{"name":"AgentsKit: The Complete JavaScript Toolkit for Building AI Agents","description":"AgentsKit is a comprehensive JavaScript toolkit designed for building AI agents, offering a lightweight core and a modular ecosystem. It provides essential components like UIs, autonomous runtime, tools, memory, and RAG, enabling developers to create sophisticated agents from simple chat interfaces to complex autonomous systems. This framework aims to simplify agent development by offering composable parts and avoiding the need to glue multiple incompatible libraries together.","github":"https://github.com/AgentsKit-io/agentskit","url":"https://osrepos.com/repo/agentskit-io-agentskit","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/agentskit-io-agentskit","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/agentskit-io-agentskit.md","json":"https://osrepos.com/repo/agentskit-io-agentskit.json","topics":["agent-framework","ai-agents","typescript","javascript","llm","rag","react","ai-tools"],"keywords":["agent-framework","ai-agents","typescript","javascript","llm","rag","react","ai-tools"],"stars":null,"summary":"AgentsKit is a comprehensive JavaScript toolkit designed for building AI agents, offering a lightweight core and a modular ecosystem. It provides essential components like UIs, autonomous runtime, tools, memory, and RAG, enabling developers to create sophisticated agents from simple chat interfaces to complex autonomous systems. This framework aims to simplify agent development by offering composable parts and avoiding the need to glue multiple incompatible libraries together.","content":"## Introduction\n\nAgentsKit.js is presented as the definitive JavaScript toolkit for building AI agents. It offers a lightweight 10KB core, a modular architecture with 22 focused packages, and zero lock-in, ensuring flexibility and reusability. Designed to address the challenges of integrating disparate libraries, AgentsKit provides a cohesive ecosystem for developing everything from basic chat UIs to full-fledged autonomous agents.\n\n## Why Use AgentsKit and Key Benefits\n\nBuilding AI agents in JavaScript often involves combining multiple incompatible libraries, leading to complexity and reusability issues. AgentsKit solves this by offering a small, contracted, and composable solution. Its core benefits include a minimal 10KB gzipped core with zero runtime dependencies, first-class support for agent runtimes (ReAct, tools, skills, delegation, memory, RAG), and easy provider swapping. The ecosystem extends beyond just the package, featuring a [Registry](https://registry.agentskit.io){:target=\"_blank\"} for ready-to-use agents and a [Playbook](https://playbook.agentskit.io){:target=\"_blank\"} for best practices, enabling developers to build, evaluate, and operate agents efficiently. AgentsKit also provides UI surfaces for React and Terminal, making it versatile for various applications.\n\n## Installation\n\nTo get started with AgentsKit, you can install the core and runtime packages using npm:\n\nbash\nnpm install @agentskit/core @agentskit/runtime tsx\n\n\n## Examples\n\nHere's a quick start example to create your first agent without requiring an API key:\n\nts\nimport type { AdapterFactory } from '@agentskit/core'\nimport { createRuntime } from '@agentskit/runtime'\n\nconst localAdapter: AdapterFactory = {\n  createSource(request) {\n    const task = request.messages.at(-1)?.content ?? 'your task'\n\n    return {\n      async *stream() {\n        yield {\n          type: 'text' as const,\n          content: `Agent ready. I received: ${task}`,\n        }\n        yield { type: 'done' as const }\n      },\n      abort() {},\n    }\n  },\n}\n\nasync function main() {\n  const runtime = createRuntime({ adapter: localAdapter })\n  const result = await runtime.run('Plan my first production agent')\n  console.log(result.content)\n}\n\nvoid main()\n\n\nRun it with:\n\nbash\nnpx tsx agent.ts\n\n\nFor a more advanced autonomous agent with tools, AgentsKit simplifies the process significantly:\n\n**Before** (typical \"JS agent\" stack):\n\nts\n// Pick your favorite: LangChain, raw fetch, Vercel AI SDK + custom runtime,\n// MCP client + custom UI, manual ReAct loop, hand-rolled streaming...\n// Then wire memory. Then wire tools. Then wire delegation. Then debug.\n\n\n**After** (AgentsKit):\n\nts\nimport { createRuntime } from '@agentskit/runtime'\nimport { openai } from '@agentskit/adapters'\nimport { webSearch, filesystem } from '@agentskit/tools'\n\nconst runtime = createRuntime({\n  adapter: openai({ apiKey: KEY, model: 'gpt-4o' }),\n  tools: [webSearch(), ...filesystem({ basePath: './workspace' })],\n})\n\nconst result = await runtime.run('Research the top 3 AI frameworks and save a summary')\n\n\n## Links\n\n*   [GitHub Repository](https://github.com/AgentsKit-io/agentskit){:target=\"_blank\"}\n*   [Official Documentation](https://www.agentskit.io/docs){:target=\"_blank\"}\n*   [Discord Community](https://discord.gg/zx6z2p4jVb){:target=\"_blank\"}\n*   [Public Roadmap](https://github.com/orgs/AgentsKit-io/projects/1){:target=\"_blank\"}","metrics":{"detailViews":2,"githubClicks":1},"dates":{"published":null,"modified":"2026-09-19T23:27:57.000Z"}}