bediashpreet

6 bulan yang laludiscuss

After reading hundreds of papers on agentic memory and trying out every possible tool, I came to the simple conclusion that maybe we're looking at memory wrong.

Memory is just... learning. Learning about the user, the task at hand, learning insights and patterns, learning from decisions - good and bad, the feedback received. Learning from every interaction. Everything else is integration (how the agent uses these learnings) and curation (decay, pruning, deduplication).

So I built Learning Machines: A system that helps agents continuously learn from every interaction.

I started working on it dec 31, and got a basic working version yesterday. Here's the PR for those interested: [learning-machine-v0](https://github.com/agno-agi/agno/pull/5897)

This post digs into the technical details.

bediashpreet

9 bulan yang laludiscuss

WTF are Agents?

> Are they workflows or are they graphs? > Are they LLMs in a loop or expensive while loops? > Are they deterministic, autonomous, or confused?

Let's cut through the noise and understand how they work.

bediashpreet

Submissions

[untitled]

[untitled]

[untitled]

[untitled]

GPU Poor Continuous Learning: Making Agents Smarter Without Fine-Tuning

Build a Self Learning Research Agent That Tracks Consensus over Time

I built a self-improving agent with dynamic context and continuous learning

Agent Security 101: stop sending your transactional data to telemetry services

Show HN: Agno – multi-agent framework, runtime and control plane

WTF Are Agents?

Agent Engineering 101: Software, systems, and security in practice

Andrej Karpathy said LLMs don't have "culture". So we gave them one

Becoming AI-first: Lessons from 100s of conversations on building AI products

Show HN: Agno – multi-agent framework, runtime and UI

comments