Tag
Warp introduces Warp Factories, an out-of-the-box system designed to simplify building and operating AI software factories by providing an infrastructure layer for deploying AI agents, targeting smaller companies.
Agent Substrate is a Google open-source runtime that enables high-density lifecycle management for large-scale AI agent deployments, multiplexing many stateful agents onto fewer physical workers via Kubernetes and microVM/gVisor sandboxes with sub-second suspend/resume.
Sapiom raises $35M Series A to reduce agent infrastructure costs, launching three products: a cost-aware model router, Agent Studio for building agents, and a runtime with typed step graphs and full traces.
Sapiom raises $35M Series A to build infrastructure for AI agents, focusing on cost management and launching three new products. The tweet highlights capabilities like multi-vendor API key management, per-agent cost tracking, and observability.
An announcement of Part I of the Ephemeral Sandbox book volume, covering concurrency ceilings and workspace contracts for parallel coding AI agents, with links to the English/Chinese chapters and supporting code.
The author suggests that agent infrastructure is evolving into a distinct field of study and practice within AI.
A structured visual reference that catalogs key components, frameworks, and tools for building AI agent infrastructure.
AWiki upgrades from a Skill to an open-source infrastructure product for AI agent connectivity, enabling internal and cross-domain collaboration with W3C DID-based identity, end-to-end encryption, and multiple integration methods.
The author argues that forward-thinking companies should invest in internal agent capabilities, and introduces Agent Vault, an open-source MCP gateway from Infisical that inventories and brokers access for internal agents. The post also highlights Sierra's internal AI tool Pinecone as a successful example.
Introspection, a new AI startup founded by ex-xAI engineers, introduces 'autoresearch' – a feedback loop system where agents maintain and improve themselves using signals, evals, and human input, moving beyond traditional agent harnesses.
This article recaps the AI agent landscape in 2026, highlighting local agents like OpenClaw and Hermes, self-improvement loops, VLA models for physical AI, and the growing importance of infrastructure for trusted agent systems.
Tidebase is an open-source tool that provides authentication, credential brokering, checkpoints, queues, schedules, and gates for AI agents, all backed by Postgres.
The traditional affiliate network model is ill-suited for AI agents, which operate through conversations, real-time recommendations, and multi-step workflows. A new infrastructure is needed, akin to a protocol layer for agent-driven business recommendations.
The author speculates on whether cloud GPU providers will become the underlying infrastructure for AI agents, drawing parallels to the telecom industry's evolution and questioning market consolidation.
This article discusses the key requirements for AI agents to successfully complete real-world tasks: a real phone number, email address, and payment method, highlighting products like AgentLine, Agent Mail, and Agent Card that provide these capabilities.
Anthropic introduces Claude Managed Agents, a set of composable APIs for building and deploying production-grade agents, addressing infrastructure challenges that separate prototypes from production.
Discusses the importance of proper audit logging for AI agents, emphasizing the need for append-only, hash-chained logs that prevent tampering, rather than storing logs in the same writable application database.
ActiveGraph is an open-source infrastructure for long-running agents, using an event-sourced reactive graph for auditable, forkable, and replayable agent state. It introduces a new architectural layer for agent coordination and state management.
The author describes rewriting their AI agent infrastructure for reliability using DBOS durable execution after facing cascading failures, and asks the community about similar experiences, tool choices, and build-vs-buy decisions.
Aditya Gupta highlights his reasons for joining YC, while Y Combinator announces its internal agent infrastructure with over 350 tools and self-improving skill loops, as discussed on the Lightcone Podcast.