# Agentic AI Foundation (AAIF) > Agentic AI Foundation (AAIF), a Linux Foundation project, is the neutral and open foundation built on transparency, collaboration, and standardization to advance the public interest in agentic AI innovation. Markdown for agents: any page is also available as Markdown — prefix its path with /md/ (e.g. https://aaif.io/md/blog/), or request the canonical URL with the header `Accept: text/markdown`. ## Pages - [About](https://aaif.io/about): Learn about the Agentic AI Foundation (AAIF) — our mission, governance, and role advancing open, standardized agentic AI in the public interest. - [About Ambassador Program](https://aaif.io/learn-more-about-the-program): How the AAIF Ambassador Program works, what ambassadors do, and how to get involved. - [Ambassador Program](https://aaif.io/ambassadors): An elite cohort of practitioners helping the world understand, use, and contribute to AAIF-hosted projects. - [Awards](https://aaif.io/awards): Recognizing the individuals, teams, and organizations building the open agentic AI ecosystem. - [Blog](https://aaif.io/blog): Guides, release notes and field reports on MCP, A2A, goose, AGENTS.md and agentgateway from the builders and maintainers at the Agentic AI Foundation. - [Brand](https://aaif.io/brand): We welcome our community to use AAIF brand assets. - [Case study](https://aaif.io/case-study): Case studies from projects hosted by the Agentic AI Foundation (AAIF). - [Community Chapters](https://aaif.io/community-chapters): AAIF Community Chapters bring members together through local events and community-driven initiatives that connect, educate, and inspire collaboration. - [Contact Us](https://aaif.io/contact): Contact us with questions related to Agentic AI Foundation (AAIF). - [Events](https://aaif.io/events): Join Agentic AI Foundation events worldwide: AGNTCon + MCPCon, MCP Dev Summits and community meetups where builders shape open standards for agentic AI. - [Governing Board](https://aaif.io/board): The governing board members of the AAIF. - [Home](https://aaif.io/): Agentic AI Foundation (AAIF) is the neutral and open foundation built on transparency, collaboration, and standardization to advance the public interest in agentic AI innovation. - [Members](https://aaif.io/members): Agentic AI Foundation members work together to further innovate, protect and standardize agentic AI. - [News](https://aaif.io/news): The latest news and press from the Agentic AI Foundation (AAIF). - [Projects](https://aaif.io/projects): AAIF is host to top open source - [Staff](https://aaif.io/staff): The team supporting AAIF. - [Submit a Project](https://aaif.io/submit-a-project): Propose an open source project to be hosted by the Agentic AI Foundation (AAIF). - [Technical Committee](https://aaif.io/tc): The members of the AAIF Technical Steering Committee. - [Videos](https://aaif.io/video): Watch exclusive interviews, event highlights, and deep dives into AAIF and agentic AI. - [Working Groups](https://aaif.io/working-groups): AAIF.io Working Groups bring members together to collaborate on focused initiatives, share expertise, and drive practical outcomes across the AI ecosystem. - [Working Groups calendar](https://aaif.io/working-groups/calendar): AAIF.io Working Groups bring members together to collaborate on focused initiatives, share expertise, and drive practical outcomes across the AI ecosystem. ## Blog - [James Ward thinks your MCP server could use some work](https://aaif.io/blog/james-ward-thinks-your-mcp-server-could-use-some-work): James Ward has a useful response to complaints that MCP wastes tokens: Show me the tools. If your agent needs 100 customer records and you gave it a tool that fetches exactly one, the ensuing parade o - [Why "agent failed" doesn't tell you enough](https://aaif.io/blog/why-agent-failed-doesn-t-tell-you-enough): An agent asked to cancel an order and issue a refund can fail in several different ways. The order service might be temporarily unavailable, the customer might not have permission to cancel, or the or - [How do you prove your AI governance works? Lessons from Toronto](https://aaif.io/blog/how-do-you-prove-your-ai-governance-works-lessons-from-toronto): Lessons from MCP Dev Summit Toronto on how enterprises are handling agent identity, access controls, enforcement, and audit evidence, with examples from NVIDIA, Accenture, and RBC. - [The security architecture customer-facing agentic apps actually need](https://aaif.io/blog/the-security-architecture-customer-facing-agentic-apps-actually-need): A practical look at securing customer-facing agentic applications with scoped tokens, human approval gates, intent logging, and continuous access checks built on open standards. - [Maintainer roundtable at AGNTCon + MCPCon EU: Composability, identity, and the cost of agents](https://aaif.io/blog/maintainer-roundtable-at-agntcon-mcpdev-summit-eu-composability-identity-and-the-cost-of-agents): At a maintainer roundtable during AGNTCon + MCPDev Summit EU in Amsterdam, moderator Nitish Tyagi of Gartner sat down with four people building the infrastructure underneath the agentic AI stack: Davi - [I saw something in MCP. Then I spent 18 months building it.](https://aaif.io/blog/i-saw-something-in-mcp-then-i-spent-18-months-building-it): TL;DR: In March 2025, my first working MCP connection made me see a different future for network operations. Eighteen months of open-source experiments became NetClaw and a talk at MCP Dev Summit Toro - [Welcome to Glass Town: building a software factory with a paper trail](https://aaif.io/blog/welcome-to-glass-town-building-a-software-factory-with-a-paper-trail): A hands-on look at building Glass Town, a transparent software factory using agent workers, persistent remote environments, Git-linked session history, and practical token controls. - [Can you reproduce an agent run?](https://aaif.io/blog/can-you-reproduce-an-agent-run): Reproducing an agent run takes more than rerunning code. What execution history needs to capture, from model responses and tool results to state, permissions, and human decisions. - [Notation for the human-agent symphony: how CHAP records human judgment alongside MCP](https://aaif.io/blog/notation-for-the-human-agent-symphony-how-chap-records-human-judgment-alongside-mcp): How the Collaborative Human-Agent Protocol gives approvals, overrides and handoffs a written form that anyone can replay, verify and improve. - [The Agent Gets a Body](https://aaif.io/blog/the-agent-gets-a-body): Giving agents control of physical devices makes state, identity, observability and confirmed outcomes much more important, from hardware fleets to factories and autonomous vending machines. - [Stateless MCP changes your security model: how to harden your MCP servers](https://aaif.io/blog/stateless-mcp-changes-your-security-model-how-to-harden-your-mcp-servers): A practical guide to hardening stateless MCP servers, covering state handles, requestState protection, routing headers, cache scope, retries, and authorization changes. - [There Is No One Agentic Commerce Protocol](https://aaif.io/blog/there-is-no-one-agentic-commerce-protocol): Agentic commerce spans discovery, authorization, payment and fulfillment. UCP, AP2, x402 and A2A each address different