PicoClaw AI 助手：超轻量级个人AI助手，10美元硬件运行，支持多LLM提供商

picoclaw-ai-assistant by aradotso/trending-skills

320 周安装量

10 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/aradotso/trending-skills --skill picoclaw-ai-assistant

AI/机器学习 Go 命令行工具

🇨🇳中文介绍

PicoClaw AI 助手

Skill by ara.so — Daily 2026 Skills 合集。

PicoClaw 是一个用 Go 编写的超轻量级个人 AI 助手。它能在 10 美元以下的硬件上运行，占用内存低于 10MB，并在 1 秒内启动。它支持多个 LLM 提供商（OpenAI 兼容、Anthropic、Volcengine）、可选的网络搜索工具，并可作为单个独立二进制文件部署在 x86_64、ARM64、MIPS 和 RISC-V Linux 设备上。

安装

预编译二进制文件

从发布页面下载：

# Linux ARM64 (Raspberry Pi, LicheeRV-Nano 等)
wget https://github.com/sipeed/picoclaw/releases/download/v0.1.1/picoclaw-linux-arm64
chmod +x picoclaw-linux-arm64
./picoclaw-linux-arm64 onboard

从源码构建

git clone https://github.com/sipeed/picoclaw.git
cd picoclaw

# 安装依赖
make deps

# 为当前平台构建
make build

# 为所有平台构建
make build-all

# Raspberry Pi Zero 2 W — 32 位
make build-linux-arm      # → build/picoclaw-linux-arm

# Raspberry Pi Zero 2 W — 64 位
make build-linux-arm64    # → build/picoclaw-linux-arm64

# 构建两种 Pi Zero 变体
make build-pi-zero

# 构建并安装到系统 PATH
make install

Docker Compose

git clone https://github.com/sipeed/picoclaw.git
cd picoclaw

# 首次运行 — 生成 docker/data/config.json 然后退出
docker compose -f docker/docker-compose.yml --profile gateway up

# 编辑配置
vim docker/data/config.json

# 在后台启动
docker compose -f docker/docker-compose.yml --profile gateway up -d

# 查看日志
docker compose -f docker/docker-compose.yml logs -f picoclaw-gateway

# 停止
docker compose -f docker/docker-compose.yml --profile gateway down

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

2. 配置 `~/.picoclaw/config.json`

{
  "agents": {
    "defaults": {
      "workspace": "~/.picoclaw/workspace",
      "model_name": "gpt-4o",
      "max_tokens": 8192,
      "temperature": 0.7,
      "max_tool_iterations": 20
    }
  },
  "model_list": [
    {
      "model_name": "gpt-4o",
      "model": "openai/gpt-4o",
      "api_key": "$OPENAI_API_KEY",
      "request_timeout": 300
    },
    {
      "model_name": "claude-sonnet",
      "model": "anthropic/claude-sonnet-4-5",
      "api_key": "$ANTHROPIC_API_KEY"
    },
    {
      "model_name": "ark-code",
      "model": "volcengine/ark-code-latest",
      "api_key": "$VOLCENGINE_API_KEY",
      "api_base": "https://ark.cn-beijing.volces.com/api/coding/v3"
    }
  ],
  "tools": {
    "web": {
      "brave": {
        "enabled": false,
        "api_key": "$BRAVE_API_KEY"
      },
      "tavily": {
        "enabled": false,
        "api_key": "$TAVILY_API_KEY"
      }
    }
  }
}

切勿硬编码 API 密钥。在配置中使用 $VAR_NAME 符号引用环境变量，或在启动前在 shell 环境中设置它们。

# 交互式聊天
picoclaw

# 单条消息
picoclaw -m "Summarize the latest Go release notes"

# 使用特定模型
picoclaw -model claude-sonnet -m "Refactor this function for clarity"

命令	描述
`picoclaw onboard`	初始化配置和工作区
`picoclaw`	启动交互式聊天会话
`picoclaw -m "..."`	发送单条消息并退出
`picoclaw -model <name>`	覆盖默认模型
`picoclaw -config <path>`	使用自定义配置文件

