Section

Demos

Working demos with full design documents: architecture, flows and run steps.

Demo · MCP

MCP Memory Demo: give any MCP client a long-term memory it can search by meaning

A local MCP server that lets Claude Desktop, Cursor or your own agent remember facts and recall them by meaning later. Each tool maps to a CoALA memory action.

By Nitin Goswami · Oct 26, 2026 · 9 min read

The demo teaches how an agent gets memory that outlives one conversation. The MCP server owns a long-term episodic memory: a Chroma collection of things the user said, each with a timestamp, tags and a source. The client's model writes to it with a learning action (remember) and reads from it with a retrieval action (recall). Recalled memories land in the model's working memory (the context window) as a tool result, …

Continue reading →

Demo · Voice AI

Voice Insight: turn call recordings into grounded, quote-checked insight

An open-source reference pipeline for speech-to-text followed by LLM inference, with every model claim checked against the transcript before it is shown. The worked example is call-centre quality review; each stage maps to the CoALA framework.

Next.js 16
AssemblyAI
zod
Tailwind CSS 4
Vitest

FollowsGrounded voice insight →CoALA →

▶ Try it live ↗

Oct 19, 2026 · 12 min read

Demo · RAG

RAG Demo: ask real-world documents, see the evidence

A minimal web app that shows semantic Retrieval-Augmented Generation end to end. Pick a knowledge base (HR policies, a lease, a router manual), ask a question, and see the passages, similarity scores and database rows behind every answer. Each stage maps to the CoALA framework.

FastAPI
LangChain
pgvector
Next.js

FollowsCoALA →

▶ Try it live ↗

Oct 17, 2026 · 9 min read