{"query":"agent","results":[{"slug":"microsoft-agent-framework-a2a-expose-consume-agent","title":"How to Let Your Agent Talk to Agents You Don't Own: A2A in Microsoft Agent Framework","dek":"Microsoft Agent Framework 1.0 ships native A2A support. Here's how to consume a remote agent in three lines — and expose yours so other people's agents can call it — with code.","section":"stack","snippet":"Most agent tutorials assume your agent owns every tool it calls. Real systems aren…","url":"/posts/microsoft-agent-framework-a2a-expose-consume-agent.html","markdown":"/posts/microsoft-agent-framework-a2a-expose-consume-agent.md"},{"slug":"bedrock-agentcore-vs-vertex-agent-engine-vs-foundry-hosted-agents","title":"Bedrock AgentCore vs Vertex Agent Engine vs Foundry Hosted Agents: The Managed Agent Runtime, Compared","dek":"All three hyperscalers now sell a managed home for your agent. Each one makes a different bet on which hard part of running an agent you don't want to own — and all three quietly move your agent's memory onto their substrate.","section":"wire","snippet":"You can now build an agent in any framework you like and still face…","url":"/posts/bedrock-agentcore-vs-vertex-agent-engine-vs-foundry-hosted-agents.html","markdown":"/posts/bedrock-agentcore-vs-vertex-agent-engine-vs-foundry-hosted-agents.md"},{"slug":"foundry-hosted-agents-ga-bring-your-own-harness-per-agent-identity","title":"Foundry Hosted Agents Hit GA: Bring Any Harness, Get a Per-Agent Identity, Pay by the vCPU-Hour","dek":"Microsoft made Foundry's hosted agents generally available — and the interesting part isn't the runtime. It's that the old 'which framework?' decision is finally decoupled from 'where does it run?', and every deployed agent now gets its own Entra identity. Here's what actually changed for a solo builder, what it costs, and where the lock-in hides.","section":"stack","snippet":"Microsoft moved   Foundry hosted agents to general availability   — and if you read only the…","url":"/posts/foundry-hosted-agents-ga-bring-your-own-harness-per-agent-identity.html","markdown":"/posts/foundry-hosted-agents-ga-bring-your-own-harness-per-agent-identity.md"},{"slug":"aws-bedrock-agents-classic-frozen-migrate-agentcore-or-abstract","title":"AWS Froze Bedrock Agents into 'Classic' and Locked Out New Builders: Migrate to AgentCore, or Abstract Your Agent Layer","dek":"Existing agents keep running, but the model catalog is frozen at July 30 and new accounts get a 403. The real decision isn't Classic vs AgentCore — it's whether your agent logic is portable enough that AWS's next retirement doesn't become your next rewrite.","section":"wire","snippet":"…You write the agent yourself — in LangGraph, CrewAI, Strands, or plain Python — and AgentCore…","url":"/posts/aws-bedrock-agents-classic-frozen-migrate-agentcore-or-abstract.html","markdown":"/posts/aws-bedrock-agents-classic-frozen-migrate-agentcore-or-abstract.md"},{"slug":"tool-highlight-agentmail-email-inbox-api-for-ai-agents","title":"Tool Highlight: AgentMail — Give Your AI Agent Its Own Email Inbox by API (Send, Receive, Thread, Search)","dek":"Not another transactional-send API. AgentMail gives each agent a real, two-way inbox you create with one API call — so a support, sales, or ops agent can hold an email conversation without you wiring inbound parsing onto Mailgun first.","section":"stack","snippet":"…AgentMail ([agentmail.to](https://www.agentmail.to/)) is an email API that gives an…","url":"/posts/tool-highlight-agentmail-email-inbox-api-for-ai-agents.html","markdown":"/posts/tool-highlight-agentmail-email-inbox-api-for-ai-agents.md"},{"slug":"tool-highlight-ledger-agent-stack-hardware-approval-for-agents","title":"Tool Highlight: Ledger Agent Stack — Give Your Agent the Keys to Nothing","dek":"An agent that can move money is an agent that can be tricked into moving money. Ledger's open-source Agent Stack lets an agent read balances and draft transactions all day — but the signature only happens on a