Kubernetes as the Agent Control Plane in 2026: Agent Sandbox Hit v1.0, 300 Claims a Second, and DRA in Every Supported Release
What shipped for running AI agents on Kubernetes by October 2026: the kubernetes-sigs Agent Sandbox project from a KubeCon preview in November 2025 to v1.0.0 in August, its four CRDs and gVisor, Kata and Firecracker runtime classes, Google's 300 claims per second and 16x growth figures, a density benchmark of 61 Kata agents versus 88, 133 and 274 per node, DRA going GA in 1.34 and locked on through 1.37, kagent, Dapr Agents 1.0, agentgateway, the Inference Extension's move into llm-d, the CNCF survey's 66 percent, and the Gartner 80 percent platform-team prediction nobody has measured.
13 minOct 5, 2026MCP in 2026: 475M SDK Downloads a Month, 39,492 Servers in a Registry Still in Preview, and 12 Gateways Selling the Same 3 Features
The MCP ecosystem ten months after the Linux Foundation took it over, measured from primary sources: 475 million SDK downloads a month across npm and PyPI, three spec revisions ending in the stateless 2026-07-28 rewrite, an official registry I paged to 39,492 servers (24,242 remote) that is still labelled preview while Glama lists 96,340, every major client with different controls, twelve gateways from $0 to $0.005 per thousand calls, the tool-overload numbers (55k tokens before the first prompt, 85 percent recoverable), and a stateless Python server on mcp 2.3.0 that I ran and tested.
14 minOct 5, 2026Infrastructure as Code in 2026: Two Forks at 1.16 and 1.13, a $6.4B Owner, 912 Public State Files, and One Agent That Ran terraform destroy
Infrastructure as code three years after the BSL relicence: Terraform 1.16.5 under IBM versus OpenTofu 1.13.1 under the Linux Foundation and who shipped what first, HCP Terraform at $0.10 to $0.99 per resource with the legacy free plan gone, CDKTF and System Initiative archived, Pulumi 3.267 and Crossplane 2.4, a Terraform MCP server that grew from registry lookups to workspace administration in 15 months, 44 percent running AI for infrastructure but 34 percent trusting it, 912 exposed state files with 41 live AWS keys, and the agent that ran terraform destroy on 2.5 years of production.
13 minOct 5, 2026GPU Clouds in 2026: H100s at $2.59 an Hour, $104B of CoreWeave Backlog on $35B of Debt, and a Six-Year Bet on Silicon
The GPU rental economy from filings and price pages fetched on 5 October 2026: H100 hours that fell from about $8 in 2023 to a $1.70 trough in October 2025 and recovered to $2.59 on the transacted index while list prices rose 25 percent; CoreWeave's $2.58B quarter, $103.7B backlog, $35.1B of debt from 15 percent DDTLs to a 5.9 percent A3 facility, and Microsoft at 67 percent of 2025 revenue; Nebius, Lambda, Crusoe, Oracle's $664B RPO and NVIDIA's $105B of guarantees; who books servers over 5, 5.5 or 6 years and what Burry's $176B means; and an own-versus-rent break-even calculator.
13 minOct 5, 2026Agent Memory in 2026: Vendors Claim 92.5 on LoCoMo, a Plain Filesystem Scored 74, and Every Memory Product Lost to BM25
Agent memory systems in 2026, kept honest: Mem0's 66.9 on LoCoMo in its own paper versus 92.5 on its managed platform a year later, Zep's 75.1 rebuttal and the three bugs behind Mem0's 66.0 for Zep, Letta's 74.0 with only a filesystem, MemoryAgentBench putting every commercial system under 45 on retrieval against BM25 at 60.5, Hindsight's 89.6, first-party memory from ChatGPT, Claude and Gemini with dates, both labs' compaction APIs, what re-reading 115k tokens costs at cache-read prices, a Postgres and pgvector layer with supersession, and why memory poisoning is still unfixed.
13 minSep 9, 2026AI Power in 2026: 485 TWh, a 0.3 GW Stargate, a 116 GW Turbine Backlog, and 1,800 MW That Dropped Off the Grid in Seconds
The electricity numbers behind AI, kept honest: IEA's 485 TWh for 2025 and 950 by 2030, LBNL's 4.7 percent of US power heading to 12, what a prompt actually costs (0.24 Wh at Google, 30 times more in reasoning mode), which gigawatt campuses are energised versus announced (Stargate Abilene at 0.3 of 1.2 GW), where the power comes from (a 116 GW gas-turbine backlog with 2031 slots, nuclear restarts in 2027, one SMR construction permit), what the grid operators are doing about 233 GW queues and 1,800 MW load-loss events, rack power from 132 kW to 600 kW, and a script to measure your own job's energy.
14 minSep 7, 2026Stablecoins in 2026: $300B in Supply, 1% Real Payments, and Rails Being Rebuilt for Agents
GENIUS Act rules are still proposals, Visa settles $7B a year in USDC, Stripe launched its own chain, and x402 has 165 million transactions worth about $50 million. An infrastructure engineer separates the settlement layer that is real from the agent-payments layer that is mostly still a demo.
16 minSep 6, 2026Seats Are Dying. What the 2026 SaaS Repricing Looks Like From the Compute Layer
A one-day 18% drop in Thomson Reuters, $1.50 per resolution at Zendesk, $15 per human at Microsoft, and a vibe-coding company at $500M run-rate with 200 people. The unit of software changed this year. Here is what it did to infrastructure.
13 minSep 3, 2026Top AI Agent Sandbox Providers: An Engineer's 2026 Roundup
A working engineer's roundup of the top AI agent sandbox providers: isolation, hosting, persistence and pricing compared — including the one I built myself.
10 minSep 2, 2026It's 2 AM. Do You Know What Your AI Agent Is Doing?
I run the microVMs that other people's AI agents execute in. At 2 AM almost all of them are idle — and the things burning money are the robots watching them.
11 minSep 2, 2026Sandbox Creation Time Benchmarks Measure Different Things
Every AI sandbox matrix has a creation time column spanning 0.79ms to 2.7s. That spread is definitional, not performance. Here's how to make it comparable.
10 minSep 2, 2026microVM Production Incidents: 4 Postmortems From My Fleet
Four real postmortems from a multi-tenant Firecracker microVM fleet I run solo: a wiped boot disk, silent config drift, a fatal page fault, and no alerts.
10 minSep 2, 2026Firecracker microVM Cloud, Built Solo in 6 Months: 179ms Boots
What it actually takes to run a Firecracker microVM cloud alone: snapshot-restore on every create, 179ms boots, pre-allocated netns, and the real costs.
9 minSep 2, 2026I Measured Every Stage of My 179ms Firecracker Boot Path
Where every millisecond of a Firecracker create goes, measured on my own production fleet, plus why I refuse to stop the clock before the guest answers.
9 minSep 2, 2026My Fork Docs Were Wrong: What VM Forking Really Preserves
I shipped a doc claiming forks keep processes and open files. A smoke test proved otherwise. Three fork paths measured, and the five places each breaks.
10 min