parts of that journey rather than replacing one another. - [Trace and analyze Goose sessions with OpenTelemetry, Jaeger and ClickHouse](https://aaif.io/blog/trace-and-analyze-goose-sessions-with-opentelemetry-jaeger-and-clickhouse): Use OpenTelemetry, Jaeger, and ClickHouse to trace Goose sessions, identify where latency comes from, inspect agent and tool activity, and persist telemetry for later analysis. - [Five themes from AGNTCon + MCPCon Europe](https://aaif.io/blog/five-themes-from-agntcon-mcpcon-europe): TL;DR: The clearest message from Amsterdam was how much of agent engineering now depends on what sits around the model: protocols, identity, state, evaluation and workflows that keep human review mana - [Agent identity and delegated access in MCP systems](https://aaif.io/blog/agent-identity-and-delegated-access-in-mcp-systems): A GitHub issue about a failing deployment has been assigned to you. You ask an internal agent to check the issue against the deployment runbook and post a status update. The agent works through tools - [Before Agents Can Work Together, They Have to Find Each Other](https://aaif.io/blog/before-agents-can-work-together-they-have-to-find-each-other): Agent interoperability depends on discovery as well as communication. AI Catalog, AGNTCY, ARD, DNS and A2A are exploring ways for agents to find and evaluate capabilities dynamically. - [AGENTS.md speaks UNIX, and you should too](https://aaif.io/blog/agents-md-speaks-unix-and-you-should-too): Unix gives coding agents the tools. AGENTS.md explains where to edit, how to check, and what to preserve. Lessons from my dotfiles and human review. - [What agents look like when the data can't leave the building](https://aaif.io/blog/what-agents-look-like-when-the-data-cant-leave-the-building): Explore how agentic AI architectures must adapt when production data cannot leave secure environments like mainframes in banking, insurance, and regulated industries. - [Docker's Sandbox Kit Spec puts Agent Permissions inside the container image](https://aaif.io/blog/dockers-sandbox-kit-spec-puts-an-agents-permissions-inside-the-container-image): Docker released V3 of the Sandbox Kit Spec, moving agent permissions directly inside OCI images to bridge the agentic container gap and standardize agent governance. - [The Web Is Growing a Second Interface](https://aaif.io/blog/the-web-is-growing-a-second-interface): WebMCP, MCP Apps and A2UI are creating new ways for agents to interact with websites and services without relying entirely on browser automation built for humans. - [Securing requestState with OpenBao](https://aaif.io/blog/securing-requeststate-with-openbao): A follow-up to our article on Designing RequestState for Multi-Round Trip Requests. All code in this post is from the companion repository `openbao-mcp-requeststate`. - [AI governance in a regulated industry: How MoonPay brought MCP sprawl under control](https://aaif.io/blog/ai-governance-in-a-regulated-industry-how-moonpay-brought-mcp-sprawl-under-control): When AI agents can act inside internal systems, governance becomes an infrastructure problem: knowing which connections exist, what they can touch, and what they did. - [Before an agent uses a model: verifying model custody on customer infrastructure](https://aaif.io/blog/before-an-agent-uses-a-model-verifying-model-custody-on-customer-infrastructure): An enterprise wants an agent to answer questions over sensitive internal records. It can keep the records on its own infrastructure, run inference locally, and give the agent access to approved tools. - [MCP's big, open-world vision](https://aaif.io/blog/mcp-big-open-world-vision): Understanding why the protocol is for strangers and the critical role that extensions play - [Your Agent Will Wake Up Eventually. Plan Accordingly.](https://aaif.io/blog/your-agent-will-wake-up-eventually-plan-accordingly): Long-running agents need more than persistence. They need durable state, recovery, idempotency and checkpoints that let work resume safely after failures. - [402 payment required: what enterprise MCP servers owe the agents that pay them](https://aaif.io/blog/402-payment-required-what-enterprise-mcp-servers-owe-the-agents-that-pay-them): Two protocol releases seven months apart made a similar move, for related reasons, and the two are usually discussed as if unrelated. - [Safety, messaging and open source agents in Shanghai](https://aaif.io/blog/safety-messaging-and-open-source-agents-in-shanghai): On September 5, members of the AAIF community gathered in Shanghai ahead of AGNTCon + MCPCon China to share work across open source agents, safety, messaging, edge computing, and agent infrastructure. - [Introducing the First Open Source Vending Machine Benchmark](https://aaif.io/blog/introducing-the-first-open-source-vending-machine-benchmark): TLDR: We just launched Prosus Vending Bench, an open-source simulated vending business for testing tool-using agents. We packaged six machines, three locations and 22 MCP tools with Harbor, the framew - [From supervised shells to purpose-built MCP tools](https://aaif.io/blog/from-supervised-shells-to-purpose-built-mcp-tools): Testing a narrow GPU metrics server on a live NVIDIA GPU. - [Dex Still Thinks Long-Running Coding Agents Stink](https://aaif.io/blog/dex-still-thinks-long-running-coding-agents-stink): The models are better. The benchmarks are higher. Dex Horthy has fresh evidence that unattended coding agents still turn healthy codebases into radioactive spaghetti. He wants you to hear about it. - [Implementing enterprise-managed MCP authorization in Keycloak](https://aaif.io/blog/implementing-enterprise-managed-mcp-authorization-in-keycloak): Enterprise MCP authorization gets complex at scale. This post introduces ID-JAG, an enterprise-managed authorization approach implemented in Keycloak, and previews upcoming EMA ecosystem support. - [Envoy AI Gateway becomes Agent Router and joins AAIF](https://aaif.io/blog/agent-router-joins-aaif): The open source project, powered by Envoy, that gives developers a single integration for models and tools has a new name and a new home. - [Agent Router: Powerful traffic handling for agent builders](https://aaif.io/blog/agent-router-powerful-traffic-handling-for-agent-builders): Envoy AI Gateway is now Agent Router and has joined the Agentic AI Foundation. This post is about what Agent Router is and what it does for the agent you are building. - [Code Is Cheap. Proof Is the Bottleneck.](https://aaif.io/blog/code-is-cheap-proof-is-the-bottleneck): Coding agents can generate software faster than teams can verify it. This piece looks at the emerging bottleneck: proving code is correct, safe, reliable, and maintainable. - [Agent memory: patterns, tradeoffs, open problems](https://aaif.io/blog/agent-memory-patterns-tradeoffs-open-problems): A practical guide to agent memory patterns, from conversation state and retrieval to shared memory, covering tradeoffs in freshness, provenance, access, deletion, and security. - [MCP 2026 changes the rules](https://aaif.io/blog/mcp-2026-changes-the-rules): The latest MCP version marks a break with the standard we’ve known until now, particularly for deployments that need to scale across multiple server instances and load balancers. - [Authorization