physical device the agent can't reach. The guardrail lives outside the runtime.","section":"stack","snippet":"An AI agent that can move money is, by construction, an agent that can…","url":"/posts/tool-highlight-ledger-agent-stack-hardware-approval-for-agents.html","markdown":"/posts/tool-highlight-ledger-agent-stack-hardware-approval-for-agents.md"},{"slug":"claude-managed-agents-vs-gemini-managed-agents-who-holds-the-session","title":"Claude Managed Agents vs Gemini Managed Agents: Who Should Hold Your Agent's Session?","dek":"Both Anthropic and Google will now run the agent loop for you — no while-loop, no state file, no scheduler. But they hand you very different things. A decision guide for founders picking a hosted agent runtime, with the code that matters.","section":"stack","snippet":"You've decided you want a  managed  agent: the provider runs the loop so…","url":"/posts/claude-managed-agents-vs-gemini-managed-agents-who-holds-the-session.html","markdown":"/posts/claude-managed-agents-vs-gemini-managed-agents-who-holds-the-session.md"},{"slug":"bedrock-agentcore-unified-observability-one-log-group","title":"One Log Group, Whole Agent: Bedrock AgentCore's Unified Observability Just Turned On by Default","dek":"Since July 20, 2026, every new AgentCore agent streams its traces, prompts, structured logs, and stdout into a single per-agent CloudWatch log group — no config. Here's the exact path, the one console toggle that makes traces show up, and how to scope access and export it.","section":"stack","snippet":"…For a new agent, look for  /aws/bedrock-agentcore/runtimes/<agent_id -<endpoint_name…","url":"/posts/bedrock-agentcore-unified-observability-one-log-group.html","markdown":"/posts/bedrock-agentcore-unified-observability-one-log-group.md"},{"slug":"deploy-adk-agent-google-cloud-agents-cli-hands-on","title":"From Empty Folder to Deployed Agent: Google's Agents CLI, Command by Command","dek":"Google's Agents CLI shipped August 3. Here's the whole loop — install, scaffold, run locally, evaluate, deploy, publish — with the real commands, so you can take an ADK agent from an empty folder to a Google Cloud runtime in one sitting.","section":"stack","snippet":"Google's [Agents CLI](/posts/google-agents-cli-skills-layer-coding-agent-deploy-wedge…","url":"/posts/deploy-adk-agent-google-cloud-agents-cli-hands-on.html","markdown":"/posts/deploy-adk-agent-google-cloud-agents-cli-hands-on.md"},{"slug":"expose-agent-as-mcp-server","title":"Your Agent Is Now an MCP Server: What Exposing an Agent as a Tool Quietly Throws Away","dek":"Deploy a LangGraph agent and it auto-publishes a /mcp endpoint, so any client can call it as a tool. Convenient — and lossy. A tool call is a flattened agent, and the parts it flattens are the parts that made it an agent.","section":"wire","snippet":"…Recursive composition — agents calling agents as tools — without [A2A](/posts/a2a-vs-mcp.html…","url":"/posts/expose-agent-as-mcp-server.html","markdown":"/posts/expose-agent-as-mcp-server.md"},{"slug":"google-agents-cli-skills-layer-coding-agent-deploy-wedge","title":"Google's Agents CLI Isn't a Coding Agent — It's a Deploy Wedge Inside the One You Already Use","dek":"Google shipped Agents CLI on August 3. The interesting part isn't a new terminal agent — it's that Google is distributing its Cloud-deploy playbook as skills you drop into Claude Code, Codex, or Antigravity. Here's what it actually is, and the wedge it opens.","section":"wire","snippet":"On   August 3, 2026  , Google shipped   Agents CLI in Agent Platform  . Skim the launch…","url":"/posts/google-agents-cli-skills-layer-coding-agent-deploy-wedge.html","markdown":"/posts/google-agents-cli-skills-layer-coding-agent-deploy-wedge.md"},{"slug":"tool-highlight-agentprizm-governed-agent-memory-skills","title":"Tool Highlight: AgentPrizm — Governed Memory and Skills for Your Agents","dek":"A hosted memory-plus-skills layer for MCP agents that promises audit receipts and right-to-forget; free to start, but