{
  "model_name": "my-model",        // 在 -model 标志和代理默认值中使用的别名
  "model": "provider/model-id",    // 带提供商前缀的模型标识符
  "api_key": "$ENV_VAR",           // API 密钥 — 使用环境变量引用
  "api_base": "https://...",       // 可选：覆盖基础 URL（用于自托管或区域端点）
  "request_timeout": 300           // 可选：超时前的秒数
}

支持的提供商前缀

前缀	提供商
`openai/`	OpenAI 和 OpenAI 兼容的 API
`anthropic/`	Anthropic Claude
`volcengine/`	Volcengine (Ark)

"agents": {
  "defaults": {
    "workspace": "~/.picoclaw/workspace",  // 文件操作的工作目录
    "model_name": "gpt-4o",                // 默认模型别名
    "max_tokens": 8192,                    // 最大响应令牌数
    "temperature": 0.7,                    // 采样温度
    "max_tool_iterations": 20              // 最大代理工具调用循环迭代次数
  }
}

获取免费 API 密钥：

Tavily : https://tavily.com — 每月 1,000 次免费查询
Brave Search : https://brave.com/search/api — 每月 2,000 次免费查询

"tools": { "web": { "tavily": { "enabled": true, "api_key": "$TAVILY_API_KEY" }, "brave": { "enabled": false, "api_key": "$BRAVE_API_KEY" } } }

除非您需要备用行为，否则一次只启用一个搜索提供商。

模式：最低成本 10 美元设备设置

适用于 LicheeRV-Nano 或类似的超低资源开发板：

# 从发布版本下载 RISC-V 或 ARM 二进制文件
wget https://github.com/sipeed/picoclaw/releases/download/v0.1.1/picoclaw-linux-riscv64
chmod +x picoclaw-linux-riscv64

# 初始化
./picoclaw-linux-riscv64 onboard

# 编辑配置 — 使用轻量级模型，较低的 max_tokens
cat > ~/.picoclaw/config.json << 'EOF'
{
  "agents": {
    "defaults": {
      "workspace": "~/.picoclaw/workspace",
      "model_name": "gpt-4o-mini",
      "max_tokens": 2048,
      "temperature": 0.5,
      "max_tool_iterations": 10
    }
  },
  "model_list": [
    {
      "model_name": "gpt-4o-mini",
      "model": "openai/gpt-4o-mini",
      "api_key": "$OPENAI_API_KEY",
      "request_timeout": 120
    }
  ]
}
EOF

./picoclaw-linux-riscv64

模式：具备网络搜索功能的全栈开发助手

{
  "agents": {
    "defaults": {
      "workspace": "~/projects",
      "model_name": "claude-sonnet",
      "max_tokens": 8192,
      "temperature": 0.3,
      "max_tool_iterations": 30
    }
  },
  "model_list": [
    {
      "model_name": "claude-sonnet",
      "model": "anthropic/claude-sonnet-4-5",
      "api_key": "$ANTHROPIC_API_KEY",
      "request_timeout": 600
    }
  ],
  "tools": {
    "web": {
      "tavily": {
        "enabled": true,
        "api_key": "$TAVILY_API_KEY"
      }
    }
  }
}

模式：使用环境变量的 Docker

# docker/docker-compose.override.yml
services:
  picoclaw-gateway:
    environment:
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
      - TAVILY_API_KEY=${TAVILY_API_KEY}
      - PICOCLAW_GATEWAY_HOST=0.0.0.0



export OPENAI_API_KEY=sk-...
export ANTHROPIC_API_KEY=sk-ant-...
docker compose -f docker/docker-compose.yml -f docker/docker-compose.override.yml --profile gateway up -d