in MCP 2026-07-28: Clarifying trust relationships for agentic systems](https://aaif.io/blog/authorization-in-mcp-2026-07-28-clarifying-trust-relationships-for-agentic-systems): The Model Context Protocol (MCP) is becoming an important integration layer for agentic systems because it gives MCP clients a consistent way to access tools, data, and backend services on behalf of u - [Deploying MCP 2026-07-28 servers on AWS: A serverless reference architecture](https://aaif.io/blog/deploying-mcp-2026-07-28-servers-on-aws-a-serverless-reference-architecture): A practical AWS serverless reference architecture for MCP servers, using API Gateway, Cognito, Lambda, and DynamoDB, backed by STRIDE threat analysis. - [Catch Them Early](https://aaif.io/blog/aaif-sandbox-phase): The Agentic AI Foundation adds a Sandbox phase to catch early-stage projects before governance becomes expensive to retrofit. Learn about the new lifecycle policy. - [MCP Usage Surged as the Protocol Went Stateless](https://aaif.io/blog/mcp-usage-surged-as-the-protocol-went-stateless): MCP tool calls surged this summer. Learn how the stateless July release helped service providers scale to meet surging demand. - [A2A v1.0: a builder's guide, part 2 - migration, security, and production ](https://aaif.io/blog/a2a-v1-0-a-builder-s-guide-part-2-migration-security-and-production): This second part picks up with the breaking wire changes in v1.0, then moves through migration from 0.3, bindings, security, durability, authorization, and conformance. - [The claim isn’t hard. The paperwork is.](https://aaif.io/blog/the-claim-isn-t-hard-the-paperwork-is): How MCP Apps put live CMS policy next to the answer — without feeding it to the model - [Improving tool-call reliability with JSON Schema 2020-12](https://aaif.io/blog/improving-tool-call-reliability-with-json-schema-2020-12): The promise of autonomous agents lies in their ability to interact with complex systems, yet their integration with existing enterprise APIs is frequently hindered by a fundamental reliability gap. Wh - [Handle long-running MCP tool calls with the MCP Tasks extension](https://aaif.io/blog/handle-long-running-mcp-tool-calls-with-the-mcp-tasks-extension): A few weeks ago, I gave a talk on something that sounds simple but is actually fairly complex: how to handle long-running MCP tool calls. - [Designing Websites for People and AI Agents with WebMCP](https://aaif.io/blog/designing-websites-for-ai-agents-with-webmcp): Learn how WebMCP lets web developers publish structured tools for AI agents, enabling direct function calls instead of page interpretation. Reduce errors and token use. - [Your agent’s memory is a software supply chain](https://aaif.io/blog/your-agents-memory-is-a-software-supply-chain): Agent memory acts like a software supply chain: persistent context helps agents but stale, malicious, or wrong memories can be silently executed, creating serious security and reliability risks. - [A platform team's guide to MCP 7-28](https://aaif.io/blog/a-platform-team-s-guide-to-mcp-7-28): The 2026-07-28 revision of the Model Context Protocol (referred to here as 7-28) moved more of MCP from an application concern toward an infrastructure one, and the practical consequence is that more - [A2A v1.0: a builder's guide, part 1 - discovery, tasks, and clients](https://aaif.io/blog/a2a-v1-0-a-builder-s-guide-part-1-discovery-tasks-and-clients): In part 1, we'll cover the core v1.0 flow: discovery, task lifecycle, server and client behavior, and the ways clients can follow work as it progresses. - [What We Learned Putting A2A Into Production](https://aaif.io/blog/what-we-learned-putting-a2a-into-production): How Eon's engineering team deployed the A2A protocol in their multi-agent assistant, covering agent cards, identity, provenance extensions, and production lessons learned. - [How to Build Reliable AI Agent Systems for Production](https://aaif.io/blog/how-to-build-reliable-ai-agent-systems-for-production): Learn how to build reliable AI agent systems for production with policy enforcement, narrow permissions, context provenance, recovery patterns, and safe stopping mechanisms. - [Enterprise MCP gateway security in practice with agentgateway](https://aaif.io/blog/enterprise-mcp-gateway-security-in-practice-with-agentgateway): Enterprise teams use MCP gateways to control how AI agents reach tools, services, and company data. Agentgateway, an open source project hosted by the Agentic AI Foundation, routes MCP, Agent-to-Agent - [How Does Agentic Commerce Work?](https://aaif.io/blog/how-does-agentic-commerce-work): Explore the emerging protocols enabling agentic commerce, from Google's UCP to Visa's Trusted Agent Protocol, and why agents need standard ways to shop and pay on behalf of users. - [Where A2A fits in the open agent ecosystem](https://aaif.io/blog/where-a2a-fits-in-the-open-agent-ecosystem): A2A standardizes collaboration between independent agents. It works alongside MCP, UCP, AP2, and established web standards, each addressing a different part of an agent interaction. - [Building a read-only multi-cloud Kubernetes inventory with goose](https://aaif.io/blog/building-a-read-only-multi-cloud-kubernetes-inventory-with-goose): A design walkthrough for OKE and AKS using a goose recipe, supervised shell access, and read-only cloud credentials. - [MCP sessions are gone. Where should your state live?](https://aaif.io/blog/mcp-sessions-are-gone-where-should-your-state-live): MCP 2026-07-28 removes something remote MCP servers have quietly depended on for a long time: transport-level sessions. - [What MCP builders learned in Seoul](https://aaif.io/blog/what-mcp-builders-learned-in-seoul): A recap of 43 sessions from MCP Dev Summit Seoul 2026, covering tool design, security, identity, testing, production reliability, and emerging applications across robotics, mobile, and ML. - [MCP in practice: lessons from Seoul](https://aaif.io/blog/mcp-in-practice-lessons-from-seoul): Five engineering lessons from MCP Dev Summit Seoul, covering tool design, security, testing, observability, and the challenges of bringing MCP into new environments. - [A2A joins AAIF’s open agentic stack](https://aaif.io/blog/a2a-joins-aaif): Agent2Agent (A2A), the open standard for inter-agent communication, is joining the Agentic AI Foundation (AAIF) as a hosted project. - [Putting a front door on local AI with agentgateway](https://aaif.io/blog/putting-a-front-door-on-local-ai-with-agentgateway): Authentication, a shared token budget, health-based failover, and usage metrics for self-hosted models: one binary, one YAML file, no Kubernetes required. - [Building a governed MCP platform with agentgateway ](https://aaif.io/blog/building-a-governed-mcp-platform-with-agentgateway): An AI agent can connect to a model or tool in minutes. The harder questions arrive later: Which identity made the call? Which tools was it allowed to discover? Would a failed model route recover? Coul - [Writing an effective AGENTS.md](https://aaif.io/blog/writing-an-effective-agents-md): An AGENTS.md file can tell a coding agent how to work inside a repository: where relevant code lives, which commands to run, which files have special handling, and what needs to be true before a chang - [Designing requestState