Introducing eve 1.0 Vercel released eve 1.0, an open-source framework for building production-ready AI agents, making it generally available after a June public preview that produced more than 230 releases and thousands of merged pull requests. The 1.0 version adds security controls for action approvals and data collection, a Workflow SDK that saves agent progress so it can resume after a crash, built-in multiplayer sessions and agent-to-agent calls, and native channels including Slack, Microsoft Teams, Discord, Telegram, GitHub, Linear, Twilio, Web Chat and iMessage. Vercel said thousands of businesses already run eve in production, citing Rillet, which tripled its shipping rate in three months with a software factory built on eve, and Clay, whose data agent monty was used weekly by 30–40% of the company just over two months after launch. Today we're announcing eve 1.0 https://eve.dev , the open-source framework for building production-ready agents. Since the public preview in June https://vercel.com/blog/introducing-eve , we've worked with early adopters to prepare eve for 1.0, shipping 230+ releases and merging thousands of pull requests. With this release, eve is now generally available. We've made eve faster, expanded integrations, and improved observability. Security controls let you decide which actions need approval and what data gets collected. We've also made it easier for coding agents to build with, measuring that experience with a rigorous evaluation suite. With eve handling your harness and infrastructure, you and your agent can focus on building instead. The harness in eve is the loop that calls models, runs tools, and delegates work to subagents. You choose the model, add or replace tools, edit instructions, and decide which actions need approval. The open-source Workflow SDK https://workflow-sdk.dev/ saves progress as the agent runs, so it can pick up from its last completed step after a crash. Multiplayer sessions and agent-to-agent calls are built in. For managed hosting, deploy your eve agent to Vercel. Vercel Workflows https://vercel.com/workflows handles durable execution, and Vercel Sandbox https://vercel.com/sandbox runs agent-generated code in isolation. Build software factories that turn requests into tested pull requests, company brains that answer questions from your business data, or customer-facing agents in your product. Thousands of businesses already run eve in production for internal and customer-facing agents. Rillet https://vercel.com/customers/how-rillet-ships-3-faster-with-ai-agents-on-vercel built a software factory on eve that takes in customer requests, converts them into specs, tests the changes, and opens PRs for human review. Rillet tripled its shipping rate in three months. Clay https://www.clay.com/blog/building-everyones-personal-data-scientist built monty, a data agent that answers employees’ questions in Slack. Just over two months in, 30–40% of the company used it every week. Lindy https://www.lindy.ai/blog/ai-agent-frameworks 's agent framework roundup names eve “Best for durable backend agents”. Multiplayer lets several people work with an agent in one shared session. eve keeps track of who said what and directs approvals and sign-ins to the right person. You can set up memory for each user or the whole team. In the native Slack channel https://eve.dev/docs/channels/slack , each thread is one shared session. Approvals appear as buttons that only the right person can answer, and a live task card shows progress and timing. You can follow up in the thread without mentioning the agent again, cancel the current turn, or reset the session from Slack. Ambient mode https://eve.dev/docs/patterns/ambient-listening lets an agent listen in channels you choose, even without being mentioned. Guided by goals you set per channel, it decides when to speak up, help, or take on a task, and when to stay quiet. To limit model costs, a small decision model screens every message first, and only the ones that might be for the agent start a turn. Slack is one of several native channels, alongside Microsoft Teams, Discord, Telegram, GitHub, Linear, Twilio, Web Chat, and iMessage. The Chat SDK channel https://eve.dev/docs/channels/chat-sdk adds support for any Chat SDK platform adapter, including WhatsApp, Messenger, Google Chat, and email. Each channel is one file, and the same agent can work across all of them. See the integrations directory https://eve.dev/integrations?filter=channel for the full list. eve 1.0 expands our native integrations for Next.js, Nuxt, SvelteKit, TanStack Start, and Vite. The framework integrations https://eve.dev/docs/guides/frontend build your agent alongside your app and set up its routes. On Vercel, you can deploy the agent and your site as one project, or host them separately. The client libraries let you work with tool calls, approval requests, and questions in a consistent way across frameworks. Use that session data to build custom UIs: stream replies into agent chats, embed an agent in a page, or show the agent's tool calls in your own components. Use eve add channel/web to scaffold a chat app with AI Elements https://elements.ai-sdk.dev/ components, or add eve's React, Vue, or Svelte bindings to an existing UI. One support-agent deployment can connect to each customer's ticketing system with their own credentials and apply that customer's approval rules. Your application authenticates the user and identifies which tenant they belong to. You can then set memory https://eve.dev/docs/patterns/multi-tenant-memory , connection credentials https://eve.dev/docs/patterns/multi-tenant-auth , and approval policy https://eve.dev/docs/patterns/multi-tenant-approvals for that tenant and user. Before each model call in the main agent loop, dynamic definitions https://eve.dev/docs/guides/dynamic-capabilities load the agent's capabilities from the session and external data. In 1.0, they cover models, connections, and subagents as well as tools, skills, and instructions. We added native memory https://eve.dev/docs/memory so agents can carry context from one session to the next. You choose the memory's scope and can use the built-in file memory, a memory provider, or one you build yourself https://eve.dev/docs/memory/custom-provider . Built-in fileMemory keeps data in memory in eve dev and in a private Vercel Blob store https://vercel.com/docs/vercel-blob/private-storage you configure on Vercel. Other providers include claude-mem https://eve.dev/integrations/claude-mem , Hindsight https://eve.dev/integrations/hindsight , Kybernesis Arcana https://eve.dev/integrations/arcana , Memanto https://eve.dev/integrations/memanto , memco https://eve.dev/integrations/memco , Supermemory https://eve.dev/integrations/supermemory , and Upstash AgentKit https://eve.dev/integrations/upstash-agentkit . We rebuilt eve’s tracing around OpenTelemetry https://eve.dev/docs/observability/otel , so you can follow an agent’s work in the tracing tools you already use. eve dev records traces locally by default. If you host eve yourself, you can export them to an OpenTelemetry backend, including one you run yourself. Tracing integrations include Raindrop https://eve.dev/integrations/raindrop , with more options in the integrations directory https://eve.dev/integrations . Add one with eve add instrumentation/