you're renting your agents' memory.","section":"stack","snippet":"…AgentPrizm ([agentprizm.com](https://agentprizm.com/)) is a hosted, \"governed\" memory-and-skills layer…","url":"/posts/tool-highlight-agentprizm-governed-agent-memory-skills.html","markdown":"/posts/tool-highlight-agentprizm-governed-agent-memory-skills.md"},{"slug":"aws-agent-registry-ga-discovery-default","title":"AWS Agent Registry Leaves Preview August 6: The Agent-Discovery Layer Just Picked a Default","dek":"On August 6, AWS moves Agent Registry out of preview and out of the bedrock-agentcore namespace into a dedicated agent-registry namespace — quietly making agent discovery a hyperscaler default.","section":"wire","snippet":"On August 6, 2026, AWS Agent Registry leaves public preview. In the same move…","url":"/posts/aws-agent-registry-ga-discovery-default.html","markdown":"/posts/aws-agent-registry-ga-discovery-default.md"},{"slug":"claude-managed-agents-per-session-overrides","title":"Override a Claude Agent's Model and Tools for One Session — Without Versioning It","dek":"Claude Managed Agents let you swap the model, system prompt, tools, MCP servers, or skills for a single session with agent_with_overrides — no new agent version, no config drift. Here's the exact call, the tri-state rules, and the two 400s that will bite you.","section":"stack","snippet":"Claude Managed Agents make you commit up front. The agent is a persisted, versioned…","url":"/posts/claude-managed-agents-per-session-overrides.html","markdown":"/posts/claude-managed-agents-per-session-overrides.md"},{"slug":"migrate-bedrock-agents-classic-to-agentcore-runtime-gateway-memory","title":"Migrate a Bedrock Agents Classic Agent to AgentCore: The Runtime, Gateway, and Memory Calls That Actually Replace It","dek":"There's no converter button. Classic ran your config; AgentCore runs your code. Here's the concrete port map — reuse the Lambdas and Knowledge Base, rewrite the orchestration — with the verified CLI and SDK calls, ARM64 gotcha included.","section":"stack","snippet":"If you're staring at a Bedrock Agents Classic agent wondering how to move…","url":"/posts/migrate-bedrock-agents-classic-to-agentcore-runtime-gateway-memory.html","markdown":"/posts/migrate-bedrock-agents-classic-to-agentcore-runtime-gateway-memory.md"},{"slug":"congress-agentic-trading-sec-clock-july-31","title":"Congress Just Put a July 31 Clock on Agent Trading — What Founders Building Money-Touching Agents Should Read Now","dek":"Eight House Democrats gave the SEC until July 31 to answer 13 questions about brokerages letting AI agents trade for retail clients. The letter names the risk every founder shipping a money-touching agent should already be designing around: correlated agents that herd.","section":"wire","snippet":"…A single bad agent hurts one portfolio. A million agents that all read the…","url":"/posts/congress-agentic-trading-sec-clock-july-31.html","markdown":"/posts/congress-agentic-trading-sec-clock-july-31.md"},{"slug":"agent-identity-standards-track-give-agents-real-ids","title":"The UN Just Put Agent Identity on the Standards Track. Give Your Agents Real IDs Before It Lands.","dek":"The ITU's new Focus Group on Agentic AI is a two-year signal, not a spec. But the teams that win when the rules arrive are already doing the one thing it will require — issuing agents their own identity instead of borrowing a human's.","section":"wire","snippet":"The UN's telecom agency, the ITU, launched a   Focus Group on Agentic AI…","url":"/posts/agent-identity-standards-track-give-agents-real-ids.html","markdown":"/posts/agent-identity-standards-track-give-agents-real-ids.md"},{"slug":"2026-03-07-agenthost-vercel-for-ai-agents","title":"AgentHost: Vercel for AI Agents","dek":"You can now deploy an AI agent site with one curl command. No signup. No config. HTTPS in under a second.","section":"dispatches","snippet":"Deploying something agents build should be as fast as agents build