for Multi Round-Trip Requests](https://aaif.io/blog/designing-requeststate-for-multi-round-trip-requests): How MRTR works in MCP 2026-07-28, how to design requestState, and the implementation and security trade-offs that matter in production. - [Agent observability: what to track first](https://aaif.io/blog/agent-observability-what-to-track-first): Standard monitoring misses this kind of failure. The run keeps dying partway through, and from outside it looks like a flaky tool or a bad model day. At Port of Context, the cause only showed up once - [Who told the agent it could spend?](https://aaif.io/blog/who-told-the-agent-it-could-spend): Once an MCP tool call can move money, authorization stops being a login detail and becomes where financial risk is actually controlled. But that control doesn't live in one place. The OAuth/MCP layer - [The age of stateless MCP](https://aaif.io/blog/the-age-of-stateless-mcp): The new MCP specification is out. It is the largest protocol change since MCP launched, and it addresses a problem that became obvious as remote servers moved from demos into production: the protocol - [We built a small browser game about the MCP 728 spec](https://aaif.io/blog/we-built-a-small-browser-game-about-the-mcp-728-spec): Introducing Protocol Kwest: Rise of the Stateless Order, a small game that runs in your web browser, and it teaches what changed in the MCP spec revision dated 2026-07-28. - [Non-blocking human-in-the-loop agents: re-engineering agentic runloops and state machines with MRTR](https://aaif.io/blog/non-blocking-human-in-the-loop-agents-re-engineering-agentic-runloops-and-state-machines-with-mr): How MCP 2026-07-28 Multi Round-Trip Requests let enterprise agents pause for human approval without long-lived server connections — with a LangGraph and agentgateway design walkthrough. - [The enterprise MCP scaling paradox: why every agent needs a tailored backend](https://aaif.io/blog/the-enterprise-mcp-scaling-paradox-why-every-agent-needs-a-tailored-backend): Explore why scaling Model Context Protocol in enterprises creates operational challenges - from server proliferation to governance gaps - and how tailored backends solve the paradox. - [Exposing OpenAPI operations as authorized MCP tools with agentgateway and Keycloak](https://aaif.io/blog/exposing-openapi-operations-as-authorized-mcp-tools-with-agentgateway-and-keycloak): Recently, Model Context Protocol (MCP) has been gaining significant traction for enabling Agentic AI to integrate with external tools. Exposing existing OpenAPI operations as authorized MCP tools requ - [From Skills and Tools to Portable Agent Plugins](https://aaif.io/blog/from-skills-and-tools-to-portable-agent-plugins): Agent Plugins 1.0 defines a small, open package format for distributing Agent Skills and MCP servers across compatible clients. - [Using Keycloak as an MCP authorization server](https://aaif.io/blog/using-keycloak-as-an-mcp-authorization-server): MCP, or Model Context Protocol, is an open standard protocol for connecting AI applications with external systems. With MCP, AI agents can access local files, databases, search engines, enterprise sys - [AI Music Needs More Knobs: YouAndOrchestra Makes Conducting Agents a Compositional Exercise](https://aaif.io/blog/ai-music-needs-more-knobs-youandorchestra-makes-conducting-agents-a-compositional-exercise): TLDR: AI music production is shifting from one-shot prompt generation toward agentic co-creation that prioritizes granular control and iterative feedback, exemplified by projects like YouAndOrchestra. - [Three judgments from AI Native Shanghai](https://aaif.io/blog/three-judgments-from-ai-native-shanghai): On 23 July 2026, members of the AAIF and CNCF communities met in Shanghai to discuss how current open source projects can support the design of AI-native systems. - [The EU AI Act and the New Rules for Building AI Agents](https://aaif.io/blog/the-eu-ai-act-and-the-new-rules-for-building-ai-agents): What companies need to know about risk, transparency, oversight, and accountability across the agentic stack. - [The Ecosystem Responds to Stateless MCP](https://aaif.io/blog/the-ecosystem-responds-to-stateless-mcp): Within days of the MCP 2026-07-28 specification release, infrastructure providers, SDK maintainers, cloud platforms, and tool vendors aligned with new version. - [MCP in production: what changes after the demo works](https://aaif.io/blog/mcp-in-production-what-changes-after-the-demo-works): A demo MCP server might expose one tool, add_to_cart, that a model calls a few times before checkout. With a single user on one machine, after a few seconds, it runs and the work looks done. - [56 things we learned from MCP Dev Summit Bengaluru](https://aaif.io/blog/56-things-we-learned-from-mcp-dev-summit-bengaluru): MCP Dev Summit Bengaluru showed the protocol moving from early server demos toward production infrastructure. The sessions covered tool design, context budgets, gateways, registries, identity, authori - [Governance as Infrastructure — What the MCP 2026-07-28 Migration Actually Demands of Permissions, Audit, and Lifecycle](https://aaif.io/blog/governance-as-infrastructure-what-the-mcp-2026-07-28-migration-actually-demands-of-permissions-a): The 2026-07-28 revision of the Model Context Protocol is the largest change since the protocol launched. Its headline is technical: the protocol core becomes stateless. The initialize handshake and th - [Safely Rolling Out the July 28 MCP Update with agentgateway](https://aaif.io/blog/safely-rolling-out-the-july-28-mcp-update-with-agentgateway): The biggest architectural change is that MCP communication is now designed around stateless requests. - [The Anatomy of MCP Authorization: How the Hardened Flow Actually Runs](https://aaif.io/blog/the-anatomy-of-mcp-authorization-how-the-hardened-flow-actually-runs): Before the first packet moves, hold roles of OAuth apart cleanly, because everything downstream depends on you not blurring them. - [Verifiable Evidence at the MCP Boundary](https://aaif.io/blog/verifiable-evidence-at-the-mcp-boundary): What the 2026-07-28 Model Context Protocol release sets up, and how we build on it together - [Migrate Sessions to Stateless Requests with MCP 2026-07-28](https://aaif.io/blog/migrate-sessions-to-stateless-requests-with-mcp-2026-07-28): MCP 7-28: a new extensions framework, OAuth/OpenID authorization updates, a formal deprecation policy, and more. - [MCP Graduates to Enterprise Infrastructure: Stateless Architecture, Formal Governance, and Security Hardening](https://aaif.io/blog/mcp-graduates-to-enterprise-infrastructure-stateless-architecture-formal-governance-and-security): The largest update to the protocol since launch removes core scaling bottlenecks, adding first class extensions, hardening authentication and adding a formal deprecation policy to make agentic AI read - [7-28 Hands MCP to Platform Teams](https://aaif.io/blog/7-28-hands-mcp-to-platform-teams): The 7-28 MCP spec revision includes a number of capabilities that will resonate with platform teams. - [MCP Just Handed You a Deprecation Policy. Steal It.](https://aaif.io/blog/mcp-just-handed-you-a-deprecation-policy-steal-it): The MCP 2026-07-28 release gives teams a template for addressing a production