OpenHuskyAgent 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
OpenHuskyAgent,提供Java语言的AI代理平台,支持浏览器自动化和聊天机器人等功能,适用于Feishu等应用
OpenHuskyAgent 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
OpenHuskyAgent,提供Java语言的AI代理平台,支持浏览器自动化和聊天机器人等功能,适用于Feishu等应用
OpenHuskyAgent 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/HandleCoding/OpenHuskyAgent
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"openhuskyagent": {
"command": "npx",
"args": ["-y", "openhuskyagent"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 OpenHuskyAgent 执行以下任务... Claude: [自动调用 OpenHuskyAgent MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"openhuskyagent": {
"command": "npx",
"args": ["-y", "openhuskyagent"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<img src="assets/logo/banner.png" alt="Husky - Your AI Workforce" width="100%" />
knowledge_search and knowledge_fetch over configured local knowledge sources.skill_list / skill_view loading.delegate_task can run child agents for isolated or parallel work./actuator/husky.Use the installer when you want the fastest setup on a Linux host.
Safer install path:
curl -fsSLO https://raw.githubusercontent.com/HandleCoding/OpenHuskyAgent/main/install.sh
less install.sh
bash install.sh
Convenience shortcut for trusted environments:
curl -fsSL https://raw.githubusercontent.com/HandleCoding/OpenHuskyAgent/main/install.sh | bash
Useful options:
bash install.sh --non-interactive
bash install.sh --install-dir="$HOME/openHusky" --port=18088
bash install.sh --upgrade
husky update
The installer clones the repository into ~/openHusky by default, installs JDK 17+ when needed, builds the service and TUI client JARs, writes runtime config to ~/.husky/.env, creates the ~/.husky/config, ~/.husky/skills, ~/.husky/db, ~/.husky/logs, and ~/.husky/memory directories, generates a random HUSKY_API_KEYS value, and can install a systemd service.
bin/husky prefers ~/.husky/.env and only falls back to the repo-local .env when the user-level config file is missing.
For the smoothest macOS install path, use the official Homebrew tap.
brew tap HandleCoding/husky
brew install HandleCoding/husky/husky
husky init
husky serve
After husky init, edit ~/.husky/.env and set OPENAI_API_KEY at minimum. Then choose one startup mode:
husky servehusky startTo upgrade a Homebrew install later:
brew update
brew upgrade HandleCoding/husky/husky
Homebrew installs openjdk@17 automatically, installs the husky launcher into your PATH, and keeps the runtime bundle under Homebrew-managed libexec.
Use the source path when you are developing locally or not on Linux.
Requirements:
git clone https://github.com/HandleCoding/OpenHuskyAgent.git
cd OpenHuskyAgent
mkdir -p ~/.husky
cp .env.example ~/.husky/.env
If you prefer a repo-local config for source-only work, bin/husky still falls back to .env when ~/.husky/.env does not exist.
./mvnw -B -ntp clean install
bin/husky serve
Success signal: the service keeps running in the current terminal and starts listening on port 18088 unless you changed HUSKY_PORT.
For local development, bin/husky dev starts the service and TUI together, but serve + tui is the clearest first-run path.
The recommended local upgrade path depends on how you installed Husky.
For a Homebrew install on macOS:
brew update
brew upgrade HandleCoding/husky/husky
For a git checkout managed with install.sh, use:
husky update
husky update wraps bash install.sh --upgrade, refuses to run on a dirty checkout, and prints the active code/config/memory paths after the upgrade.
If you want the lower-level command explicitly, this still works:
bash install.sh --upgrade
./mvnw -B -ntp -DskipTests package
The goal is to get Husky working once in under a minute: install, start the service, verify health, then open the TUI.
Edit ~/.husky/.env and set at least:
OPENAI_API_KEY=your-key
OPENAI_BASE_URL=https://api.openai.com
OPENAI_MODEL=gpt-5.4
OPENAI_API_KEY is the only strictly required value for a first run if the default base URL and model work for your provider.
