Examples

Recipes

Short, focused GitHub agent snippets, selective approval, a reusable review agent, read-only exploration, toolpick, and evlog observability.

Apply a github-tools recipe to this project

Shorter than the full examples, these are single-file snippets for one specific technique. Each one reads GITHUB_TOKEN from the environment by default, swap in Vercel Connect if you're deploying on Vercel.

Triage incoming issues with selective approval

Approves destructive actions but lets comments through unattended:

triage-issues.ts

import { createGithubTools } from '@github-tools/sdk'
import { generateText } from 'ai'

const { text } = await generateText({
  model: 'anthropic/claude-sonnet-4.6',
  tools: createGithubTools({
    preset: 'issue-triage',
    requireApproval: {
      addIssueComment: false,
      closeIssue: true,
      createIssue: true,
    },
  }),
  prompt: `
    Read all issues labeled "needs-triage" on vercel-labs/github-tools.
    For each one, classify it as bug, feature, or question.
    Post a comment with the classification and a suggested next step.
  `,
})

See Configure approval per operation for the full risk table.

Build a reusable review agent

For behavior shared across multiple calls, use createGithubAgent once and call it repeatedly:

review-agent.ts

import { createGithubAgent } from '@github-tools/sdk'

const reviewer = createGithubAgent({
  model: 'anthropic/claude-sonnet-4.6',
  preset: 'code-review',
  system: `
    You review pull requests for code quality and security issues.
    Always cite specific file paths and line numbers.
    Never approve a PR that introduces console.log statements.
  `,
})

Explore a repository, read-only

A script with no write permissions at all, safe to run against any repo:

explore-repo.ts

import { createGithubTools } from '@github-tools/sdk'
import { streamText } from 'ai'

const result = streamText({
  model: 'anthropic/claude-sonnet-4.6',
  tools: createGithubTools({ preset: 'repo-explorer' }),
  prompt: 'Find all TypeScript files that export a function named "create" in vercel-labs/github-tools and explain what each one does.',
})

for await (const chunk of result.textStream) {
  process.stdout.write(chunk)
}

Run a maintainer workflow with full approval

Full write access, gated behind approval on every operation:

maintainer-workflow.ts

import { createGithubTools } from '@github-tools/sdk'
import { generateText } from 'ai'

const { text } = await generateText({
  model: 'anthropic/claude-sonnet-4.6',
  tools: createGithubTools({
    preset: 'maintainer',
    requireApproval: true,
  }),
  prompt: `
    Check if there are any stale issues (no activity for 30 days) on vercel-labs/github-tools.
    For each stale issue, post a comment asking the author for an update.
    If no response after the comment, close the issue with a polite message.
  `,
})

See the full eve version of this task for a standalone agent, schedule included.

Reduce tool context with toolpick

With all 53 tools visible on every step, tool definitions eat tokens. toolpick selects only the most relevant ones per step:

with-toolpick.ts

import { createGithubTools } from '@github-tools/sdk'
import { createToolIndex } from 'toolpick'
import { generateText } from 'ai'
import { openai } from '@ai-sdk/openai'

const tools = createGithubTools()
const index = createToolIndex(tools, {
  embeddingModel: openai.embeddingModel('text-embedding-3-small'),
})

const result = await generateText({
  model: openai('gpt-4o'),
  tools,
  prepareStep: index.prepareStep(),
  prompt: 'Check if the CI is passing on the main branch of vercel/ai.',
})

Each step, toolpick picks the best ~5 tools. All tools remain callable, only the visible set changes. Add a rerankerModel for maximum accuracy on ambiguous queries:

with-reranking.ts

const index = createToolIndex(tools, {
  embeddingModel: openai.embeddingModel('text-embedding-3-small'),
  rerankerModel: openai('gpt-4o-mini'),
})

See toolpick docs for caching, description enrichment, and model-driven discovery options.

Add AI observability with evlog

Wrap the model with evlog to log token usage, tool calls, cost, and timing for every agent turn:

with-evlog.ts

import { createGithubTools } from '@github-tools/sdk'
import { generateText } from 'ai'
import { createLogger } from 'evlog'
import { createAILogger } from 'evlog/ai'

const log = createLogger()
const ai = createAILogger(log, { toolInputs: { maxLength: 500 } })

const result = await generateText({
  model: ai.wrap('anthropic/claude-sonnet-4.6'),
  tools: createGithubTools({ preset: 'code-review' }),
  prompt: 'Review the latest PR on vercel-labs/github-tools.',
})

log.emit()

Choose the right pattern

Pattern	Entry point	Best for
One-shot generation	`generateText` + `createGithubTools`	scripts, CLI tools, batch jobs
Streaming	`streamText` + `createGithubTools`	chat UIs, interactive terminals
Reusable agent	`createGithubAgent`	multi-turn assistants, persistent bots
eve agent	`githubExtension` from `@github-tools/eve-extension`	standalone agents in 3 files, durable HITL approval (`once`, predicates)
Durable agent + streaming	`createDurableGithubAgent` + `"use workflow"`	hosted chat, crash-safe tool loops, Nuxt/Next APIs on Vercel
Platform bot	`createGithubTools` + Chat SDK + Workflow	GitHub/Slack/Discord bots with durable multi-turn sessions
Multi-agent	eve subagents or agent-as-tool	one entry point routing to preset-scoped specialists

See API Reference for the full type signatures and Tools Catalog for every available tool.

Edit this pageorReport an issue

Manager & sub-agents

A broadly-capable GitHub manager agent that delegates to specialist eve sub-agents, each scoped to one preset (code-review, issue-triage, release-manager), instead of one agent holding every tool.

Scope with Presets

Expose only the tools your workflow needs using presets.