Evolving Agents Framework
Hey HN, I've been working on an open-source framework for creating AI agents that evolve, communicate, and collaborate to solve complex tasks. The Evolving Agents Framework allows agents to: Reuse, evolve, or create new agents dynamically based on semantic similarity Communicate and delegate tasks to other specialized agents Continuously improve by learning from past executions Define workflows in YAML, making it easy to orchestrate agent interactions Search for relevant tools and agents using OpenAI embeddings Support multiple AI frameworks (BeeAI, etc.) Current Status & Roadmap This is…
Evolving Agents Framework launched on March 9, 2025 with 139 votes, #310 of 7,215 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
The Evolving Agents Framework is an open-source tool for building AI agents that can dynamically create, evolve, and communicate with each other to solve complex problems. Agents reuse or create specialized versions based on semantic similarity, delegate tasks to one another, and improve through learning from past executions. Workflows are defined in YAML, and the framework supports multiple AI backends while using embeddings to discover relevant tools and agents. Currently in proof-of-concept stage, it is designed for developers building distributed multi-agent systems.
written from the facts on this page · September 2026
From the sources
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 guardrails. - EvolvingAgentsLabs/evolving-agents
ACTIVE again — 2026-09-06. This repository was frozen on 2026-08-01 and closed with a pointer to ai-os . ai-os has now come home: it is a subtree here, with its history intact, and this is where the organisation's active work lives. Nothing was rewritten to make the arrival look tidy. The 2025 toolkit stays in legacy/eat/ , the flat results stay in Evidence below, and two more have been added — because they point the same way as the first, which is the finding. A plugin for the Claude Agent SDK that versions an agent's evolution — diff it, merge it, refuse to ship it when the eval fails. The Agent SDK runs the loop, ships the tools, manages context, and enforces permissions. It also…from github.com
In the maker’s words, at launch
Hey HN, I've been working on an open-source framework for creating AI agents that evolve, communicate, and collaborate to solve complex tasks. The Evolving Agents Framework allows agents to: Reuse, evolve, or create new agents dynamically based on semantic similarity Communicate and delegate tasks to other…
Does a similar job
all alternatives →
Open AgentsApr 2026 · open-agents.dev · ▲161OpenAgents - The collaboration OS for AI agents. Contribute to openagents-org/openagents development by creating an account on GitHub.
ART – a new open-source RL framework for training agents2025 · github.com · ▲116Hey HN, I wanted to share a new project we've been working on for the last couple of months called ART (https://github.com/OpenPipe/ART). ART is a new open-source framework for training agents using reinforcement learning (RL). RL allows you to train an agent to perform better at any task whose outcome can be measured and quantified. There are many excellent projects focused on training LLMs with RL, such as GRPOTrainer (https://huggingface.co/docs/trl/main/en/grpo_trainer) and verl…
Adam – An embeddable cross-platform AI agent libraryMay 2026 · github.com · ▲24An embeddable cross-platform AI agent library written in C. Cloud and local LLMs, tool calling, long-term memory, voice, sessions, research mode, self-evolving loops. The SQLite of agent frameworks: small, portable, just works. - sqliteai/adam
Use functional tokens for AI agents to simplify app workflows2024 · nexa4ai.com · ▲80Hi HN! I want to share our latest project at NEXA AI. We developed AI agent foundation models designed to transform how developers create AI agent powered apps. One major challenge we've observed with current human-computer interactions is that many simple, one-step tasks become unnecessarily complex, multi-step workflows due to limitations of current GUIs. AI agents can solve this, but existing AI agent models are slow and costly. To tackle these issues, we built lightweight AI agent models based on our Octopus V2, small language models for function calling (You can learn more about our…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2025
the whole month →
Mimic Human Research & Save Findings in AI Knowledge Base
AI · 2025 · sider.ai