模式：在 Go 中为特定目标构建

# 为 MIPS 交叉编译 (OpenWRT 路由器)
GOOS=linux GOARCH=mips GOMIPS=softfloat go build -o build/picoclaw-linux-mips ./cmd/picoclaw

# 为 32 位 ARM 交叉编译 (旧款 Raspberry Pi)
GOOS=linux GOARCH=arm GOARM=7 go build -o build/picoclaw-linux-arm ./cmd/picoclaw

# 为 RISC-V 64 位交叉编译
GOOS=linux GOARCH=riscv64 go build -o build/picoclaw-linux-riscv64 ./cmd/picoclaw

二进制文件在设备上无法执行

# 验证二进制文件是否与设备架构匹配
file picoclaw-linux-arm64
uname -m   # 应匹配：aarch64 = arm64, x86_64 = amd64

# 确保有可执行权限
chmod +x picoclaw-linux-arm64

Termux 上出现 "Permission denied"

Termux 需要 proot 来处理某些系统调用：

pkg install proot
termux-chroot ./picoclaw-linux-arm64 onboard

API 密钥未被识别

不要在配置中使用 "api_key": "sk-..." 字面量 — 设置环境变量并在配置中引用它们，如 "$OPENAI_API_KEY"。
验证环境变量是否在当前 shell 中导出：echo $OPENAI_API_KEY。

Docker 网关无法从主机访问

在启动容器之前，在环境变量或 config.json 中设置 PICOCLAW_GATEWAY_HOST=0.0.0.0。

最近版本内存使用率高

项目说明最近的 PR 可能会将 RAM 使用量推高到 10–20MB。如果这对超低内存设备是个问题，请固定到较早的发布标签：

git checkout v0.1.1
make build

默认：~/.picoclaw/config.json

picoclaw -config /path/to/custom-config.json

依赖项更改后重新构建

cd picoclaw
make deps
make build

硬件目标快速参考

设备	价格	二进制文件
LicheeRV-Nano (E/W)	~$10	`picoclaw-linux-riscv64`
NanoKVM	~$30–50	`picoclaw-linux-riscv64`
MaixCAM / MaixCAM2	~$50–100	`picoclaw-linux-arm64`
Raspberry Pi Zero 2 W (32 位 OS)	~$15	`picoclaw-linux-arm`
Raspberry Pi Zero 2 W (64 位 OS)	~$15	`picoclaw-linux-arm64`
通过 Termux 的 Android	—	`picoclaw-linux-arm64`
标准 Linux x86_64	—	`picoclaw-linux-amd64`

🇺🇸English

PicoClaw AI Assistant

Skill by ara.so — Daily 2026 Skills collection.

PicoClaw is an ultra-lightweight personal AI assistant written in Go. It runs on $10 hardware with under 10MB RAM and boots in under 1 second. It supports multiple LLM providers (OpenAI-compatible, Anthropic, Volcengine), optional web search tools, and deploys as a single self-contained binary on x86_64, ARM64, MIPS, and RISC-V Linux devices.

Installation

Precompiled Binary

Download from the releases page:

# Linux ARM64 (Raspberry Pi, LicheeRV-Nano, etc.)
wget https://github.com/sipeed/picoclaw/releases/download/v0.1.1/picoclaw-linux-arm64
chmod +x picoclaw-linux-arm64
./picoclaw-linux-arm64 onboard

Build from Source

git clone https://github.com/sipeed/picoclaw.git
cd picoclaw

# Install dependencies
make deps

# Build for current platform
make build

# Build for all platforms
make build-all

# Raspberry Pi Zero 2 W — 32-bit
make build-linux-arm      # → build/picoclaw-linux-arm

# Raspberry Pi Zero 2 W — 64-bit
make build-linux-arm64    # → build/picoclaw-linux-arm64

# Build both Pi Zero variants
make build-pi-zero

# Build and install to system PATH
make install

Docker Compose

git clone https://github.com/sipeed/picoclaw.git
cd picoclaw

# First run — generates docker/data/config.json then exits
docker compose -f docker/docker-compose.yml --profile gateway up

