@agentscript-ai/linear
This package allows you to integrate your agents with Linear.
API Reference
LinearClient(options)
Creates a client for communicating with the Linear API.
Options
apiKey
(string, required): The API key for Linear
Example
import { LinearClient } from 'agentscript-ai/linear';
const linear = LinearClient({
apiKey: process.env.LINEAR_API_KEY,
});
searchIssues
Tool
The searchIssues tool is used to search for issues in Linear.
Options
llm
(LanguageModel, required): The configured language model to uselinear
(LinearClient, required): Linear client for making requests
Input
query
(unknown, required): Descriptive query in object format
Output
Array of Issue
objects
Example
import { AnthropicModel } from 'agentscript-ai/anthropic';
import { LinearClient, searchIssues } from 'agentscript-ai/linear';
import { defineTool, inferAgent, executeAgent } from 'agentscript-ai/core';
import * as s from 'agentscript-ai/schema';
const linear = LinearClient({
apiKey: process.env.LINEAR_API_KEY,
});
const llm = AnthropicModel({
model: 'claude-3-5-sonnet-latest',
apiKey: process.env.ANTHROPIC_API_KEY,
});
const tools = {
linear: {
searchIssues: searchIssues({ llm, linear }),
},
};
const prompt = 'Find all tasks created in last 3 days';
const output = s.array(s.object({props: {
id: s.string(),
url: s.string(),
title: s.string(),
description: s.string({ optional: true }),
status: s.string(),
createdAt: s.date(),
updatedAt: s.date()}}));
const agent = await inferAgent({
tools,
output,
llm,
prompt,
});
await executeAgent({agent})
console.log(agent.state?.output)
Types
Issue
The type of output from the searchIssues tool.
id
(string, required): Linear identifierurl
(string, required): URL to Linear issuetitle
(string, required): Title of the issuedescription
(string, optional): Description of the issuestatus
(string, required): Status of the issue, as displayed on the Linear appcreatedAt
(Date, required): Timestamp when the issue was createdupdatedAt
(Date, required): Timestamp when the issue was last updated