Most of the @speakeasydev has been together for multiple years now through cycles of growth and PMF iteration. Longevity >> team size.

We'll be at The @aiconference next week at Pier 48, San Francisco. Come find us on the floor. We'll be talking through how teams put identity, policy, and an audit trail on every agent action. We also have a shuffle board. See you there!

Promise its costs not our revenue 😂

Very happy we partnered with @speakeasydev on this, previous SDK vendor risk was very real for the ecosystem!

Open tooling builds stronger developer ecosystems. We teamed up with @speakeasydev to ship the new Google GenAI SDKs for our Interactions, Agents, and Webhooks APIs. Read why we believe SDK generation belongs in the open and explore Speakeasy's newly open-sourced OpenAPI generator suite: nitter.net/GoogleAIStudio/status/…

Working with the @GoogleAIStudio team has been a dream. We love working with companies that care about DX & AX as much as we do. We're just getting started, and can't wait to keep building alongside them!

Excited to share that we partnered with @speakeasydev to build the sdks for the Interactions API and supported them to open-source their their entire OpenAPI generator suite (SDKs, agent CLIs, and MCP servers) open source for the community to use: developers.googleblog.com/wh…

Today we're announcing our partnership with @googledevs, and open sourcing infrastructure for agent experience together 🤝 Every enterprise is coming to the realization that developer experience is no longer the whole story. Agents are rapidly becoming the users integrating with your systems, and they need infrastructure built for them: Discoverable interfaces, structured output, context they can query at runtime. Those are the foundations we've been building together. Google is future-proofing the Gemini APIs' integration experience so agents get the same first-class treatment developers do, and Speakeasy is the platform generating and governing the artifacts that make that possible. We've been building the Speakeasy AI Control Plane to provide enterprises the identity, policy enforcement, and observability over every agent connection. But before you implement control, you need robust connections. We've been working with the Google team to Open Source the primitives needed for agents to build those connections. The Speakeasy generator is now open source and includes everything you need to make your services consumable by agents: MCPs, CLIs, and SDKs speakeasy.com/blog/partnerin… github.com/speakeasy-api/ope…

Keeping all your MCP connections on your private and accessible only on your tailnet and off the public internet is a hard security boundary that’s tough to beat. If you want all your agent connections flowing through tailscale our MCP gateway has a dedicated integration @speakeasydev

An awesome resource if you're thinking about the practical limitations of rolling out @claudeai tag to you organisation such as managing access, tool permissions, tracking operators of the agent and getting it to work with your IDP.

Every use of Claude tag tracked, governed and authorised to access the right resources.

We worked hard for this.

AI agents get a lot more interesting once they can actually *do* things. At @lisbonaiweek, builders from @PaddleHQ, @alpic_ai, @speakeasydev and @DustHQ are sharing what they’ve learned building with agents in the wild: what shipped, what broke, and what they’d do differently. Grab your spot: luma.com/paddle-lisbon-ai

With DCR, any client could call itself anything. With CIMD, the name comes from a URL on the vendor's own domain, so the consent screen finally says who is really asking.

I am really conflicted working on something like our slack agent In some ways it’s really valuable to have your own “harness” - with scopes, approvals, workflows, custom UI. It’s a much cleaner and safer experience than just hitting an API / MCP But surprisingly it’s a lot of work with a lot of annoying details to get right. And part of me thinks that ultimately all “agent work” is just going to collapse into either a super harness like Claude/Codex or a company-specific agent I think ultimately this work we’re doing will be thrown away and the approval layer moved into something like @executorsh or @speakeasydev

Glad we all stuck with MCP and tool generation. Tool bloat, context management and discovery were always a client side problem. Only a matter of time before the industry aligned and it did!

New favorite marketing product!

This makes a lot of sense. For our own internal harness at @speakeasydev we got to the same place as Exo by making the harness tiny and handing the model a language instead of a tool menu. Kit has one compose call that runs a program that reads files, runs tests, edits, retries, and delegates in a single round trip. The primary driver of cost in agent loops is context re-sent per round trip, so a harness that lets the model collapse many steps into one turn is much more efficient. Kind of a bitter-lesson argument too: don't hand-encode plan modes, todo tools, and special-purpose tools. Let the model take control. github.com/speakeasy-api/kit