GCWing/BitFun
BitFun combines a high-performance agent runtime written in Rust with a polished desktop application. It pairs the depth of a Code Agent with open, general-purpose capabilities for work beyond software development.
安装Install
dsh plugin --profile web add github:GCWing/BitFun把 GCWing/BitFun 加入你的 DSH 配置（web profile）即可启用。
READMEREADME
English 中文
A desktop AI agent that turns every task into an app you can open
Writes code, produces documents, and drives the desktop — with Mini Apps, a Rust runtime, and a self-hostable device-sync server.
⬇ Download for macOS · Windows · Linux · Verify downloads
Website · Quick start · Security · Discussions · Contributing
Key features
| Feature | What it does |
|---|---|
| Agentic Mini Apps | A task gets its own interface — chart, board, form, panel — with a conversation bound to that interface's live state |
| Self-hosted multi-device control | Login, cross-device session sync, and controlling one device from another run through a relay you deploy. Zero-knowledge; no vendor cloud in the path |
| Coding | Plan, edit, test, and commit inside real Git repositories. Agentic, Plan, Debug, Deep Review, long-horizon tasks |
| Office work | Research, writing, presentations, meeting notes, reports |
| Desktop execution | Browser, terminal, desktop applications, the filesystem, and remote workspaces |
| Four tiers of customization | Custom Agents → MCP / Skills / Hooks → Mini Apps → source-level changes |
| Performance | 98.67% average KV cache hit rate; flashgrep searches Chromium-scale trees ~36x faster |
| Cross-platform and model-agnostic | Windows, macOS, and Linux. You choose what it runs on |
Why BitFun
Agentic Mini Apps. Most agents push every task through the same chat box. BitFun builds the task its own interface instead — a chart, a board, a form, a panel — and binds a conversation to that interface's live state. You ask about what is on screen rather than re-describing it. Community builds already range from market dashboards to domain-specific tools.
Browse the public Mini Apps gallery →
Self-hosted multi-device control. Account login, cross-device session and settings sync, and controlling one signed-in device from another all run through a relay you deploy. Nothing is brokered by a vendor's cloud — the distinction that decides whether this is allowed inside a company network at all. The relay is zero-knowledge: clients derive keys locally, and the server only ever holds Argon2id hashes and AES-GCM-wrapped material.
A runtime you can reshape. Four continuous tiers, from a single Markdown file to forking the runtime: custom Agents → MCP / Skills / Codex-compatible Hooks → Mini Apps → source-level changes. You extend BitFun using BitFun.
KV cache that actually hits. Agent cost is dominated not by generated tokens but by context re-sent every turn, and a single timestamp or reordered tool list invalidates the cache from that byte onward. Prompt assembly is byte-stable across turns: 98.67% average cache hit rate over a SWE-Bench-Pro run.
flashgrep. An agent re-searches the same repository dozens to hundreds of times per task, and cold traversal on every tool call can cost more than inference itself. A resident cross-turn index cuts search time by up to 94.6% on Chromium-scale trees — roughly 36x on average.
Install
Download a build — grab the latest installer from Releases, install it, configure your model, and you are ready to go.
Or run from source:
pnpm install
pnpm run desktop:dev
Prerequisites: Node.js 22.12+ (LTS recommended), pnpm 10.15.0 via Corepack, the Rust toolchain, and the Tauri prerequisites. More detail in CONTRIBUTING.md.
First run
- Launch BitFun, click Open on the Welcome tab, and choose a project folder.
- Open More options (…) → Settings → Models → Create First Configuration.
- Choose a provider, enter its API key, select one or more models, and click Save. BitFun makes the first saved model primary and tests the connection automatically.
- Return to the Session tab, type a concrete task, and press Enter or click Send.
What you can hand to BitFun
Two kinds of complex work: shipping code in real repositories, and turning source material into office deliverables. When a task needs the browser, desktop apps, the terminal, or a remote environment, BitFun can enter the real workspace.
| Scenario | Delivery goal | Typical capabilities |
|---|---|---|
| Coding | Move from a real repository to a mergeable result. | Agentic, Plan, Debug, testing, Git, Deep Review, long-horizon tasks, and benchmarks. |
| Office Work | Move from source material to useful written and visual deliverables. | Research, presentations, summarization, writing, meeting notes, and reports. |
Shared capabilities
- Interface layer: Mini Apps give a task its own UI, with the conversation bound to that UI's live state.
- Execution layer: the filesystem, terminals, Git, browser operation, desktop applications, Computer Use, and remote workspaces let the Agent reach the real environment when a task leaves the editor.
- Customization layer: MCP, Skills, Hooks, custom Agents, and source-level extension let BitFun keep growing around your tools, roles, and interfaces.
Agent core metrics
The data below evaluates BitFun's core Agent capabilities, all measured with Deepseek-V4-Pro.
[!NOTE] These are BitFun's initial evaluation results, with each case run once. Benchmarks fluctuate with task sampling, model versions, runtime environment, and single-run variance, so treat these as an initial sanity signal that the Agent is already reasonably capable — not as a fixed ranking claim or a final ceiling. Full benchmark details will follow.
1. Initial completion snapshot — The chart below compares the current single-run results on SWE-Bench-Pro (complex software engineering) and SWE-Bench-Verified (human-verified GitHub issue fixes).
Benchmark references: SWE-Bench-Pro / SWE-Bench-Verified
2. Token economy — Agent economy needs to be evaluated across end-to-end token consumption, execution time, and KV Cache reuse. From the same SWE-Bench-Pro round, BitFun's average KV Cache hit rate was 98.67%. The follow-up report will add broader cost and latency metrics.
3. Context retrieval at scale — Agent experience also depends on how quickly it retrieves context in very large projects. On tens-of-millions-line repositories such as Chromium, BitFun uses flashgrep to cut search time by up to 94.6%, averaging a 36.1x speedup.
Customize your BitFun
BitFun's extension paths progress continuously from light to deep customization:
| Tier | Path | Best for |
|---|---|---|
| L1 | Custom Agent | Defining roles, flows, constraints, and tool bundles. |
| L2 | MCP / Skills / Hooks | Connecting external tools and professional capabilities, and running your own commands at Agent lifecycle points — fully Codex-hook compatible, so existing hook scripts work as-is. |
| L3 | Mini App | Generating dedicated interfaces, forms, panels, or visualizations for tasks. |
| L4 | Source-level customization | Changing tools, adapters, UI, Runtime, or product shape. |
You can use BitFun's Code Agent to extend BitFun itself.
Where this is going
- Lights-Out Factory (in progress): Design during the day, let tasks flow to the server and run through the night, then review the results in the morning.
- Infinite Radius (in progress): Extending from desktop and browser to mobile, wearables, and more devices, so work stays accessible and continuous.
- App Evolution: Build tailored workflows with custom Agents, MCP, Skills, Mini Apps, or source-level customization. Community contributors have already created specialized versions for short-form drama, media, and more.
- Better, Faster, Cheaper: Pursue greater efficiency, better results, and lower cost.
- Ultimate Desktop: Continuously refine an easier-to-use, more capable, and more beautiful desktop experience.
Community & contributing
Questions, ideas, and bug reports are all welcome in Discussions and Issues.
Stars, Issues, and PRs are welcome. We especially care about:
- Code Agent, Deep Review, debugging, and long-task execution capabilities
- Cowork, research, document, and desktop workflows
- MCP, Skills, Mini App, LSP plugins, and new domain Agents
- Runtime stability, performance, context efficiency, and verifiability
Please submit PRs directly to the main branch. For more details, see CONTRIBUTING.md.
Disclaimer
- This project is spare-time exploration and research into next-generation human-machine collaboration, not a commercial profit-making project.
- AI-assisted development is part of this project's workflow. Contributions are reviewed as code, and AI-assisted PRs should disclose their testing level; see CONTRIBUTING.md.
- This project depends on and references many open-source projects. Thanks to all open-source authors. If your rights are affected, please contact us for remediation.
相关推荐Related
-
nexu-io/open-design
🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your…
-
esengine/DeepSeek-Reasonix
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
-
Molunerfinn/PicGo
:rocket: The Ultimate Image Uploader for Efficient Creators. Supports Obsidian, Typora, VS Code etc. and 60+ image hosti…
-
titanwings/colleague-skill
将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital …
-
anywhere-labs/deepseek-harness-desktop
为 DeepSeek Harness (DSH) 插件生态打造的现代化桌面端解决方案。万物皆「插件」，桌面本身也是「插件」。
-
tt-a1i/archify
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained…
-
YaoApp/yao
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop,…
-
Q00/ouroboros
Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make i…