531 posts tagged with "AI agents"
AI agents and autonomous systems
Block's Buzz Topped GitHub Trending: What a Nostr Hive-Mind Gets Right (and Skips) Versus an MCP Deploy Surface
Block's Buzz hit #1 on GitHub trending with a Nostr-based workspace where humans and agents share one room. Here is what its chat-first model solves for multi-agent coordination — and why a deploy-from-chat platform still needs a typed, scoped MCP tool surface for production changes.
Goose Under the Linux Foundation: The Neutral Reference Client for Deploy-from-Chat
Block donated its Goose agent to the Linux Foundation's Agentic AI Foundation, alongside MCP and AGENTS.md. Here is why a PaaS team should certify its deploy and rollback MCP tools against Goose instead of one vendor's CLI — with a versioned deploy recipe to prove it.
Your Deploy Runbook Should Be a Skill, Not a Wiki Page
Agent Skills turn deploy, rollback, and log-triage runbooks from wiki pages agents never read into versioned skill bundles every major harness loads on demand. Here is the conversion — and why enforcement still belongs in the governed tool layer.
The Agent-Sandbox Market Crystallized Into Three Architectures. Here's the Bar for Building Your Own.
E2B, Modal, and Daytona each lead a different sandbox architecture — Firecracker microVMs, gVisor, hardened containers. A workload-conditional verdict on which wins where, the four-boundary isolation bar none of them ships by default, and the honest starting point for sandboxes on owned hardware.
LangGraph Platform Is GA: Do Your Agents Need a Per-Node Runtime, or Just a Container?
LangGraph Platform's GA brings per-node agent billing to production. We work out the cost math at typical volumes, separate the free primitives from the metered ones, and give a rule for when to pay versus shipping a container.
llm-d Is Now a CNCF Sandbox Project: What Kubernetes-Native Distributed Inference Means for Self-Hosting Your AI Agents' Brains
llm-d brings distributed LLM inference — prefix-cache-aware routing and prefill/decode disaggregation — to Kubernetes as a CNCF Sandbox project. What it means for self-hosting AI-agent inference, what it costs versus hosted APIs, and how early the project still is.
The MCP Roadmap's Five Priorities, Ranked by What They Cost a Self-Hosted Team
The August 2026 MCP roadmap names five priorities for the next spec release. Here is what each one means for teams running their own MCP servers, ranked by urgency, with an adoption sequence for owned infrastructure.
Qovery Says the Hard Part of Agent Deploys Is Governance, Not Access — They're Right
Qovery's CEO says the hard part of letting AI agents deploy is governance, not access — RBAC, budget limits, and audit trails enforced server-side. Why that validates the self-hosted playbook, and why agent-run migration makes the destination's meter the only bill that matters.
Rubrik Gave AI Agents the Keys to the Recovery Vault: What a Backup Vendor's Governed MCP Server Teaches Infrastructure Tool Design
Rubrik's September 2026 MCP server gives customer AI agents governed access to backup and recovery state — RBAC parity, blast-radius-gated restores, and auditable tool calls. Here is the five-rule checklist its design implies for any infrastructure MCP surface.