Commands and integrations
SourceVault's engine reaches your AI tools three ways: the Hermes plugin's slash commands, LLM-callable tools, and an MCP server any MCP client can attach to. All of it runs over localhost with signed requests.
Hermes slash commands
Deterministic commands that work reliably with any local model. Telegram uses underscore forms (/code_ask).
| Command | What it does |
|---|---|
/code-help | Command reference |
/code-status | Integration health check |
/code-repos | List indexed repos |
/code-sync <repo> | Fast-forward the repo mirror |
/code-read <repo> <path> | Read an exact file |
/code-search <repo> "query" | Hybrid semantic + literal search |
/code-context <repo> "query" | Retrieve a compact context pack |
/code-ask <repo> "question" | Retrieve and answer with citations |
/code-history <repo> "question" | Search indexed commit history (SourceVault v1.8+) |
Install and configuration for the plugin live in its repository: sourcevault-code-tools. For models that handle structured tool use, the plugin also registers code_search, code_read_file, and code_history tools.
MCP server
The MCP server exposes the same engine to OpenClaw and any other MCP client, which get bounded, cited context instead of re-reading files. The server is local-only. Paired with a local-model client the whole loop runs offline; a cloud-backed client sends what it retrieves to its own vendor, by your choice.
Machine API
For your own tooling, the HMAC-signed endpoints (/api/search-codebase, /api/read-file, /api/history-search) accept signed JSON over localhost. The OpenAPI description ships with every install at /docs on your own server.