#agent-infrastructure
The latest AI and developer news about #agent-infrastructure, with the original source and a short summary.
The latest AI and developer news about #agent-infrastructure, with the original source and a short summary.
Berthd offers an open-source macOS client that runs Claude Code and Codex on remote dev boxes, allowing agents to continue working even when the local laptop is closed.
The platform processes approximately 1 trillion tokens daily internally and offers serverless and reserved capacity options.
LangChain announced the general availability of LangGraph Platform for deploying long-running and stateful agents.
AgentENV rapidly manages agent reinforcement learning environments using Firecracker-based sandboxes.
LangSmith has launched a managed execution environment for Deep Agents in public beta.
Introducing Phantom, an AI agent that builds its own infrastructure, learns, and evolves through a dedicated VM.
Running web agents at production scale requires five layers beyond the browser itself: warm pools, isolation, identity, observability, and a model gateway.
Mirage has been released, unifying S3, Drive, and Slack into a single file system.
InsForge, a backend platform that coding agents can manage directly, has been open-sourced
Cirrus Labs, a CI/CD and virtualization powerhouse, is joining OpenAI's Agent Infra side.