# Edit config
vim docker/data/config.json

# Start in background
docker compose -f docker/docker-compose.yml --profile gateway up -d

# View logs
docker compose -f docker/docker-compose.yml logs -f picoclaw-gateway

# Stop
docker compose -f docker/docker-compose.yml --profile gateway down

Docker: Web Console (Launcher Mode)

docker compose -f docker/docker-compose.yml --profile launcher up -d
# Open http://localhost:18800

Docker: One-shot Agent Mode

# Single question
docker compose -f docker/docker-compose.yml run --rm picoclaw-agent -m "What is 2+2?"

# Interactive session
docker compose -f docker/docker-compose.yml run --rm picoclaw-agent

Docker: Expose Gateway to Host

If the gateway needs to be reachable from the host, set:

PICOCLAW_GATEWAY_HOST=0.0.0.0 docker compose -f docker/docker-compose.yml --profile gateway up -d

Or set PICOCLAW_GATEWAY_HOST=0.0.0.0 in docker/data/config.json.

Termux (Android)

pkg install wget proot
wget https://github.com/sipeed/picoclaw/releases/download/v0.1.1/picoclaw-linux-arm64
chmod +x picoclaw-linux-arm64
termux-chroot ./picoclaw-linux-arm64 onboard

Quick Start

1. Initialize

picoclaw onboard

This creates ~/.picoclaw/config.json with a starter configuration.

2. Configure `~/.picoclaw/config.json`

{
  "agents": {
    "defaults": {
      "workspace": "~/.picoclaw/workspace",
      "model_name": "gpt-4o",
      "max_tokens": 8192,
      "temperature": 0.7,
      "max_tool_iterations": 20
    }
  },
  "model_list": [
    {
      "model_name": "gpt-4o",
      "model": "openai/gpt-4o",
      "api_key": "$OPENAI_API_KEY",
      "request_timeout": 300
    },
    {
      "model_name": "claude-sonnet",
      "model": "anthropic/claude-sonnet-4-5",
      "api_key": "$ANTHROPIC_API_KEY"
    },
    {
      "model_name": "ark-code",
      "model": "volcengine/ark-code-latest",
      "api_key": "$VOLCENGINE_API_KEY",
      "api_base": "https://ark.cn-beijing.volces.com/api/coding/v3"
    }
  ],
  "tools": {
    "web": {
      "brave": {
        "enabled": false,
        "api_key": "$BRAVE_API_KEY"
      },
      "tavily": {
        "enabled": false,
        "api_key": "$TAVILY_API_KEY"
      }
    }
  }
}

Never hard-code API keys. Reference environment variables using $VAR_NAME notation in config, or set them in your shell environment before launch.

3. Run

# Interactive chat
picoclaw

# Single message
picoclaw -m "Summarize the latest Go release notes"

# Use a specific model
picoclaw -model claude-sonnet -m "Refactor this function for clarity"

Key CLI Commands

Command	Description
`picoclaw onboard`	Initialize config and workspace
`picoclaw`	Start interactive chat session
`picoclaw -m "..."`	Send a single message and exit
`picoclaw -model <name>`	Override the default model
`picoclaw -config <path>`	Use a custom config file

Configuration Reference

Model Entry Fields

{
  "model_name": "my-model",        // Alias used in -model flag and agent defaults
  "model": "provider/model-id",    // Provider-prefixed model identifier
  "api_key": "$ENV_VAR",           // API key — use env var reference
  "api_base": "https://...",       // Optional: override base URL (for self-hosted or regional endpoints)
  "request_timeout": 300           // Optional: seconds before timeout
}

Supported Provider Prefixes

Prefix	Provider
`openai/`	OpenAI and OpenAI-compatible APIs
`anthropic/`	Anthropic Claude
`volcengine/`	Volcengine (Ark)