failure most people have not connected it to yet, and it is not the part of the spec anyone is talking about. It is a temp - [Measuring AGENTS.md: What Five Runs Show That One Doesn't](https://aaif.io/blog/measuring-agents-md-what-five-runs-show-that-one-doesn-t): Five controlled tests show AGENTS.md improves coding agent efficiency, reducing tokens, time, and unnecessary code changes. - [MCP 2026-07-28: What's Changing and How to Migrate](https://aaif.io/blog/mcp-2026-07-28-whats-changing-and-how-to-migrate): Explore MCP's biggest update since launch. Learn how the protocol evolves from local tool to distributed, stateless architecture for enterprise scale. - [Agentgateway now supports ID-JAG and MCP Enterprise Managed Auth](https://aaif.io/blog/agentgateway-now-supports-id-jag-and-mcp-enterprise-managed-auth): Agentgateway now supports MCP Enterprise Managed Auth and ID-JAG, giving enterprises centralized control over AI agent access to SaaS tools—no per-user consent required. - [MCP 7-28 Release Party — Come Celebrate With the AAIF Community Near You](https://aaif.io/blog/mcp-7-28-release-party-come-celebrate-with-the-aaif-community-near-you): The Model Context Protocol hits a major milestone, and we are marking it the right way: in person, with the people building it. - [Running goose fully offline on a DGX Spark](https://aaif.io/blog/running-goose-fully-offline-on-a-dgx-spark): A hands-on look at running a local-first agent on the NVIDIA DGX Spark: zero cloud calls, on a 128 GB box that fits on a desk. Almost every agent demo you see talks to a frontier model over a cloud A… - [Introducing MCP 7-28 for AI Application Developers: What Goes Away, and What Might Break](https://aaif.io/blog/introducing-mcp-7-28-for-ai-application-developers-what-goes-away-and-what-might-break): Junghwan Park (9bow) is an AAIF Ambassador, a PyTorch Ambassador, and the lead maintainer of the PyTorch Korea User Group (PyTorchKR). A Korean version of this post is available here. TL;DR: MCP 7-28… - [Agentic AI Is Being Built in Real Life — Come Build It With Us](https://aaif.io/blog/agentic-ai-is-being-built-in-real-life-come-build-it-with-us): We're looking for venue hosts, organizers, and anyone who wants to help grow the AAIF events community. Raise your hand and tell us how you'd like to take part. - [The Human Agent: A Random Lunch, Blind Developers, and the Human Connection Launching the Loop](https://aaif.io/blog/the-human-agent-blind-developers-and-the-human-connection-launching-the-loop): Humans remain the most creative and critical actors in the agent economy. Even in open-ended environments like OpenClaw, AI agents still operate within relatively constrained paths. Humans don't. We… - [Introducing the MCPA: the First Official Certification for the Model Context Protocol](https://aaif.io/blog/introducing-the-mcpa-the-first-official-certification-for-the-model-context-protocol): The Model Context Protocol (MCP) has become one of the most important standards in agentic AI. In a little over a year, it went from a promising idea to the default way AI applications connec… - [Agentic AI Momentum Report](https://aaif.io/blog/agentic-ai-momentum-report): We track the top open source agentic AI projects gaining traction and becoming core ecosystem infrastructure. The Momentum set spans 116 projects across 5 layers: Frameworks & Infrastructure, Agent C… - [Can MCP Help a Small Local Model Shine? Hands-on with Goose](https://aaif.io/blog/can-mcp-help-a-small-local-model-shine-hands-on-with-goose): I wanted to know whether the whole agent loop could run locally on my M3 24GB laptop: the model, the tools, and my MCP server on the same machine, with no cloud model provider in the loop. - [Community Spotlight: Building the Interoperable Internet of Agents with Jason Cottrell](https://aaif.io/blog/community-spotlight-building-the-interoperable-internet-of-agents-with-jason-cottrell): The true power of agentic systems lies in openness. The growth of agentic AI is too vast, too important, and too transformative to belong to any single software vendor. To move beyond single-prototyp… - [Beyond Single-User Bots: How goose is Building a Distributed AI Teammate Ecosystem with MCP and Shared Compute](https://aaif.io/blog/how-goose-is-building-a-distributed-ai-teammate-ecosystem): Most AI assistants are designed as isolated, single-user desktop utilities tied to an individual's local terminal and API keys. They operate within silos, unable to collaborate across engineering tea… - [Agentgateway v1.3.0: LLM Consumption, Reimagined](https://aaif.io/blog/agentgateway-v1-3-0-llm-consumption-reimagined): Agentgateway, an open gateway project for agentic AI infrastructure that joined the Agentic AI Foundation, has released v1.3.0. The release rebuilds how the gateway handles LLM traffic. - [Productionizing MCP for Regulated Industries: Three Hard Constraints for Enterprise Engineering](https://aaif.io/blog/productionizing-mcp-for-regulated-industries-three-hard-constraints-for-enterprise-engineering): Deploying Model Context Protocol architectures within enterprise banking environments that require strict security patterns like out-of-band personal data isolation, distributed tracking, and decoupl… - [Community Spotlight: JetBrains' Katherine Druckman on Why Open Collaboration Is Essential to Trusted Agentic AI](https://aaif.io/blog/community-spotlight-jetbrains-katherine-druckman-on-why-open-collaboration-is-essential-to-trusted-agentic-ai): Katherine Druckman, Head of Community and Partnership Engagement at JetBrains, a Gold Member of the Agentic AI Foundation (AAIF) with nearly two decades of experience in open source software communit… - [A Stronger Voice: What Membership Can Mean in Open Agentic AI](https://aaif.io/blog/a-stronger-voice-what-membership-can-mean-in-open-agentic-ai): Step deeper into working groups, draft a blog post, or bring novel ideas to office hours. There's a lot left to build, and giving direct supporters a voice is one of the more important tools in that… - [We Planned for 10 Ambassadors. We're Welcoming 138.](https://aaif.io/blog/we-planned-for-10-ambassadors-were-welcoming-138): The first AAIF Ambassador cohort is composed of 138 members across 41 countries. Here's what the response to this program revealed about where the agentic AI community actually is right now. - [Native Speakers: Why AI's Most Powerful Users Are Blind](https://aaif.io/blog/native-speakers-why-ais-most-powerful-users-are-blind): Large language models don't “see” interfaces, buttons, or navigate visually. They live and die by language, and that fact arguably makes LLMs one of the most consequential accessibility developments… - [How Vstorm Put AGENTS.md Into Every AI Agent-Ready Project It Ships](https://aaif.io/blog/how-vstorm-put-agents-md-into-every-ai-agent-ready-project-it-ships): Vstorm, an Applied Agentic AI Engineering Consultancy and AAIF Silver Member, embedded AGENTS.md auto-generation into its open source agentic AI project template. Every FastAPI + Next.js project the… - [Skills Over MCP](https://aaif.io/blog/skills-over-mcp): I’m a big fan and user of both MCP and Agent Skills, so when I learned there’s a Skills Over MCP working group (WG) that’s looking into integrating Skills with MCP, I had