All posts
Every piece, by year. Most recent first.
2026
10 pieces-
SuperServe, field-tested: what 356 live assertions reveal about an agent runtime
SuperServe's landing page makes four promises. We drove the live API 356 ways across 24 test phases — booting every template, running nine agent runtimes, executing a multi-agent swarm — to map the gap between the spec sheet and the substrate.
Jun 17- ai-agents
- sandbox
- firecracker
- microvm
- agent-infrastructure
- superserve
- agent-runtime
-
Vercel's eve and the agent-as-a-directory bet
Vercel open-sourced eve at Ship London — a framework where an agent is a folder of files. We built 75 agents on it and ran an adversarial review. Here's what holds up, what breaks, and the stateful-on-stateless tension the launch posts skip.
Jun 17- eve
- vercel
- agents
- typescript
- harness
-
44% of YC's Spring 2026 batch is the same company. That's the bet.
A founder analyzed all 196 YC Spring 2026 companies and found 86 are the same shape: AI-native B2B Agent-as-a-Service. That convergence is YC's 2024 vertical-agent thesis executed at scale — and a wager that speed beats defensibility.
Jun 16- y-combinator
- ai-agents
- agent-as-a-service
- vertical-ai
- ai-startups
- services-as-software
-
The stablecoin neobank stack is forkable, and most won't survive it
Strip the logos off the stablecoin neobank boom and most of the apps are the same six vendors in a trench coat. A teardown of 29 operators, the vendor cap table that captures the margin, the regulation that makes a charter a moat, and the three escape routes that are left.
Jun 15- stablecoins
- neobanks
- fintech
- crypto-cards
- payments
- distribution
-
Anthropic's kill switch and the software-export war America already lost
On June 12 a Commerce letter switched off two Anthropic models worldwide. Strip the news and a harder question remains: can you export-control software at all? America tried once before, on encryption, and lost in court. This control fails on the same three layers.
Jun 14- anthropic
- export-controls
- open-weights
- zhipu
- us-china
- ai-policy
-
Who owns the coding-agent runtime?
In 48 hours the question of where long-running coding agents actually run got both answers at once: an indie $7M bet against lock-in, and a frontier-lab acquisition that pulls the runtime layer inside Codex.
Jun 13- ai-agents
- agent-runtime
- sandboxes
- openai
- codex
- niteshift
- background-agents
-
The agent-memory funding wave hides four different bets
On one June Tuesday, money poured into startups all selling AI-agent 'memory.' The word covers at least four different technical products, and the frontier labs are absorbing the easiest of them as a free feature.
Jun 12- ai-agents
- agent-memory
- context-graphs
- continual-learning
- vector-databases
- openai
- anthropic
-
DeepSeek took outside money, and the cap table is the story
The lab that refused capital is closing a $7.4B first round at up to $59B. Why a battery maker leads it, why Tencent's check is defensive, and why Liang kept 40%.
Jun 11- deepseek
- china
- fundraising
- tencent
- catl
- open-weights
- liang-wenfeng
-
Stop fighting Codex CLI's approval prompts
The Codex CLI config that ends the permission nagging — config.toml profiles, sandbox and approval modes, AGENTS.md, reasoning effort, MCP servers, and the codex exec setup for CI.
Jun 10- codex
- openai
- coding-agents
- claude-code
- developer-workflow
-
The LLM router was three products wearing one name
Three different products spent two years fighting over the phrase 'LLM router.' Aggregation won at a $1.3B valuation, gateways became table stakes, and the most-hyped category — semantic cost-routing — quietly froze on GitHub.
Jun 9- llm-router
- ai-gateway
- openrouter
- inference
- infrastructure