"How Do You Fix 70% Data Loss Across 1 Million Concurrent Connections?" - this is a question a Production @AkkaDotNET Support customer asked us earlier this year. We solved it.
Here's how we did it:
Connecting an MCP server is only useful if your agent knows what to do with it.
Netclaw 0.26.0 lets MCP servers provide their own prompts as skills. Less translation. Better execution.
What's new:
netclaw.dev/changelog/0.26…
Quick start:
netclaw.dev/getting-starte…
Your agent should do the job - not wander around the environment trying to figure out how.
Netclaw 0.26.0 makes fewer wasted moves and gets to useful work faster.
What's new:
netclaw.dev/changelog/0.26…
Quick start:
netclaw.dev/getting-starte…
Akka .NET 1.5.71 is out.
This maintenance release includes targeted fixes for Cluster Sharding recovery, remoting, TestKit / multi-node testing, and ClusterClientDiscovery.
If you’re running any of those components, review the notes and plan the upgrade:
github.com/akkadotnet/akk…
Netclaw 0.26.0 is out.
Your agent should do the job - not burn tool calls, fight flaky integrations, or trip over the host OS.
55 PRs focused on getting out of the way: fewer wasted moves, better MCP, server prompts as skills, and native PowerShell on Windows.
What's new: