cc-pocket

作者 heypandax已验证

Drive Claude Code or OpenAI Codex from your phone — resume sessions, stream output, approve tool permissions remotely. End-to-end encrypted, zero-knowledge relay, open source.

54
Stars
4
Forks
Kotlin
语言
2026/8/24
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/heypandax/cc-pocket

快速入门

使用 cc-pocket 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

CC Pocket

CI Latest release License: MIT

English | 简体中文

Your coding agents stay on your computer. You stay in control from anywhere.

CC Pocket is an open-source, local-first control plane for command-line coding agents. The agent keeps running on your own machine, against your own checkout; from a phone, a tablet or another computer you watch it work, answer the permission prompts that block it, continue the same session, and read what it changed. Traffic is end-to-end encrypted and passes through a zero-knowledge relay that only ever forwards ciphertext — no CC Pocket account, no content logging. Clean-room Kotlin, MIT.

v1.9.0 drives six agent backends — Claude Code, OpenAI Codex, OpenCode, Kimi Code (Preview), ZCode and DeepSeek. They are not equivalent: see the capability matrix before you pick one.

🌐 Website · 📖 User manual · 💬 Support, no sign-in · 📦 Latest release

CC Pocket: the desktop console showing paired machines and a live session, beside the phone app showing a session list and an approval decision.

Real product UI with scripted demo data — regenerate with bash marketing/site/generate-assets.sh. Provenance: site/assets/product/manifest.json.

Quick start

1 · Get the appApp Store (iPhone · iPad) · TestFlight beta · Android APK. Prefer a computer? See the Desktop app.

2 · Install the daemon on the machine that runs your agent CLI — any supported one, not Claude specifically:

curl -fsSL https://raw.githubusercontent.com/heypandax/cc-pocket/main/scripts/install.sh | bash   # macOS · Linux
irm https://raw.githubusercontent.com/heypandax/cc-pocket/main/scripts/install.ps1 | iex          # Windows

3 · Pair — run cc-pocket-daemon pair, then scan the QR it prints (or type the 6-digit code) in the app. You are connected end-to-end.

Package managers, mirrors, updates and per-platform notes: Install details.

The four jobs

JobWhat you get
01WatchStreaming output, tool events with timing, sub-agent cards and background-task state, across devices. Filter projects, sessions and usage by agent.
02ApproveA permission request reaches your phone the moment the agent raises one. Allow or deny in seconds; no answer times out to a safe deny.
03ContinueTake a running session over in place instead of forking it, start a new task straight from the phone or the desktop app, and get missed output backfilled after a reconnect.
04InspectChanged files with line-level diffs, file preview, context and usage. Images in your own prompts stay visible in replay.

Capability differs by backend — the matrix below is the source of truth.

Agent support

Public capability claims for v1.9.0, audited against commit ec957f2b on main. Machine-readable copy: site/public-capabilities.json.

AgentCore sessionApproval & modeChanges & diffUsage
Claude Code✓ Yes✓ Yes✓ Yes✓ Yes
OpenAI Codex✓ Yes✓ Yes✓ Yes✓ Yes
OpenCode✓ Yes✕ No — always Full access✕ No✓ Yes
Kimi Code Preview✓ Yes✓ Yes✕ No✓ Yes · new in v1.8.0
ZCode✓ Yes✓ Yes✕ No✓ Yes · new in v1.8.0
DeepSeek Harness narrow v1✓ Yes✓ Yes✕ No✕ No
  • Core session means discover, replay, create, resume, send and receive text, and live streaming. Every backend does all of it.
  • OpenCode has no enforceable interactive approval. opencode run has no approval protocol, so those sessions run at Full access and the app says so up front instead of offering modes it cannot enforce.
  • Kimi Code is Preview. DeepSeek is supported, but narrow: approvals and multiple-choice questions are bridged to the app, but the sandbox mode is fixed at launch (changing it relaunches the session), and there is no Changed-files/diff view, no usage accounting and no model switching.
  • DeepSeek Harness has no timeout of its own. Left alone, an unanswered approval or question blocks its turn indefinitely — it does not deny. CC Pocket puts the request on the daemon's normal approval window instead: an approval that expires is answered reject, and a question that expires is answered skipped, so an unanswered request ends the wait rather than hanging it. DeepSeek also has no "always allow" — every request is a one-off decision.
  • Boundaries follow the release. Full detail: Features and the User manual.

