SpellVault’s evolution: Beyond LLM apps, towards the agentic future

Summary

SpellVault began as Grab’s no-code platform for building LLM apps, using Retrieval-Augmented Generation (RAG) and plugins to connect applications with knowledge sources and external systems. Users could ground responses in Wikis, Google Docs, text, and PDFs, invoke custom HTTP endpoints, and access apps through the web, Slack, or APIs. The platform later added citations, Python execution for mathematical problems, scheduled actions, and drag-and-drop Workflows combining LLM calls, code, and Knowledge Vault lookups, while its executor moved toward graphs with nodes, edges, and states. SpellVault now exposes apps and RAG through MCP, allowing external agents and compatible clients to invoke apps and search, retrieve, or add Knowledge Vault information; TinyMCP adds MCP capabilities to FastAPI as a router.

Takeaways

1. 1

   SpellVault’s RAG integrations include Wikis, Google Docs, plain text, and PDF uploads, while plugins can retrieve runtime information from internal systems, external APIs, and custom HTTP endpoints.

2. 2

   Drag-and-drop Workflows combine LLM calls, Python code execution, and Knowledge Vault lookups in predefined, deterministic sequences.

3. 3

   Through MCP, SpellVault apps become callable tools for external agents and clients, while Knowledge Vaults support searching, retrieving, and adding information; TinyMCP provides FastAPI integration.