eve – build AI agents that you own

eve is an open-source agent framework for durable, long-running work. Build, govern, and evolve enterprise-grade agents that can scale.
Picked up a P1 bug and reproduced it in a sandbox.
Fixed, with tests. @Reviewer ready for review.
ReviewerAgent10:33 AM
The merge logic is right, but the security pass flagged one thing. @Coder
Good catch. The merge now checks the guest cart belongs to the signing-in session, with a test for it. Pushed.
ReviewerAgent10:41 AM
Verified the fix. Security pass is clean, approving.
Merged and closed the issue. It goes out with the next deploy.
Start from a working template, or build your own from scratch.
Build a Slack agent that answers your team's business questions from your documented dbt models.
Build an agent that turns issues into reviewed draft pull requests, from triage and planning to implementation.
Agents inside your product, over web, voice, or iMessage, with memory for every user.
@data-agent how are repeat orders trending this quarter?
data-agentAgent9:41 AM
Repeat customers placed 44% of orders in October, up from 38% in August.
Write your agent as plain files. When it needs to behave differently for each customer, make any file dynamic.
An instructions.md file is a complete agent. Describe its role in Markdown, then run eve.
Static in this example. Any file can be dynamic.
Add instructions that depend on the customer. Enterprise customers get a one-hour SLA, and Pro customers get a reply within a business day.
Choose the model per customer: a larger model for enterprise conversations.
Skills are Markdown playbooks loaded only when relevant, so the agent gets focused guidance without carrying it in every prompt.
Static in this example. Any file can be dynamic.
Drop a TypeScript file in tools/ and the model can call it. The filename becomes the tool name, no registration required.
Static in this example. Any file can be dynamic.
Let the agent page the on-call engineer, but only for enterprise customers.
Add channel files to answer customers in Slack, Discord, Teams, or the web with the same agent.
Static in this example. Any file can be dynamic.
Connections handle auth for services like Linear, GitHub, and Stripe, so the agent can file a bug for a support issue without managing tokens.
Static in this example. Any file can be dynamic.
Add subagents for specialized work. The support agent hands billing questions to a billing specialist and uses its answer.
Static in this example. Any file can be dynamic.
Give enterprise customers second-level support: a specialist the agent hands hard cases to.
Schedules run agents automatically for jobs like daily digests, continuing durably without an active session.
Static in this example. Any file can be dynamic.
Add instructions that depend on the customer. Enterprise customers get a one-hour SLA, and Pro customers get a reply within a business day.
Customize at every layer, from the harness to the UI to every agent run.
Start with great defaults. Turn off what you don't need, extend what you do. Scale from side project to enterprise.
Build rich agent UIs natively in Next.js, Nuxt, SvelteKit, and TanStack. Ship agent and app in one deploy.
Control where your agent runs and who can access it. Self-host with your own workflow storage, sandbox provider, and model routing.