In this post, I’ll walk you through how I built a fully autonomous, multi-agent crypto trading team. This system uses a local LLM (via Ollama) for its reasoning, fetches real-time 

Developer Relations Lead @Gaia (gaianet.ai)

Judge & Mentor @ ETHDenver, Ex-Head of Platforms & Community @AngelHack.

Building a Multi-Agent Crypto Trading Bot with Local LLMs, Recall, and Agno

In the world of Large Language Models (LLMs), amnesia is the default. When you interact with an API, it knows nothing about you, your past projects, or the specific "truths" of you

A Deep Dive with Gaia Nodes and Supermemory

Building Stateful vs. Stateless AI Agents

Have you ever asked ChatGPT to write a report, read the output, and thought, "Eh, that's kind of generic"?We've all been there. The standard "one-shot" approach to AI - prompt in, 

Day 6 of 2026 Building!

Building Self-Refining AI Agents with Ollama & Langfuse

The Problem: Ephemeral AI OutputsEvery LLM call today produces a response that vanishes into chat history. You can't prove:Which agent identity generated itWhich model configuratio

A minimal end-to-end pattern for cryptographically attributable AI inference – no zkML, no TEEs, just signatures + datachain storage.

Verifiable AI in 69 Lines: Signed Inference on Gaia + Irys

youtube

github

devto

Platforms @AngelHack & Community Architect @TribeI write about dev communities, hackathons on tini.ltd/hk-blog

Harish Kotra

Developer Relations Lead @Gaia (gaianet.ai) Judge & Mentor @ ETHDenver, Ex-Head of Platforms & Community @AngelHack.