evolving-agents
evolving-agents copied to clipboard
matiasmolinas
Your toolkit for autonomous, evolving agent ecosystems. Create, execute, govern, and evolve agents that learn from experience, collaborate, build new capabilities, and operate safely within defined gu...
Hi everyone, First, thank you for the 445 stars on Evolving Agents Toolkit. It proved that we are all looking for the same thing: autonomous agents that can actually manage...
It seems like a common agent. Any doc describes the evolution part?
The Evolving Agents Toolkit (EAT) currently utilizes `beeai-framework==0.1.4`. This version is significantly outdated compared to the latest releases of the BeeAI framework (e.g., `v0.1.23` or newer). This migration aims to...
#### Problem/Motivation (Solution inspired on [langmem](https://github.com/langchain-ai/langmem) .. ) With the new `eat_semantic_memory` store in place, we need an automated process to populate it. The system currently learns from experiences in...
#### Problem/Motivation (Solution inspired on [langmem](https://github.com/langchain-ai/langmem) .. ) Currently, the EAT framework's "Smart Memory" is purely episodic. The `eat_agent_experiences` collection stores a raw, chronological log of everything an agent does....
#### Problem/Motivation (Solution inspired on [memvid](https://github.com/Olow304/memvid) .. ) The `eat_agent_experiences` collection is designed to grow indefinitely. Over time, this will lead to: 1. **Increased MongoDB Costs:** Storing millions of detailed...
`The OpenAI Agents SDK has introduced more sophisticated built-in support for human-in-the-loop (HITL) flows, primarily for seeking approval for sensitive tool executions. This includes mechanisms to pause agent runs, request...
The Evolving Agents Toolkit (EAT) aims to provide a framework for building AI agent systems that can autonomously evolve and improve themselves. The current "Smart Memory" version (EAT-SM) provides a...
**Problem** Currently, interacting with the `SystemAgent` and observing its complex orchestrations (including component evolution) is primarily done through logs and script outputs. A visual, interactive interface would significantly improve usability,...
The Evolving Agents Toolkit (EAT) currently supports component creation and evolution. To push its capabilities further towards genuine self-improvement and the discovery of novel, high-performing agents/tools, we can integrate principles...
Metadata
Owner
Metadata
Your toolkit for autonomous, evolving agent ecosystems. Create, execute, govern, and evolve agents that learn from experience, collaborate, build new capabilities, and operate safely within defined gu...