it. That's…","url":"/posts/2026-03-07-agenthost-vercel-for-ai-agents.html","markdown":"/posts/2026-03-07-agenthost-vercel-for-ai-agents.md"},{"slug":"agent-client-protocol-acp-vs-mcp","title":"Agent Client Protocol (ACP): The Third Protocol Named ACP, and Why It's LSP for Coding Agents","dek":"MCP gives an agent tools. ACP gives an agent an editor. The role swap between them is the whole architecture — and it's the reason the same three letters now point at three unrelated standards.","section":"wire","snippet":"…MCP gives an agent tools. ACP gives an agent an editor. In a single…","url":"/posts/agent-client-protocol-acp-vs-mcp.html","markdown":"/posts/agent-client-protocol-acp-vs-mcp.md"},{"slug":"tool-highlight-nooa-nvidia-object-oriented-agent-harness","title":"Tool Highlight: NOOA — NVIDIA's Object-Oriented Agent Framework Makes an Agent Auditable by Design","dek":"Most agent frameworks bolt tracing on after the fact. NOOA — NVIDIA's open-source labs-OO-Agents — makes the agent itself a plain Python class, so every capability, every piece of state, and every model call is testable, traceable, and version-controlled from the first line. It's the harness-layer piece of the new Open Secure AI Alliance.","section":"stack","snippet":"Ask a team running an agent in production the one question that matters after…","url":"/posts/tool-highlight-nooa-nvidia-object-oriented-agent-harness.html","markdown":"/posts/tool-highlight-nooa-nvidia-object-oriented-agent-harness.md"},{"slug":"2026-07-23-founders-wire-measure-identify-account-agents-in-production","title":"The Founder's Wire, Week of July 23: AWS Starts Measuring Coding Agents, Identity Gets an AI-Native Rebuild, and Gartner Puts a Number on the Agent Economy","dek":"Three verified moves that rhyme: the agent stack grew an accountability layer this week. Coding-agent value became a dashboard, machine and agent identity got a $60M rebuild, and the consultants finally priced what's at stake.","section":"wire","snippet":"…AWS started measuring coding-agent value\n\nAmazon CloudWatch   launched Coding Agent Insights on July…","url":"/posts/2026-07-23-founders-wire-measure-identify-account-agents-in-production.html","markdown":"/posts/2026-07-23-founders-wire-measure-identify-account-agents-in-production.md"},{"slug":"cross-agent-memory-layer-memorix-vs-memsearch-vs-agentmemory-vs-memmy","title":"Memorix vs memsearch vs agentmemory vs Memmy: Picking a Cross-Agent Memory Layer","dek":"Four open-source tools now give Claude Code, Codex, and Cursor one shared memory. They don't disagree on recall — they disagree on what your agent's memory *is*: files you own, a tool your agents call, a local service, or a second-brain agent.","section":"stack","snippet":"If you run more than one coding agent —   Claude Code   in the terminal,   Codex…","url":"/posts/cross-agent-memory-layer-memorix-vs-memsearch-vs-agentmemory-vs-memmy.html","markdown":"/posts/cross-agent-memory-layer-memorix-vs-memsearch-vs-agentmemory-vs-memmy.md"},{"slug":"running-ai-agents-on-kubernetes-kagent-agentgateway","title":"How to Run AI Agents on Kubernetes: kagent, agentgateway, and the Data-Plane Split","dek":"Kubernetes already solved \"declare a workload, let a mesh own the network.\" Agents on K8s are quietly re-deriving the same split — and the mistake is letting your framework own connectivity.","section":"stack","snippet":"The first time you put an agent on Kubernetes, the temptation is obvious and…","url":"/posts/running-ai-agents-on-kubernetes-kagent-agentgateway.html","markdown":"/posts/running-ai-agents-on-kubernetes-kagent-agentgateway.md"},{"slug":"2026-06-24-where-to-run-a-long-running-ai-agent","title":"Cloudflare Agents vs Bedrock AgentCore vs Vercel: Where to Run a Long-Running AI Agent","dek":"The three managed agent runtimes don't really compete on price or region. They compete on one question — who owns the agent's state during the hours it sits idle, waiting.","section":"wire","snippet":"Most of what you read about agent infrastructure