Personal Agent Template
Deploy a durable personal AI agent with web chat, Slack, Linear, and memory.
Open-source template featuring persistent memory, web chat, Slack, and Linear integration.
This is an open-source template for launching a durable personal AI assistant powered by the Eve framework and Nuxt. It is built for developers and technical professionals who want a custom AI agent integrated directly into their workspace tools.
What it is
It connects an Eve agent runtime with a Nuxt web application, letting you chat via browser or Slack while maintaining a persistent profile memory. The agent mounts tools for GitHub and Linear through Vercel Connect, executing real actions rather than guessing from conversation history.
Who it's for
It suits developers and technical leads who want a self-hosted AI agent with real tool integrations. It does not suit non-technical users looking for a finished, no-code desktop application.
Key features
Persistent Web Chat
Chat in the browser with threads that resume across sessions and real-time tool execution.
Slack Integration
Interact with your agent via DMs and @mentions with context shared across channels.
Linear and GitHub Tools
Query issues, projects, pull requests, and CI workflows via Vercel Connect MCP.
Model-Maintained Memory
Store durable user facts in private Vercel Blob storage recalled before every agent turn.
Up and running in 3 steps
Our honest verdict
What's great
- Durable agent architecture separating the Nuxt web UI from the Eve runtime service
- Integrates directly with Slack, GitHub, and Linear using Vercel Connect
- Maintains bounded, model-maintained persistent memory via Vercel Blob storage
- Includes a morning briefing skill combining recalled memory and assigned Linear issues
Where it falls short
- Requires deploying and managing multiple services across Vercel and PostgreSQL
- Requires active Vercel integrations and Blob storage configuration for full functionality
- Built as a code template requiring manual customization rather than a ready-to-use app
Pricing & license
Free under the MIT license. The only cost is running your own infrastructure, database, and AI model API usage.
Open remote AI-training roles
870 open remote AI-training roles, updated November 14, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
What framework powers the agent runtime?
The template uses Eve, a durable agent framework.
Where does the agent store user memory?
User facts are stored as documents in private Vercel Blob storage using Eve's fileMemory provider.
