openhands

OpenHands announces weekly updates, including Kimi K3 as the new free default model and enhancements to Automations, conversation context, first-run guidance, LLM provider credentials, and Jira Cloud setup.

A developer shares how moving a workflow to OpenHands cut their Opus 5 bill from $200 to $20 per month, arguing that agents matter more than frontier models.

OpenHands shares a blog post arguing dev tools must be open source, highlighting the concept of 'long-running forks' where agents nightly merge upstream changes, and demonstrates using OpenHands Agent Canvas automations for this.

OpenHands and Gray Swan are hosting an event to discuss AI agent security risks, including prompt injection and agent-specific threats, and how to build secure agents.

OpenHands Enterprise now integrates with Azure DevOps, enabling users to comment on work items or PRs and have OpenHands automatically perform the work and open a pull request in Azure Repos.

Graham Neubig shares a sidekick architecture for reducing LLM costs by delegating simple tasks to a smaller agent, with a 200-line example using the OpenHands SDK. This approach is also used in Cognition's Devin Fusion hybrid-model harness.

Blog post by Xingyao Wang explaining why OpenHands V1 chose a different architecture from Claude Managed Agents, arguing that reliability comes from implementation details rather than topology.

Hermes Agent now supports orchestrating OpenHands agents via a new optional skill, joining existing built-in skills for Claude Code, Codex, OpenCode, and Hermes itself.

OpenHandsDev launched the Agent Control Plane, a system for controlling, observing, and scaling hundreds of AI agents across an organization.