benchmarks the wrong moment. It clocks…","url":"/posts/2026-06-24-where-to-run-a-long-running-ai-agent.html","markdown":"/posts/2026-06-24-where-to-run-a-long-running-ai-agent.md"},{"slug":"deepagents-code-acp-langchain-coding-agent","title":"LangChain's Deep Agents Now Ships Its Own Coding Agent — and Speaks ACP","dek":"In early July, Deep Agents quietly split into three shippable packages: a model-agnostic harness, a terminal coding agent, and an ACP adapter. The library became a product line — and unbundled the coding agent from both the model and the editor.","section":"wire","snippet":"Somewhere between two alpha tags on July 6th and 7th, LangChain's Deep Agents…","url":"/posts/deepagents-code-acp-langchain-coding-agent.html","markdown":"/posts/deepagents-code-acp-langchain-coding-agent.md"},{"slug":"convex-57m-series-b-backend-for-agent-written-code","title":"Convex Raised $57M to Build the Backend for Agent-Written Code — Why the Money Is Chasing the Layer Under the Agent","dek":"Insight Partners led a $57M Series B into a database that swaps SQL for TypeScript and pre-packages the code AI agents keep getting wrong. Strip the press release and it's a clean bet: as agents write more of the app, the infrastructure that makes agent code behave becomes the defensible layer — and that's where the funding is moving.","section":"wire","snippet":"…capital has largely   stopped rewarding \"another agent\"   — models improve monthly and the agent layer…","url":"/posts/convex-57m-series-b-backend-for-agent-written-code.html","markdown":"/posts/convex-57m-series-b-backend-for-agent-written-code.md"},{"slug":"agent-registry-vs-mcp-registry-discovery","title":"Agent Registry vs MCP Registry: The New Discovery Layer, and Why It's Already Fragmenting","dek":"The MCP registry catalogs tools. The agent registry catalogs agents — and AWS, Google, and Microsoft each shipped one this quarter that can't see the others.","section":"wire","snippet":"For most of 2025, agent discovery meant one question —  where do I find MCP…","url":"/posts/agent-registry-vs-mcp-registry-discovery.html","markdown":"/posts/agent-registry-vs-mcp-registry-discovery.md"},{"slug":"tool-highlight-agent-zero-open-source-agent-computer","title":"Tool Highlight: Agent Zero — the Open-Source Agent You Give a Whole Computer","dek":"What Agent Zero is, who it's for, how to start in one docker command, what it costs (free), and the honest catch — the self-hosted, multi-agent framework that hands an AI a real Linux desktop, a browser, and a shell.","section":"stack","snippet":"Most AI agent tools hand the model a chat box and a few functions…","url":"/posts/tool-highlight-agent-zero-open-source-agent-computer.html","markdown":"/posts/tool-highlight-agent-zero-open-source-agent-computer.md"},{"slug":"microsoft-agent-framework-vs-langgraph-vs-claude-agent-sdk","title":"Microsoft Agent Framework vs LangGraph vs Claude Agent SDK: The Founder's Agent-Stack Pick","dek":"Microsoft folded Semantic Kernel and AutoGen into one production framework and shipped it for .NET and Python. That doesn't make it your default — it sharpens a three-way choice that comes down to one question: what are you optimizing for?","section":"wire","snippet":"…Microsoft Agent Framework   (MAF) folds [Semantic Kernel and AutoGen](https://github.com/microsoft/agent…","url":"/posts/microsoft-agent-framework-vs-langgraph-vs-claude-agent-sdk.html","markdown":"/posts/microsoft-agent-framework-vs-langgraph-vs-claude-agent-sdk.md"},{"slug":"multi-agent-vs-single-agent","title":"Multi-Agent vs Single-Agent: When More Agents Actually Help","dek":"Two of the most-cited essays on agent design say opposite things. They are both right — the disagreement is really about whether your task reads or writes.","section":"wire","snippet":"…The single agent grinds through it sequentially and fails. The multi-agent system splits…","url":"/posts/multi-agent-vs-single-agent.html","markdown":"/posts/multi-agent-vs-single-agent.md"}]}