Agent Defaults

"agents": {
  "defaults": {
    "workspace": "~/.picoclaw/workspace",  // Working directory for file operations
    "model_name": "gpt-4o",                // Default model alias
    "max_tokens": 8192,                    // Max response tokens
    "temperature": 0.7,                    // Sampling temperature
    "max_tool_iterations": 20              // Max agentic tool-call loop iterations
  }
}

Web Search Tools

Get free API keys:

Tavily : https://tavily.com — 1,000 free queries/month
Brave Search : https://brave.com/search/api — 2,000 free queries/month

"tools": { "web": { "tavily": { "enabled": true, "api_key": "$TAVILY_API_KEY" }, "brave": { "enabled": false, "api_key": "$BRAVE_API_KEY" } } }

Only enable one search provider at a time unless you want fallback behavior.

Common Patterns

Pattern: Minimal $10 Device Setup

For a LicheeRV-Nano or similar ultra-low-resource board:

# Download the RISC-V or ARM binary from releases
wget https://github.com/sipeed/picoclaw/releases/download/v0.1.1/picoclaw-linux-riscv64
chmod +x picoclaw-linux-riscv64

# Initialize
./picoclaw-linux-riscv64 onboard

# Edit config — use a lightweight model, low max_tokens
cat > ~/.picoclaw/config.json << 'EOF'
{
  "agents": {
    "defaults": {
      "workspace": "~/.picoclaw/workspace",
      "model_name": "gpt-4o-mini",
      "max_tokens": 2048,
      "temperature": 0.5,
      "max_tool_iterations": 10
    }
  },
  "model_list": [
    {
      "model_name": "gpt-4o-mini",
      "model": "openai/gpt-4o-mini",
      "api_key": "$OPENAI_API_KEY",
      "request_timeout": 120
    }
  ]
}
EOF

./picoclaw-linux-riscv64

Pattern: Full-Stack Dev Assistant with Web Search

{
  "agents": {
    "defaults": {
      "workspace": "~/projects",
      "model_name": "claude-sonnet",
      "max_tokens": 8192,
      "temperature": 0.3,
      "max_tool_iterations": 30
    }
  },
  "model_list": [
    {
      "model_name": "claude-sonnet",
      "model": "anthropic/claude-sonnet-4-5",
      "api_key": "$ANTHROPIC_API_KEY",
      "request_timeout": 600
    }
  ],
  "tools": {
    "web": {
      "tavily": {
        "enabled": true,
        "api_key": "$TAVILY_API_KEY"
      }
    }
  }
}

Pattern: Docker with Environment Variables

# docker/docker-compose.override.yml
services:
  picoclaw-gateway:
    environment:
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
      - TAVILY_API_KEY=${TAVILY_API_KEY}
      - PICOCLAW_GATEWAY_HOST=0.0.0.0



export OPENAI_API_KEY=sk-...
export ANTHROPIC_API_KEY=sk-ant-...
docker compose -f docker/docker-compose.yml -f docker/docker-compose.override.yml --profile gateway up -d

Pattern: Build for a Specific Target in Go

# Cross-compile for MIPS (OpenWRT routers)
GOOS=linux GOARCH=mips GOMIPS=softfloat go build -o build/picoclaw-linux-mips ./cmd/picoclaw

# Cross-compile for 32-bit ARM (older Raspberry Pi)
GOOS=linux GOARCH=arm GOARM=7 go build -o build/picoclaw-linux-arm ./cmd/picoclaw

# Cross-compile for RISC-V 64-bit
GOOS=linux GOARCH=riscv64 go build -o build/picoclaw-linux-riscv64 ./cmd/picoclaw

Troubleshooting

Binary won't execute on device

# Verify the binary matches the device architecture
file picoclaw-linux-arm64
uname -m   # Should match: aarch64 = arm64, x86_64 = amd64

# Ensure executable permission
chmod +x picoclaw-linux-arm64

"Permission denied" on Termux

Termux requires proot for some system calls:

pkg install proot
termux-chroot ./picoclaw-linux-arm64 onboard

API key not recognized

Do not use "api_key": "sk-..." literals in config — set env vars and reference them as "$OPENAI_API_KEY".
Verify the env var is exported in your current shell: echo $OPENAI_API_KEY.