Architecture & trust boundary

flowchart LR
    app["📱🖥️ CC Pocket app<br/>(phone · tablet · desktop)"] -- "wss · ciphertext" --> relay["relay<br/>(zero-knowledge broker)"]
    relay -- "wss · ciphertext" --> daemon["local daemon<br/>(your computer)"]
    daemon -- "stdio" --> agent["agent CLI<br/>(claude · codex · opencode · kimi · zcode · DeepSeek)"]

The daemon runs on your computer, drives the agent CLI as a subprocess and dials out to the relay — no inbound ports to open. The relay pairs your devices and routes opaque encrypted frames; it holds no message content and no private keys. The app and the daemon run an end-to-end session (P-256 ECDH + HKDF + AES-256-GCM, an X3DH/Noise-style handshake), so plaintext never leaves the two trusted endpoints. On the same network the app connects to the daemon directly for lower latency; the relay stays as the from-anywhere fallback. Pairings expire and can be revoked.

Honest limits: the agent still executes with your own operating-system permissions — end-to-end encryption is not a sandbox. OpenCode sessions have no enforceable interactive approval. The custom Noise-style channel has not had an independent third-party audit. Threat model: docs/SECURITY.md. Report vulnerabilities privately via GitHub security advisories.

Platforms & distribution

SurfaceOfficial packages
Phone / tablet appiOS · iPadOS (App Store, TestFlight) · Android APK
Desktop appmacOS Apple Silicon · Intel (signed .dmg) · Windows x86_64 .msi. No official Linux desktop package — build from source.
Local daemonmacOS Apple Silicon · macOS Intel · Linux x86_64 · Linux arm64 · Windows x86_64
HarmonyOSSigned HAP, Preview — limited capability
RelayHosted zero-knowledge relay by default; self-hosting supported

The desktop app and the local daemon are different packages: the app is a client, the daemon is what actually runs the agent.

Install details

macOS — signed & notarized
curl -fsSL https://raw.githubusercontent.com/heypandax/cc-pocket/main/scripts/install.sh | bash
cc-pocket-daemon pair

Verifies the download against the release's SHA256SUMS, installs under ~/.local (one directory per version), and registers the launchd service so it runs on login and reconnects itself. Homebrew: brew install --cask heypandax/tap/cc-pocket (use the full name; an unrelated cask is also called cc-pocket).

Linux — x86_64 / arm64 daemon
curl -fsSL https://raw.githubusercontent.com/heypandax/cc-pocket/main/scripts/install.sh | bash
cc-pocket-daemon pair

Pulls a self-contained tarball (bundled JRE, no system Java), installs under ~/.local and registers a systemd --user service. Voice transcription uses ffmpeg instead of macOS's afconvert. There is no official Linux desktop app package — build it from source.

Windows — x86_64
irm https://raw.githubusercontent.com/heypandax/cc-pocket/main/scripts/install.ps1 | iex

One command: installs, registers a logon Scheduled Task, and drops straight into pairing. Scoop: scoop bucket add heypandax https://github.com/heypandax/scoop-bucket then scoop install cc-pocket-daemon.

Mainland China mirror

GitHub downloads crawl there, so the installer and release artifacts are mirrored on the relay: curl -fsSL https://pocket.ark-nexus.cc/dl/install.sh | bash (Windows: irm https://pocket.ark-nexus.cc/dl/install.ps1 | iex). Same script, checksum-verified, with automatic fallback to GitHub. The daemon's self-update uses the mirror too.

