Agentlas-OS
This project implements agent routing: an agent is defined as a package of memory, skills, and its own scripting tools. As personal agent collections grow to dozens or hundreds, it automatically selects and invokes only the agents that match the current task instead of including all of them in the system prompt.
What it addresses
Agents accumulate over time until there are dozens or hundreds, and it is a waste to include all of them in the system prompt.
Shared over time
Each entry reflects what was shared on that date. Details may have changed since then.
Agentlas-OS
This project implements agent routing: an agent is defined as a package of memory, skills, and its own scripting tools. As personal agent collections grow to dozens or hundreds, it automatically selects and invokes only the agents that match the current task instead of including all of them in the system prompt.
Problem: Agents accumulate over time until there are dozens or hundreds, and it is a waste to include all of them in the system prompt.
Posted by @rator9521 · Original comment ↗
“I create agent routing. The key is how you define an agent. I define it as a package of memory, skills, and its own scripting tools. Within the deterministic code, it's not the agent that operates but the automation. Assigning responsibility and receiving probabilistic responses is the same as using LLM. However, as you go through life, agents gradually accumulate, eventually reaching dozens or hundreds. It's a waste to include all of this in the system prompt. With our self-developed routing flow, you can automatically select and use only the ones that perfectly match your task.”