[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-92775":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":16,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":20,"hasPages":20,"topics":22,"createdAt":10,"pushedAt":10,"updatedAt":30,"readmeContent":31,"aiSummary":32,"trendingCount":16,"starSnapshotCount":16,"syncStatus":33,"lastSyncTime":34,"discoverSource":35},92775,"llm-space","deer-flow\u002Fllm-space","deer-flow","A desktop app for agent builders — prototype your next agent ideas, inspect every step of your harness execution, debug failures, and evaluate performance, all in one place.","",null,"TypeScript",70,10,53,1,0,17,44.82,"MIT License",false,"main",[23,7,24,25,26,27,28,29],"agent","develop","electrobun","harness","llm","llm-tools","managed-agents","2026-07-22 04:02:07","English | [中文](.\u002FREADME.zh-CN.md)\n\n---\n\n# LLM Space 4\n\n![screenshot](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fe207bc62-4dab-4b13-a541-d176a8f96c40)\n\n[**LLM Space** v4](https:\u002F\u002Fgithub.com\u002Fdeer-flow\u002Fllm-space) is a desktop app for agent builders — prototype your next agent ideas, inspect every step of your harness execution, debug failures, and evaluate performance, all in one place.\n\nLLM Space is a sister project of [DeerFlow](https:\u002F\u002Fgithub.com\u002Fbytedance\u002Fdeer-flow), and we dogfood it heavily: every version of DeerFlow is built and debugged with LLM Space. The project started in March 2023, and v4 is its fourth major iteration.\n\n## Contents\n\n- [Features](#features)\n- [Tech stack](#tech-stack)\n- [Project layout](#project-layout)\n- [Install](#install)\n- [Run the app](#run-the-app)\n- [User guide](#user-guide)\n- [Contributing](#contributing)\n- [Sponsors](#sponsors)\n- [Donate](#donate)\n- [License](#license)\n\n## Features\n\n- **Build** — write and version your prompts, system messages, tools, and model settings.\n- **Trace** — see every model call and tool run inside the agent loop as it happens.\n- **Debug** — replay a run from history and step through it to find what went wrong.\n- **Evaluate** — measure how your agent performs across runs.\n- **Manage** — keep your threads organized as files on your own machine.\n\nYour files and API keys stay on your local computer. LLM Space collects a small amount of anonymous usage data to improve the app - see [TELEMETRY.md](.\u002FTELEMETRY.md) for exactly what is collected and how to opt out.\n\n## Tech stack\n\n- **Language & tooling** — TypeScript, built and managed with [Bun](https:\u002F\u002Fbun.com).\n- **Desktop shell** — [Electrobun](https:\u002F\u002Felectrobun.dev), a lightweight way to ship a native app.\n- **UI** — React with Tailwind CSS and shadcn\u002Fui.\n- **Agent framework** — [Pi Agent Core](https:\u002F\u002Fgithub.com\u002Fearendil-works\u002Fpi), a lightweight agent framework for building agents.\n\n## Project layout\n\nLLM Space is a Bun monorepo:\n\n```\npackages\u002F\n  core\u002F       # Shared logic: types, the agent loop, thread storage\napps\u002F\n  desktop\u002F    # The desktop app (Electrobun shell + React UI)\n```\n\n## Install\n\nYou need [Bun](https:\u002F\u002Fbun.com) first. Bun is a fast, all-in-one runtime and package manager for JavaScript — think of it as a drop-in replacement for Node.js and npm. Follow the [official install guide](https:\u002F\u002Fbun.com\u002Fdocs\u002Finstallation).\n\nOnce Bun is ready, install the project from the repo root:\n\n```bash\nbun install\n```\n\n## Run the app\n\nStart the desktop app for local development:\n\n```bash\nbun dev\n```\n\nBuild a canary release:\n\n```bash\nbun run build:canary\n```\n\n## User guide\n\nThe user guide lives in this repository:\n\n- [Quick start](.\u002Fdocs\u002Fget-started.md)\n- [User manual](.\u002Fdocs\u002Findex.md)\n- [Core concepts](.\u002Fdocs\u002Fcore-concepts.md)\n\n## Contributing\n\nFor now, we only merge pull requests from the [DeerFlow](https:\u002F\u002Fgithub.com\u002Fbytedance\u002Fdeer-flow) core team members.\n\nEveryone else is very welcome to help by [opening an issue](https:\u002F\u002Fgithub.com\u002Fdeer-flow\u002Fllm-space\u002Fissues) — bug reports, ideas, and feedback all make the project better.\n\n## Sponsors\n\nLLM Space is free and open source, and it stays that way thanks to our sponsors. We are proud and grateful to be backed by them.\n\n### 🏆 Platinum sponsor\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fsuperdesign.dev\" target=\"_blank\" rel=\"noopener\">\n    \u003Cimg src=\".\u002Fdocs\u002Fimages\u002Fsponsor-superdesign.svg\" alt=\"Superdesign - AI product design agent that turns prompts into designs on an infinite canvas (Platinum Sponsor)\" width=\"600\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cstrong>\u003Ca href=\"https:\u002F\u002Fsuperdesign.dev\">Superdesign\u003C\u002Fa>\u003C\u002Fstrong> is an AI product design agent that turns natural-language prompts into UI mockups, components, and full designs on an infinite canvas. Thank you for making LLM Space possible. 💜\n\u003C\u002Fp>\n\nWant to see your logo here? We would love to talk - [reach out by opening an issue](https:\u002F\u002Fgithub.com\u002Fdeer-flow\u002Fllm-space\u002Fissues) or [support the project](#donate).\n\n## Donate\n\nIf LLM Space is useful to you and you would like to support its development, you can donate here:\n\n**[Support LLM Space →](https:\u002F\u002Fmy.feishu.cn\u002Fwiki\u002FOvLBwVuSkiCR1ik5wGEcBXZfnye)**\n\nThank you.\n\n## License\n\nLLM Space is released under the [MIT License](LICENSE).\n","LLM Space 是一款面向 LLM 智能体开发者的本地桌面应用，用于快速构建、可视化追踪、交互式调试和性能评估智能体运行全流程。核心功能包括：提示词与工具配置管理、实时 agent 执行链路追踪（含模型调用与工具执行）、历史回放与单步调试、跨会话性能指标对比，所有数据与 API 密钥均保留在用户本地。基于 TypeScript 和 Bun 构建，采用 Electrobun 封装桌面壳，集成 Pi Agent Core 轻量级 agent 框架，适合个人开发者及小团队在本地高效迭代 LLM 智能体原型与生产前验证。",2,"2026-07-10 02:30:25","CREATED_QUERY"]