RL environments are the playgrounds where agents learn. Until now, they’ve been fragmented, closed, and hard to share. We are launching the Environments Hub to change that: an open, community-powered platform that gives environments a true home.Environments define the world, rules and feedback loop of state, action and reward. From games to coding tasks to dialogue, they’re the contexts where AI learns, without them, RL is just an algorithm with nothing to act on.
Meet Foundry: An AI Startup that Builds, Evaluates, and Improves AI Agents
Training AI Agents with RL | Unsloth Documentation
Learn how to train AI agents for real-world tasks using Reinforcement Learning (RL).
Coasts — Containerized Hosts for AI Agents
Free, open source parallel runtimes for AI agents. Run multiple isolated environments on your machine — no cloud, no conflicts.
Project Think: building the next generation of AI agents on Cloudflare
Announcing a preview of the next edition of the Agents SDK — from lightweight primitives to a batteries-included platform for AI agents that think, act, and persist.
AGNTCY.org — Building the Internet of Agents (IoA)
AGNTCY delivers an open-source stack enabling AI agents to collaborate across vendors and frameworks through discovery, identity, messaging, and observability.
Prime Intellect - The Open Stack for Self-Improving Agents
The compute and infrastructure platform for you to train, evaluate, and deploy your own agentic models.
Prime Intellect - The Open Stack for Self-Improving Agents
The compute and infrastructure platform for you to train, evaluate, and deploy your own agentic models.
The Open-Source Toolkit for Building AI Agents v2
An opinionated, developer-first guide to building AI agents with real-world impact
AI agent runs amok in Fedora and elsewhere
Agentic AI systems can be used to do a variety of things autonomously on behalf of a human user [...]
OpenAI co-founds the Agentic AI Foundation under the Linux Foundation
OpenAI co-founds the Agentic AI Foundation under the Linux Foundation and donates AGENTS.md to support open, interoperable standards for safe agentic AI.
hyperspaceai/agi
The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and push breakthroughs here. Fully peer-to-peer. Join from your browser or CLI.
pguso/ai-agents-from-scratch
Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.
Discovery of a new OpenAI agent message board
A swarm of autonomous AI agents, self-identifying as OpenAI agents, used a small German volunteer wiki to save answers, coordinate live, and share sandbox bypasses. OpenAI noticed and said nothing.
Training Agentic Reasoners — Will Brown, Prime Intellect
ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
We introduce ARC-AGI-3, an interactive benchmark for studying agentic intelligence through novel, abstract, turn-based environments in which agents must explore, infer goals, build internal models of environment dynamics, and plan effective action sequences without explicit instructions. Like its predecessors ARC-AGI-1 and 2, ARC-AGI-3 focuses entirely on evaluating fluid adaptive efficiency on novel tasks, while avoiding language and external knowledge. ARC-AGI-3 environments only leverage Core Knowledge priors and are difficulty-calibrated via extensive testing with human test-takers. Our testing shows humans can solve 100% of the environments, in contrast to frontier AI systems which, as of March 2026, score below 1%. In this paper, we present the benchmark design, its efficiency-based scoring framework grounded in human action baselines, and the methodology used to construct, validate, and calibrate the environments.
