Agent Integration R&D

Role
Design & build
Type
Prototypes, NDA
Focus
Agents & integrations

A set of prototypes connecting LLM agents to tools, data and messaging channels. Under NDA, so this covers the architecture only.

Architecture

Agent memory over MCP
An MCP server and HTTP wrapper expose a Redis store to agents through a strict JSON contract.
Messaging webhooks
Webhook endpoints validate signatures and keep one conversation session per sender.
Concurrent scraping pipeline
Pluggable scrapers, one class per source, run concurrently with a cap, retries and exponential back-off.
Streaming clients
Real-time Server-Sent Events clients for voice-agent sessions.
Backend proxy for agent flows
Front ends talk to hosted agent flows through a backend proxy, never directly.
LLM tracing
Self-hosted tracing for model calls.

Main processing path

  1. channel webhooksignature check
  2. backend proxysession per sender
  3. agent flowLLM
  4. toolsMCP, data APIs
  5. replysame channel

Simplified, with generic component names. Highlighted steps use a model; the rest is software.

Stack

  • TypeScript
  • Node.js
  • Python
  • Express
  • FastAPI
  • Redis
  • MCP
  • Playwright
  • Docker