no choice but to lurk. - [Introducing the AAIF Annual Technical Excellence Awards — Nominations Now Open](https://aaif.io/blog/introducing-the-aaif-annual-technical-excellence-awards): The open agentic AI community has built something remarkable. It's time we celebrated the people and organizations making it happen. - [How to Write a Great Nomination for the AAIF Technical Excellence Awards](https://aaif.io/blog/how-to-write-a-great-nomination-for-the-aaif-technical-excellence-awards): The inaugural AAIF Annual Technical Excellence Awards are here — and your nomination could make all the difference. - [MCP's Missing Half: Why Second-Order Servers Don't Exist Yet](https://aaif.io/blog/mcps-missing-half-why-second-order-servers-dont-exist-yet): MCP servers can call tools, but clients cannot expose them back to servers. Jerome Swannack, one of MCP's original architects, explains how client-to-server tool sharing could unlock more modular, pl… - [TIL at MCPDev Summit Bengaluru: Six Lessons from the Agentic Frontier](https://aaif.io/blog/til-at-mcpdev-summit-bengaluru-six-lessons-from-the-agentic-frontier): The Agentic AI Foundation held its first event in India last week in Bengaluru and the community came out in force for a dose of agentic truthtelling. The 57 sessions were packed and the energy in th… - [AI Agents for Air-Gapped Industrial Environments: Why goose?](https://aaif.io/blog/ai-agents-for-air-gapped-industrial-environments-why-goose): The explosive growth of AI agent technology has brought tools like OpenAI’s Claude Code, Grok Build, and Codex to the forefront. While the IT industry has rapidly adopted these advancements, the situ… - [Three Key Operational Patterns You Need to Prevent MCP Horror Stories](https://aaif.io/blog/three-key-operational-patterns-you-need-to-prevent-mcp-horror-stories): Many MCP failures come from weak security architecture or lack of operational guardrails for what the agents can and cannot do. In her talk, Cecilia Liu of Docker examined two real MCP “horror storie… - [How Port of Context eliminated production agent failures with goose, Arcade.dev, and Code Mode](https://aaif.io/blog/how-port-of-context-eliminated-production-agent-failures): Port of Context needed a GTM intelligence agent that could search multiple key terms in real time across data-intensive sources like GitHub and Hacker News. Before committing to an execution path, th… - [goose Doubles Down on Open in Latest Two Releases](https://aaif.io/blog/goose-doubles-down-on-open-in-latest-two-releases): goose is an open source AI agent runtime hosted at the Agentic AI Foundation. Its last two releases, versions 1.36 and 1.37, dropped in quick succession and together push goose further open.Here's wh… - [Karpathy's LLM Wiki as Agent Memory](https://aaif.io/blog/karpathys-llm-wiki-as-agent-memory): At work, I’m building agents to handle various operational tasks and have found Karpathy’s LLM Wiki design to be an excellent solution for implementing most types of memory for my agents.The LLM wiki… - [Designing agentgateway: A Unified High-Performance Gateway for AI and API Traffic](https://aaif.io/blog/designing-agentgateway-a-unified-high-performance-gateway-for-ai-and-api-traffic): Solo.io’s Lin Sun on the infrastructure challenges emerging around AI systems, why existing gateway patterns are being stretched in new ways, and why agentgateway was built as a unified, high-perform… - [agentgateway Joins AAIF as an Open Gateway for Agentic AI Infrastructure](https://aaif.io/blog/agentgateway-joins-aaif-as-an-open-gateway-for-agentic-ai-infrastructure): The Agentic AI Foundation welcomes agentgateway — an open source gateway purpose-built for MCP, Agent-to-Agent, LLM, and API traffic — as its newest hosted project. - [AAIF Community Spotlight: Yaron Schneider – Why Strong Foundations and Standardization Will Define the Era of Agentic AI](https://aaif.io/blog/why-strong-foundations-will-define-the-era-of-agentic-ai): How do we take the incredible momentum of autonomous AI agents and scale it into reliable, enterprise-grade production? As businesses rush to deploy agentic workloads, the focus is rapidly shifting f… - [The Tool Abstraction Problem: Lessons Learned Building 1000+ MCP Tools](https://aaif.io/blog/the-tool-abstraction-problem): The Tool Abstraction Problem: Lessons Learned Building 1000+ MCP Tools - [Datadog's 5 Tips for Building AI Agents](https://aaif.io/blog/datadogs-5-tips-for-building-ai-agents): Getting an AI agent to work is a different problem from getting it to run in production without someone watching it. Datadog built its first hundred agents across SRE, code generation, and security i… - [MCP Is Growing Up](https://aaif.io/blog/mcp-is-growing-up): The 2026-07-28 release candidate makes MCP easier to run, reason about, and extend in agentic systems. - [We're Building a Squad of Agentic AI Advocates: Join the AAIF Ambassador Program](https://aaif.io/blog/were-building-a-squad-of-agentic-ai-advocates-join-the-aaif-ambassador-program): Angie Jones VP of Developer Experience, Agentic AI Foundation - [Building Trust Into the Protocol: Bloomberg's MCP Contributions](https://aaif.io/blog/building-trust-into-the-protocol-bloombergs-mcp-contributions): A deep dive into Ania Musial’s talk at MCP Dev Summit North America 2026 - [Welcome to AAIF: The MLOps Community Finds Its New Home](https://aaif.io/blog/mlops-community-joins-aaif): I'm thrilled to welcome the MLOps Community into the Agentic AI Foundation (AAIF) as our user community. - [100 Tools Down to 3: Prime Video's Approach to Progressive Tool Discovery](https://aaif.io/blog/prime-videos-approach-to-progressive-tool-discovery): Explore how Prime Video's approach simplifies tool discovery, reducing hundreds of options down to three key tools. - [MCP Was Designed for the Cloud. The Edge Has Different Rules.](https://aaif.io/blog/mcp-was-designed-for-the-cloud-the-edge-has-different-rules): Almost all of MCP's current adoption is happening in cloud environments, on large models with generous compute budgets.Manufacturing floors, medical devices, vehicles, smartphones,are where the next… - [Are MCP and CLIs Competing?](https://aaif.io/blog/are-mcp-and-clis-competing): Nick Cooper, Member of Technical Staff at OpenAI and a contributor to the MCP ecosystem, shared that he'd been thinking about this debate for a year, but stopped short of picking a side: "As for whet… - [How Uber Runs 60,000 AI Agent Tasks Per Week With MCP](https://aaif.io/blog/how-uber-runs-60000-ai-agent-tasks-per-week-with-mcp): A deep dive into Meghana Somasundara and Rush Tehrani’s talk at MCP Dev Summit North America 2026 - [Stateless: The Future of MCP Transports](https://aaif.io/blog/stateless-the-future-of-mcp-transports): The operational scale of MCP is significant: Google Cloud maintains the reliability for its MCP servers supporting AlloyDB, Spanner, Cloud SQL, Bigtable, and Firestore. The team's open source MCP Too… - [The Missing Layer in AI Interoperability: Discovery](https://aaif.io/blog/the-missing-layer-in-ai-interoperability-discovery): As we integrate AI into more workflows, a common question is: how do AI systems find each other and related artifacts? AI Catalog addresses this by providing a shared, trusted discovery layer