The new dashboard makes Agent work that needs your attention easier to find, with tasks awaiting decision and recent activity in one place. Project- and cluster-level links open Agent work in context, while Kubernetes fleet health now distinguishes current problems from retained warning history. Clearer Optimizer evidence helps you verify recommendations before approving changes.

Hyphen now makes Kubernetes optimization easier to automate, understand, and verify with workload-level Optimizer policies, clearer evidence and results, and more resilient deployment networking. Hyphen CLI v0.29.0 also adds safer environment key handling and links that take you directly to the correct deployment run.

Hyphen now speaks MCP. Connect Claude, Cursor, VS Code, or any MCP client to https://mcp.hyphen.ai/, sign in, and your assistant can manage your Hyphen organization directly — with the same permissions you have in the app.

This week's update makes it easier to troubleshoot Kubernetes workloads in Hyphen. Teams can connect runtime observability data like New Relic, jump directly to the resource they are investigating, see clearer warning context, and review more complete deployment run history after a deploy.

This week extends the Kubernetes management release with clearer inventory navigation, richer node and workload detail, and easier Agent task filtering. It also includes backend reliability work for deployment networking and policy resolution across target-scoped Agent tasks.

Kubernetes inventory views now make it easier to understand what changed in a cluster and where attention is needed:

Hyphen now gives teams a complete Kubernetes management loop: register clusters with your organization by installing Horizon, inspect inventory changes over time, prompt Agent for workload optimization recommendations, approve scale changes, and safely review automated or manually initiated cleanup of stale resources.

Hyphen organization policies can now control two additional recurring Agent tasks: Log Analysis and Optimizer. These new policy controls sit alongside stale feature flag cleanup, giving teams a more complete organization-level way to decide which recurring Agent work runs automatically and where it should apply.

Deployments now support object storage across cloud providers, Hyphen Agent can inspect and run project environment deployments from chat, and organizations can control stale feature flag cleanup with recurring Agent task policies.

Hyphen Agent can now answer organization activity questions directly from chat, remember durable member preferences, and show up in Slack with the same organization chat functionality available in the Hyphen App. Ask what happened to a project, who created a resource, what an actor changed, or what recent deployment activity looks like, and the agent will search Hyphen events and return a grounded answer with linked resources.

Hyphen Agent can now turn Log Analysis findings into code review. After Agent analyzes deployment logs and identifies an underlying issue, it can use a connected GitHub repository to open a pull request with a proposed fix. This release also adds project, short link, and QR code tools, safer structured action prompts, and live link updates in Hyphen.

You can now manage your organization's teams directly from the Hyphen chat interface, with real-time updates reflected everywhere instantly. Agent messages also now contain live links to every entity they reference, so navigating from chat to the work the agent created is easy.

Hyphen Agent can now analyze deployment logs or New Relic APM, surface issues, and link findings directly to GitHub. App detail pages have been rebuilt around environment and preview context.

Hyphen now tells you when your deployment settings have drifted from what's actually running, before you waste a run. The optimizer also gets smarter guardrails: it can now recommend scaling above your SLA floor and adjust your instance bucket, while still protecting you from going below it.

You can now keep ongoing conversations with the Hyphen Agent in dedicated chat sessions, give the Optimizer more application context from connected GitHub repositories, and fine tune deployments with more granular container resource controls.

This release also adds support for selecting the latest preview build when triggering preview deployment runs.

Project environments now have clearer roles and a simpler deployment model.

You can now assign a type to each project environment and map exactly one deployment policy to each environment. Deployment policies are now environment-specific, replacing the previous model where a single policy could target multiple environments.