Docker gateway not reachable from host

Set PICOCLAW_GATEWAY_HOST=0.0.0.0 in the environment or in config.json before starting the container.

High memory usage in recent versions

The project notes that recent PRs may push RAM usage to 10–20MB. If this is a concern on ultra-low-memory devices, pin to an earlier release tag:

git checkout v0.1.1
make build

Config file location

Default: ~/.picoclaw/config.json

Override at runtime:

picoclaw -config /path/to/custom-config.json

Rebuild after dependency changes

cd picoclaw
make deps
make build

Hardware Targets Quick Reference

Device	Price	Binary
LicheeRV-Nano (E/W)	~$10	`picoclaw-linux-riscv64`
NanoKVM	~$30–50	`picoclaw-linux-riscv64`
MaixCAM / MaixCAM2	~$50–100	`picoclaw-linux-arm64`
Raspberry Pi Zero 2 W (32-bit OS)	~$15	`picoclaw-linux-arm`
Raspberry Pi Zero 2 W (64-bit OS)	~$15	`picoclaw-linux-arm64`

Weekly Installs

320

Repository

aradotso/trending-skills

GitHub Stars

First Seen

7 days ago

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

gemini-cli317

github-copilot317

codex317

amp317

cline317

kimi-cli317

超能力技能使用指南：AI助手技能调用优先级与工作流程详解

40,300 周安装

PicoClaw AI 助手：超轻量级个人AI助手，10美元硬件运行，支持多LLM提供商

🇨🇳中文介绍

PicoClaw AI 助手

安装

预编译二进制文件

从源码构建

Docker Compose

相关 Skills

Docker：Web 控制台（启动器模式）

Docker：一次性代理模式

Docker：将网关暴露给主机

Termux (Android)

快速开始

1. 初始化

2. 配置 ~/.picoclaw/config.json

3. 运行

关键 CLI 命令

配置参考

模型条目字段

支持的提供商前缀

代理默认值

网络搜索工具

常用模式

模式：最低成本 10 美元设备设置

模式：具备网络搜索功能的全栈开发助手

模式：使用环境变量的 Docker

模式：在 Go 中为特定目标构建

故障排除

二进制文件在设备上无法执行

Termux 上出现 "Permission denied"

API 密钥未被识别

Docker 网关无法从主机访问

最近版本内存使用率高

配置文件位置

依赖项更改后重新构建

硬件目标快速参考

🇺🇸English

PicoClaw AI Assistant

Installation

Precompiled Binary

Build from Source

Docker Compose

Docker: Web Console (Launcher Mode)

Docker: One-shot Agent Mode

Docker: Expose Gateway to Host

Termux (Android)

Quick Start

1. Initialize

2. Configure ~/.picoclaw/config.json

3. Run

Key CLI Commands

Configuration Reference

Model Entry Fields

Supported Provider Prefixes

Agent Defaults

Web Search Tools

Common Patterns

Pattern: Minimal $10 Device Setup

Pattern: Full-Stack Dev Assistant with Web Search

Pattern: Docker with Environment Variables

Pattern: Build for a Specific Target in Go

Troubleshooting

Binary won't execute on device

"Permission denied" on Termux

API key not recognized

Docker gateway not reachable from host

High memory usage in recent versions

Config file location

Rebuild after dependency changes

Hardware Targets Quick Reference

最新 Skills

2. 配置 `~/.picoclaw/config.json`

2. Configure `~/.picoclaw/config.json`