that gi… - [Your MCP Server Works. Your Agent Doesn't. Here's Why.](https://aaif.io/blog/your-mcp-server-works-your-agent-doesnt-heres-why): Red Hat engineers Wesley Chun and Calum Murray opened with a problem that a lot of MCP server builders have already run into: your code passes every test, the agent still fails, and you have no idea… - [Anthropic's Lessons from Building MCP Apps](https://aaif.io/blog/anthropics-lessons-from-building-mcp-apps): MCP Apps exist because displaying data in chat is wasteful. Take the case of a simple request like “What’s the weather today in New York?” When a user asks for it, the model gets JSON from the tool,… - [How to Submit your Project to the AAIF](https://aaif.io/blog/how-to-submit-your-project-to-the-aaif): Do you have an open source project? Submit your project to the AAIF for a chance to collaborate with leading tech companies. - [The Four Pillars of Agentic AI Infrastructure on Kubernetes](https://aaif.io/blog/agentic-ai-infrastructure-on-kubernetes): Explore Agentic AI Infrastructure Kubernetes and how it revolutionizes software engineering standards for the future. - [Stripe on Agentic Commerce: Trends from 2026](https://aaif.io/blog/five-lessons-stripe-sessions-on-agentic-commerce): Explore Stripe On Agentic Commerce and its impact on the future of payments. Insights from Stripe Sessions 2026. - [Closing the Context Gap: Why MCP + Skills Works](https://aaif.io/blog/closing-the-context-gap-why-mcp-skills-works): At the MCP Dev Summit 2026, Pedro Rodrigues, AI Tooling Engineer at Supabase, challenged a growing rift in the developer community. "People keep asking if they should build an MCP server or use Agent… - [Use agentgateway to Mediate MCP and LLM Traffic at Solo.io](https://aaif.io/blog/use-agentgateway-to-mediate-mcp-and-llm-traffic-at-solo-io): Lin Sun Head of Open Source, Solo.io Lin is Head of Open Source at Solo.io and co-chair of KubeCon + CloudNativeCon 2026. She is an active contributor to AAIF working... - [How Duolingo Built an AI Slackbot With 180+ MCP Tools](https://aaif.io/blog/how-duolingo-built-an-ai-slackbot-with-180-mcp-tools): At the MCP Dev Summit, Aaron Wang, a software engineer at Duolingo, shared how the company went from a handful of engineers experimenting with MCP, to 250 weekly active users (about 30% of the compan… - [Debugging the Hardest Parts of MCP with MCP Debugger](https://aaif.io/blog/debugging-the-hardest-parts-of-mcp-with-mcp-debugger): Nate Barbettini Nate is the Founding Engineer of Arcade.dev, currently building on the cutting edge of AI. 🤖 Over the past year, I’ve spent a lot of time in the... - [From Workflow Orchestration to Agentic Orchestration](https://aaif.io/blog/from-workflow-orchestration-to-agentic-orchestration): Yaron Schneider Yaron is the Co-Founder of Diagrid and Chair of the Workflow Working Group at the Agentic AI Foundation - [MCP Apps: Extending the Frontier](https://aaif.io/blog/mcp-apps-extending-the-frontier): A deep dive into the keynote by Ido Salomon & Liad Yosef at MCP Dev Summit North America 2026 - [Where New MCP Ideas Go to Become Real: Goose as a Proving Ground](https://aaif.io/blog/where-new-mcp-ideas-go-to-become-real-goose-as-a-proving-ground): Agentic AI Foundation A deep dive into Alex Hancock’s talk at MCP Dev Summit North America 2026 Alex Hancock opened his talk at MCP Dev Summit with a couple of... - [MCP Maintainer Roundtable: Control, Security, And Quality](https://aaif.io/blog/mcp-maintainer-roundtable-control-security-and-quality): Agentic AI Foundation At the MCP Dev Summit NA in New York on April 2–3, the Agentic AI Foundation brought together a roundtable with the MCP Project maintainers: Clare Liguori... - [MCP Is Now Enterprise Infrastructure: Everything That Happened at MCP Dev Summit North America 2026](https://aaif.io/blog/mcp-is-now-enterprise-infrastructure-everything-that-happened-at-mcp-dev-summit-north-america-2026): Agentic AI Foundation New York City · Agentic AI Foundation & Linux Foundation The biggest ideas and sharpest insights from MCP Dev Summit North America: where the builders, contributors, and... - [Why I’m Joining the Agentic AI Foundation—Building the Foundation for the Internet of Agents](https://aaif.io/blog/why-im-joining-the-agentic-ai-foundation-building-the-foundation-for-the-internet-of-agents): Mazin Gilbert Mazin Gilbert is the Executive Director of the Agentic AI Foundation, part of the Linux Foundation. We are at a clear inflection point in AI. For the past... - [Building the Foundation for Agentic AI](https://aaif.io/blog/building-the-foundation-for-agentic-ai): Blog post from AAIF's VP of Developer Experience, Angie Jones. - [Coding Agents Are the Foundation for Every Agent You'll Ever Build](https://aaif.io/blog/coding-agents-are-the-foundation-for-every-agent-youll-ever-build): Sam Partee Co-founder and Head of AI Research By Sam Partee, Co-founder & Head of AI Research, Arcade.dev, based on his joint talk with Harrison Chase (LangChain) at the Coding... - [AAIF's First Quarter Success Story: New Members, Technical Wins, and Open Governance](https://aaif.io/blog/aaifs-first-quarter-success-story-new-members-technical-wins-and-open-governance): David Nalley, AAIF Governing Board chair and Director of Developer Experience at Amazon Web Services ## Press & News - [AGNTCon + MCPCon Japan to Convene Builders Advancing Production-Ready Agentic AI](https://aaif.io/news/agntcon-mcpcon-japan-to-convene-builders-advancing-production-ready-agentic-ai): Industry leaders and open source innovators from SoftBank, Hitachi, NTT, Google, Microsoft, Anthropic, and more will gather in Tokyo to explore the standards, infrastructure, security and governance… - [AI Magazine: How Linux Foundation Unifies Open Standards for AI Agents](https://aaif.io/news/ai-magazine-linux-foundation-unifies-open-standards): Linux Foundation has launched Agentic AI Foundation (AAIF) co founded by OpenAI, Anthropic and Block to ensure open-source, transparent agentic AI tools - [Agentic AI Foundation Adds 43 New Members as Enterprise and Government Adoption of Open Agent Standards Accelerates](https://aaif.io/news/agentic-ai-foundation-adds-43-new-members): Financial services, infrastructure, security, and public sector organizations join AAIF’s growing community to help shape the standards behind production-grade agentic AI - [Agentic AI Foundation Announces Global 2026 Events Program Anchored by AGNTCon + MCPCon North America and Europe](https://aaif.io/news/agentic-ai-foundation-announces-global-2026-events-program): Agentic AI Foundation Expanded global schedule brings agentic AI ecosystem together across ten cities, with flagship AGNTCon + MCPCon events and regional MCP Dev Summits driving standards adoption… - [Agentic AI Foundation Launches MCPA Certification to Validate MCP Expertise](https://aaif.io/news/agentic-ai-foundation-launches-mcpa-certification): The first official certification for MCP validates builders’ understanding of MCP architecture, security, and implementation as adoption of the protocol grows. - [Agentic AI Foundation Unveils MCP Dev Summit North America 2026 Schedule](https://aaif.io/news/mcp-dev-summit-north-america-2026-schedule): Agentic AI Foundation New York City event will explore how open standards