Updating

cc-pocket-daemon version reports what is running, how it was installed, and the single command that updates this install — offline, and whether or not the daemon is up. The app shows the same under Settings ▸ Versions.

A daemon installed by the one-liner keeps itself current: it checks daily and applies the update in the background. Turn that off with cc-pocket-daemon config --auto-update off and you get a phone notification instead. Homebrew, Scoop and Windows installs never self-apply — update them through their own package manager (brew upgrade --cask heypandax/tap/cc-pocket, scoop update cc-pocket-daemon). The desktop app states it plainly when an update check fails, rather than showing "up to date".

Works with third-party gateways

If you route Claude Code through an LLM gateway or API relay (ANTHROPIC_BASE_URL), the official Remote Control is disabled as of v2.1.196 — it requires talking to api.anthropic.com directly. CC Pocket drives the CLI over stdio on your machine, so the endpoint does not matter. The daemon detects a gateway ANTHROPIC_BASE_URL and the model picker leads with one-tap presets for common vendor ids (DeepSeek, GLM, Kimi, Qwen, MiniMax) alongside a free-form custom id field. Which model an id actually reaches is decided by your gateway.

Build from source

ModuleWhatStack
:protocolShared wire protocol (pocket/* frames) — single source of truthKotlin Multiplatform + kotlinx.serialization
:daemonRuns on your computer; drives the agent CLI as a subprocess, dials out to the relayKotlin/JVM + Ktor
:relayCloud broker: device-key pairing, ciphertext routing, multi-tenant, rate-limitedKotlin/JVM + Ktor + SQLite
:mobileThe CC Pocket appCompose Multiplatform — Android · iOS · desktop

Requires JDK 17 (any distribution — the Gradle toolchain downloads one if yours differs), the Android SDK (ANDROID_HOME or local.properties; the Android modules are configured even for JVM-only tasks), and at least one installed, logged-in agent CLI. To build the mobile app, copy the committed Firebase placeholder once (a real Firebase project is only needed for push/analytics):

cp mobile/composeApp/google-services.json.template mobile/composeApp/google-services.json

Local single-machine (no relay), for development:

./gradlew :protocol:check                         # protocol contract test
./gradlew :daemon:run --args="run"                # daemon — local WebSocket on 127.0.0.1:8765
./gradlew :daemon:run --args="test-client"        # drive it against a real agent CLI

Through the relay (off-LAN), the real product path:

./gradlew :daemon:installDist
daemon/build/install/cc-pocket-daemon/bin/cc-pocket-daemon run --relay wss://<your-relay>
daemon/build/install/cc-pocket-daemon/bin/cc-pocket-daemon pair    # in another terminal

Build the app: Android via ./gradlew :mobile:composeApp:assembleDebug; iOS via iosApp/iosApp.xcodeproj (Xcode — first copy iosApp/iosApp/GoogleService-Info.plist.template to GoogleService-Info.plist next to it). Desktop (including Linux) via ./gradlew :mobile:composeApp:packageDistributionForCurrentOS. On-device iOS install: docs/ios-device.md.

Docs

Contributing

Issues and PRs welcome — CONTRIBUTING.md covers build prerequisites, test entry points, and which scripts are maintainer-only. Please report security issues privately via GitHub security advisories.

License

MIT — see LICENSE.

常见问题

What is cc-pocket?

cc-pocket is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by heypandax. Drive Claude Code or OpenAI Codex from your phone — resume sessions, stream output, approve tool permissions remotely. End-to-end encrypted, zero-knowledge relay, open source. It has 54 GitHub stars.

Is cc-pocket safe to use?

Yes. cc-pocket passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install cc-pocket?

Clone the repository with "git clone https://github.com/heypandax/cc-pocket" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is cc-pocket written in?

cc-pocket is primarily written in Kotlin. It is open-source under heypandax on GitHub, so you can review or fork the full source.

Are there alternatives to cc-pocket?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh cc-pocket against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情