vercel-labs/personal-agent-template is an open-source template for deploying a personal AI agent with persistent conversations, Slack access, GitHub and Linear integrations, and user-scoped long-term memory. Individuals customize it to create an agent that works across web chat and connected services while preserving approved context between sessions. The catalogue instructions relate to configuring and using this personal-agent workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/vercel-labs/personal-agent-template/agents-mdgit clone --depth 1 https://github.com/vercel-labs/personal-agent-templateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/vercel-labs/personal-agent-template/agents-md)<a href="https://agentmods.dev/instructions/vercel-labs/personal-agent-template/agents-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/personal-agent-template/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00716 | $0.00716 |
| Opus 5 | $0.00358 | $0.00358 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
personal-agent-template AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal Agent Template
Durable personal AI assistant built with Eve and Nuxt.
Quick Reference
| Command | Description |
|---|---|
pnpm install |
Install dependencies |
pnpm dev |
Generate Nuxt types, then start Nuxt + Eve |
pnpm build |
Production build |
pnpm lint |
ESLint (pnpm lint:fix to autofix) |
pnpm typecheck |
TypeScript check — app/server/shared plus agent/ |
pnpm build:agent |
Build the Eve agent on its own |
pnpm auth:schema |
Regenerate the Better Auth Drizzle schema |
pnpm db:generate |
Regenerate the auth schema, then the Drizzle migration |
pnpm db:migrate |
Apply migrations |
Structure
personal-agent-template/
├── agent/ # Eve agent (channels, tools, skills, connections)
├── app/ # Nuxt UI (pages, components, composables)
├── server/ # Nitro API, Drizzle schema, server utils
├── shared/ # Cross-layer types and helpers
└── docs/ # Architecture, environment, customization
Documentation
- Architecture — System design, request flows, internal API
- Environment — Environment variables
- Customization — Rename agent, add tools, integrations
- README — Quick start and feature overview
Eve Framework
This project uses Eve with a Nuxt frontend (eve/nuxt module). Before writing agent code, read the relevant guide in node_modules/eve/docs/ — start with docs/README.md, which maps each task to its page.
nuxt typecheck does not cover agent/, and eve build bundles without typechecking. pnpm typecheck runs both halves; keep it that way when adding agent code.
Internal API Pattern
The Eve agent calls Nuxt over HTTP:
agent/lib/*-internal.ts → /api/internal/* → server/utils/*
Authenticated with Authorization: Bearer <INTERNAL_API_SECRET>. See server/utils/internal-api.ts.
Memory
The caller's account identity — name, timezone, locale, bio — is injected into
the session instructions by agent/instructions.ts,
read over the internal API. That is app data the Profile page owns, distinct
from the memory slot below, which holds what the agent chooses to remember.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +8 lines · +157 tokens per session 3a12d6d421f8
- 5d ago First seen · 64 lines · 559 tokens per session scan A 67a17ba2a4c7
personal-agent-template AGENTS.md is an instructions file published in the GitHub repository vercel-labs/personal-agent-template (462 stars, last pushed 2d ago), licensed MIT. It adds 716 tokens to every session, about $0.0036 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
macro CLAUDE.md
Claude Code instructions for macro-inc/macro, covering claude.md, architecture overview, key services, data storage and macrodb schema changes.
macro AGENTS.md
AGENTS.md instructions for macro-inc/macro, a project described as: Macro is a unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM — @-linked together with shared AI memory.
evlog AGENTS.md
AGENTS.md instructions for HugoRCD/evlog, covering evlog, commands, monorepo structure, conventions and code style: no slop.
agentconnect CLAUDE.md
Instructions for agentconnect-md/agentconnect, covering claude.md, what this is, monorepo (pnpm workspace, packages/), platform modules and comment style.
metabase copilot-instructions.md
Copilot instructions for metabase/metabase, covering metabase developer assistant instructions, code review standards, security critical issues, performance red flags and code quality essentials.
linearis AGENTS.md
AGENTS.md instructions for linearis-oss/linearis, covering agents.md, identity, audience, quick commands and commit rules.