and shared infrastructure enable secure, scalable AI agents in production Summary The Agentic AI Foundation today announced… - [Agentic AI Foundation Welcomes 57 New Members, Gaining Major Financial Services Players and APAC Leaders](https://aaif.io/news/agentic-ai-foundation-welcomes-57-new-members): Alibaba, Visa, and Wells Fargo join as Gold Members as demand for open agentic AI infrastructure accelerates globally - [Agentic AI Foundation Welcomes 97 New Members As Demand for Open, Collaborative Agent Standardization Increases](https://aaif.io/news/aaif-welcomes-97-new-members): Agentic AI Foundation Agentic AI Foundation Welcomes 97 New Members As Demand for Open, Collaborative Agent Standardization Increases Industry leading organizations unite under neutral Foundation led… - [Agentic AI Foundation Welcomes the Gates Foundation to Help Expand the Benefits of Agentic AI Globally](https://aaif.io/news/agentic-ai-foundation-welcomes-the-gates-foundation): Collaboration will bring the needs of underserved communities into the open ecosystem shaping agentic AI - [Anthropic: Donating the Model Context Protocol and establishing the Agentic AI Foundation](https://aaif.io/news/anthropic-donating-mcp-aaif): Today, we’re donating the Model Context Protocol (MCP) to the Agentic AI Foundation (AAIF), a directed fund under the Linux Foundation, co-founded by Anthropic, Block and OpenAI, with support from… - [Block: Block, Anthropic, and OpenAI Launch the Agentic AI Foundation](https://aaif.io/news/block-anthropic-openai-launch-aaif): Today, the industry is making a pivotal choice. - [CIO Dive: Big tech takes steps to build open standards for agentic AI](https://aaif.io/news/cio-dive-big-tech-open-standards-agentic-ai): Anthropic said it will donate the Model Context Protocol to the Linux Foundation, a move that could ease AI agent interoperability and enterprise adoption. - [CIO: Tech heavyweights align on agentic AI standards, promising more choice for CIOs](https://aaif.io/news/cio-tech-heavyweights-align-on-agentic-ai-standards): The Agentic AI Foundation (AAIF), announced on Tuesday, aims to develop common protocols for how agents access data and interact with business systems, reflecting growing concern that today’s mix of… - [GitHub Blog: MCP joins the Linux Foundation: What this means for developers building the next era of AI tools and agents](https://aaif.io/news/github-blog-mcp-joins-linux-foundation): MCP joins the Linux Foundation: What this means for developers building the next era of AI tools and agents - [Google-backed agentic A2A protocol gets a new home](https://aaif.io/news/google-backed-agentic-a2a-protocol-gets-a-new-home): The Agent2Agent Protocol (A2A), a Google-created standard for AI agents to talk to one another, is moving to the Agentic AI Foundation, backers of the emerging standard told Axios. - [InfoWorld: Linux Foundation launches Agentic AI Foundation](https://aaif.io/news/infoworld-linux-foundation-launches-aaif): The Linux Foundation has announced the formation of the Agentic AI Foundation (AAIF), which is intended to provide a neutral, open foundation to ensure that agentic AI evolves transparently and… - [Linux Foundation Announces the Formation of the Agentic AI Foundation (AAIF), Anchored by New Project Contributions Including Model Context Protocol (MCP), goose and AGENTS.md](https://aaif.io/news/linux-foundation-announces-formation-of-aaif): Agentic AI Foundation With founding contributions from Anthropic, Block, and OpenAI, the AAIF unites cutting-edge technology and open source governance to shape the future of open and accessible AI... - [MCP just got its biggest update ever — here’s what changes for AI agents](https://aaif.io/news/mcp-just-got-its-biggest-update-ever-here-s-what-changes-for-ai-agents): The Model Context Protocol, the open standard that has quietly become the connective tissue between AI agents and the world's software, is getting its largest update since Anthropic released it… - [OpenAI: OpenAI co-founds the Agentic AI Foundation under the Linux Foundation](https://aaif.io/news/openai-co-founds-aaif): Today, OpenAI is co-founding the Agentic AI Foundation (AAIF)⁠(opens in a new window) under the Linux Foundation, alongside Anthropic and Block, and with the support of Google, Microsoft, AWS… - [SDTimes: Linux Foundation forms Agentic AI Foundation to be new home for MCP, goose, and AGENTS.md](https://aaif.io/news/sdtimes-aaif-new-home-mcp-goose-agents-md): SDTimes: Linux Foundation forms Agentic AI Foundation to be new home for MCP, goose, and AGENTS.md - [SiliconANGLE: Linux Foundation announces Agentic AI Foundation joined by Anthropic, OpenAI, Block](https://aaif.io/news/siliconangle-linux-foundation-announces-aaif): Linux Foundation announces AAIF alongside contributions from Anthropic, OpenAI, and Block to standardize agentic AI. - [TechCrunch: OpenAI, Anthropic and Block join new Linux Foundation effort to standardize the AI agent era](https://aaif.io/news/techcrunch-openai-anthropic-block-linux-foundation): As AI moves beyond chatbots and towards systems that can take actions, the Linux Foundation is launching a new group dedicated to keeping AI agents from splintering into a mess of incompatible… - [Techzine: Newly launched Agentic AI Foundation to take charge of MCP's future](https://aaif.io/news/techzine-aaif-takes-charge-of-mcp): The brand-new Agentic AI Foundation has been launched by the Linux Foundation. - [The New Stack: Anthropic Donates the MCP Protocol to the Agentic AI Foundation](https://aaif.io/news/newstack-anthropic-donates-mcp): Anthropic’s Model Context Protocol is only a year old, but has quickly become the default for large language models (LLMs) to access data, tools and services in agentic loops. - [VentureBeat: The Agentic AI Foundation offers shared specs for building, running, and scaling agents](https://aaif.io/news/venturebeat-aaif-shared-specs): The Linux Foundation, Anthropic, OpenAI, Block, and other companies in the AI space created the Agentic AI Foundation to help further standardize the evolution of open-source AI. - [Wired: OpenAI, Anthropic, and Block Are Teaming Up to Make AI Agents Play Nice](https://aaif.io/news/wired-openai-anthropic-block-ai-agents): American AI giants are backing a new effort to establish open standards for building agentic software and tools. ## Projects - [AGENTS.md](https://aaif.io/projects/agents-md) - [Agent Router](https://aaif.io/projects/agent-router): Agent Router is an open source AI gateway built on Envoy that connects applications to models and MCP tools while platform teams manage access, routing, and usage. - [Agent2Agent (A2A)](https://aaif.io/projects/agent2agent): Agent2Agent (A2A) is an open protocol that enables AI agents to communicate, collaborate, and securely exchange information and tasks across different platforms and frameworks. - [Model Context Protocol](https://aaif.io/projects/model-context-protocol) - [agentgateway](https://aaif.io/projects/agentgateway): agentgateway enables secure, scalable connections between AI agents, models, tools, and APIs across ecosystems. - [goose](https://aaif.io/projects/goose): An open source, extensible AI agent that goes beyond code suggestions. Install, execute, edit, and test with any LLM.