, │
│ Copilot, Cursor, etc) │
└───────────┬─────────────┘
│ MCP Protocol
┌───────────▼─────────────┐
│ Wyrm MCP Server │
│ ┌───────────────────┐ │
│ │ MemCache Layer │ │
│ │ (sub-ms reads) │ │
│ └─────────┬─────────┘ │
│ ┌─────────▼─────────┐ │
│ │ Encryption Layer │ │
│ │ (AES-256-GCM) │ │
│ └─────────┬─────────┘ │
│ ┌─────────▼─────────┐ │
│ │ SQLite + FTS5 │ │
│ │ (WAL mode) │ │
│ └───────────────────┘ │
└─────────────────────────┘Frequently Asked Questions
Is Wyrm free?
Yes. Wyrm is free and open source under the MIT license. The core MCP server with all 31 tools, full-text search, and local storage is completely free.
Where is my data stored?
Locally in a SQLite database file on your machine (default: ~/.wyrm/wyrm.db). Your data never leaves your computer unless you enable cloud sync (coming in Pro).
Is it secure?
Yes. Wyrm includes optional AES-256-GCM encryption for data at rest, input sanitization on all tool inputs, path validation to prevent directory traversal, and parameterized queries to prevent SQL injection.
Which AI clients work with Wyrm?
Any MCP-compatible client: Claude Desktop, GitHub Copilot (VS Code), Cursor, Windsurf, Continue, and any other tool that supports the Model Context Protocol.
Will it slow down my AI?
No. Wyrm uses SQLite WAL mode for concurrent access and an in-memory cache layer that returns cached reads in under 1ms. Write operations are typically under 5ms.
Can I use it with multiple projects?
Yes. Wyrm supports unlimited projects, each with their own sessions, quests, and context. Switch between projects seamlessly.