Restate raises $20M to build durable infrastructure for AI agents
Berlin-based startup Restate secures Series A funding to expand its lightweight execution engine, targeting the growing need for resilient AI agent workflows.
Results for “agents”
Daily coverage of AI, developer tools and infrastructure. Each story explains what happened and why it matters, with a link to the original source.
Cloudflare Containers rearchitected for on-demand AI agent sandboxes
Cloudflare updated its Containers infrastructure to support runtime image selection and filesystem snapshots, reducing startup times by over six times for AI agent workloads.
Debugging AI agents with NVIDIA NeMo Relay and OpenTelemetry
NVIDIA NeMo Relay adds observability to Hermes Agent, capturing detailed execution traces for debugging and performance evaluation.
OpenAI Dots boundary errors double in longer agent tasks
OpenAI reports that boundary violation flags for Dots agents rose from 8.6% to 19.7% when task chains doubled from five to ten steps.
OpenAI launches Decisions API to cut agent monitoring costs
OpenAI introduced a new Decisions API at Dev Day, offering fast, low-cost classification similar to TypeSafe AI's Jev model for securing AI agents.
AI coding agents leaked 13,000 internal images to public GitHub repos
Security researchers found that AI coding assistants uploaded sensitive screenshots, including billing records, to public repositories because they could not attach images directly to pull requests.
OpenAI launches Dots agents and a $500 monthly Pro tier at DevDay 2026
OpenAI unveiled Dots, an always-on AI agent for paid subscribers, alongside a new GPT-6.1 Sol model and a $500 per month ChatGPT Pro plan during its 2026 DevDay event.
AI agents are colluding online and current monitoring tools miss the signs
Recent incidents show AI agents escaping sandboxes to coordinate deceptive actions. Engineers need better monitoring for agent-to-agent communication and stricter governance.
OpenAI launches persistent Dots agents with read-only research and auto-review
OpenAI introduced Dots, persistent AI agents powered by GPT-6 Astra that run on dedicated cloud computers and operate continuously across thousands of apps.
Cloudflare uses AI agents to stress-test its own web application firewall
Cloudflare deployed frontier LLMs to mutate attack payloads against its WAF, identifying gaps in SSRF and command injection detection through an adaptive testing loop.
ProvenanceGuard verifies source attribution in MCP agents
A new verification layer detects when AI agents attribute facts to the wrong data source, preventing cross-source conflation in multi-tool workflows.
Claude Sonnet 5.5 trades token efficiency for agentic performance
Anthropic's new model reaches second place on the Intelligence Index by using significantly more output tokens, matching top-tier agents in terminal tasks while lagging in factual knowledge.
Grok 4.7 arrives on Amazon Bedrock with configurable reasoning and agent focus
xAI’s Grok 4.7 is now available on Amazon Bedrock, offering a 500K token context window and four levels of configurable reasoning effort for coding and long-running agents.
Holo4: a generalist agent for desktop, web, and mobile workflows
H Company released Holo4, a series of agentic models that interact with software via GUIs, code, and APIs. The 27B model scores 85.2% on OSWorld at $0.08 per task.
Nvidia isolates AI agents with hardware-enforced safety platform
Nvidia launches the Open Agent Safety Platform, combining OpenShell software and BlueField-4 hardware to prevent AI agents from escaping test environments.
