Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents.
| Date | Stars |
|---|---|
| 2026-07-31 | 1421 |
| 2026-08-06 | 1539 |
Today
+118 stars today
This week
— stars this week
This month
— stars this month
Momentum
532.0
growth rate 0.00%/day
English | [中文](./README.zh-CN.md) [](https://github.com/deer-flow/llm-space/actions/workflows/ci.yml) [](https://github.com/deer-flow/llm-space/releases) [](./package.json) [](./mise.toml) [](./LICENSE) --- # LLM Space 4 <a href="https://trendshift.io/repositories/83147?utm_source=trendshift-badge&utm_medium=badge&utm_campaign=badge-trendshift-83147" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/83147/daily?language=TypeScript" alt="deer-flow%2Fllm-space | Trendshift" width="250" height="55"/></a>  https://github.com/user-attachments/assets/2ba7a600-1f1a-44c0-b9f1-34ad42100213 [**LLM Space** v4](https://github.com/deer-flow/llm-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. **Official website:** https://deer-flow.github.io/llm-space/ LLM Space is a sister project of [DeerFlow](https://github.com/bytedance/deer-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. ## Contents - [Features](#features) - [Tech stack](#tech-stack) - [Project layout](#project-layout) - [Download](#download) - [Install](#install) - [Run the app](#run-the-app) - [User guide](#user-guide) - [Contributing](#contributing) - [Sponsors](#sponsors) - [Donate](#donate) - [License](#license) ## Features - **Build** — write and version your prompts, system messages, tools, and model settings. - **Trace** — see every model call and tool run inside the agent loop as it happens. - **Debug** — replay a run from history and step through it to find what went wrong. - **Evaluate** — measure how your agent performs across runs. - **Manage** — keep your threads organized as files on your own machine. - **Generate** — let AI write your prompt and tools for you, and even turn any thread into a runnable [LangGraph](https://github.com/langchain-ai/langgraph) agent. Your 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](./TELEMETRY.md) for exactly what is collected and how to opt out. ## Tech stack - **Language & tooling** — TypeScript, built and managed with [Bun](https://bun.com). - **Desktop shell** — [Electrobun](https://electrobun.dev), a lightweight way to ship a native app. - **UI** — React with Tailwind CSS and shadcn/ui. - **Agent framework** — [Pi Agent Core](https://github.com/earendil-works/pi), a lightweight agent framework for building agents. ## Project layout LLM Space is a Bun monorepo: ``` packages/ core/ # Shared logic: types, the agent loop, thread storage apps/ desktop/ # The desktop app (Electrobun shell + React UI) ``` ## Download Grab a DMG from the [latest release](https://github.com/deer-flow/llm-space/releases/latest) — macOS, Apple Silicon and Intel. It comes in two editions: - **LLM Space** — uses the system WebView. Small download (~27 MB), light on memory and battery. - **LLM Space Performance** — embeds its own rendering engine (~130 MB). Rendering stays consistent across macOS versions, and usually performs better. Install either, or both. They share the same `~/.llm-space` data, so switching editions keeps your threads and settings, and both update themselves in place. ## Install Building
Excerpt of 7,161 characters
Read on GitHub
Henry Li · ByteDance
442
48
Anx · @undefined
32
JeffJiang · ByteDance Inc. · China
28
18
DanielWalnut
15
4
3
2
2
天魔 · China
1
1
Octopus · Independent Developer · United States
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0fe33ff679966bd5, topic:llm