Most deployments only need .env:
| Variable | Default | Purpose |
|---|---|---|
OPENAI_API_KEY | empty | OpenAI-compatible API key; required for model calls |
OPENAI_BASE_URL | https://api.openai.com | OpenAI-compatible endpoint |
OPENAI_COMPLETIONS_PATH | /v1/chat/completions | Chat completions path |
OPENAI_MODEL | gpt-5.4 | Main chat model |
OPENAI_TEMPERATURE | 0.7 | Main model temperature |
AUXILIARY_* | blank/main fallback | Optional model for summaries, compression, web summaries, and vision |
HUSKY_PORT | 18088 | HTTP/WebSocket service port |
HUSKY_DATA_DIR | ~/.husky | Runtime data directory for DBs, skills, MCP config, and logs |
AUTH_ENABLED | true | Enables API key auth for /api/chat |
HUSKY_API_KEYS | generated/example | Comma-separated Chatbot API keys; replace before public deployment |
TUI_WS_ALLOWED_ORIGINS | * | WebSocket origins; wildcard is local/dev only |
WEB_BACKEND | auto | auto, brave, tavily, or none |
BRAVE_SEARCH_API_KEY | empty | Enables Brave search |
TAVILY_API_KEY | empty | Enables Tavily search |
PROXY_* / HUSKY_PROXY_URL | env-driven | Shared outbound HTTP proxy settings |
WEB_PROXY_* | empty | Web-specific proxy override |
BROWSER_ENABLED | false | Enables Playwright browser tools |
MCP_ENABLED | false | Enables MCP server loading |
MCP_CONFIG_PATH | ${HUSKY_DATA_DIR}/config/mcp-servers.json | MCP server config path |
SKILLHUB_API_KEY | empty | Enables authenticated SkillHub operations |
Browser and MCP integrations are disabled by default. Enable them only when configured intentionally.
husky serve keeps the service in the current terminal. On macOS or other environments without systemd, use the lightweight background commands:
husky start
husky status
husky logs
husky stop
This mode writes its PID to ~/.husky/husky.pid and logs to ~/.husky/logs/husky-serve.log.
For long-running Linux server deployments, systemd is still the recommended path:
sudo systemctl start husky-agent
sudo systemctl status husky-agent
journalctl -u husky-agent -f
Most runtime defaults live in service/src/main/resources/application.yml.
| Area | Important keys |
|---|---|
| LLM | spring.ai.openai.*, agent.auxiliary.* |
| Agent loop | agent.graph.max-react-loops, agent.llm.*, agent.tool.*, agent.checkpoint.enabled |
| Context | context.threshold-percent, context.context-length, context.model-context-lengths, context.tail-token-budget |
| Channels | channel-bindings.*, channels.feishu.instances.*, channels.telegram.instances.*, channels.slack.instances.*, tui.ws.*, chatbot.enabled |
| Scenes | scenes.default-scene, scenes.configs.*.toolsets, allowed-tools, denied-tools, approval, backend, working-dir, memory, storage |
| Execution | execution.backend.docker.*, execution.backend.idle-ttl-seconds |
| Web | web.backend, web.proxy.*, BRAVE_SEARCH_API_KEY, TAVILY_API_KEY |
| Browser | browser.enabled, browser.headless, browser.timeout-seconds, browser.allow-private-network |
| MCP | mcp.enabled, mcp.config-path, scene allowed-mcp-servers / denied-mcp-servers |
| Knowledge | knowledge.enabled, knowledge.local-sources, limits for snippets/documents/depth |
| Skills | skill.builtin-dir, skill.dir, skill.managed-dirs, skillhub.* |
| Auth | auth.enabled, auth.api-keys |
| Observability | management.endpoints.web.exposure.include, husky.observability.* |
Storage defaults to local. Non-local workspace/checkpoint providers are extension points; unsupported remote types fail fast instead of silently falling back to local behavior.
curl -N \
-H 'X-Api-Key: <your-api-key>' \
-H 'X-User-Id: demo-user' \
-H 'Content-Type: application/json' \
-H 'Accept: text/event-stream' \
-d '{"message":"Search the latest Spring AI docs"}' \
http://localhost:18088/api/chat
Request fields:
| Field | Required | Purpose |
|---|---|---|
message | yes | User input |
sessionId | no | Existing server-issued session id; omit on first request |
Headers:
| Header | Required | Purpose |
|---|---|---|
X-Api-Key | yes when auth is enabled | Chatbot API authentication |
X-User-Id | yes | Stable end-user identity for session ownership |
X-Scene | no | Scene override when channel bindings allow it |
SSE events include token, reasoning, message, tool_started, tool_completed, tool_failed, done, and error.
./mvnw -B -ntp test
OPENAI_API_KEY=... ./mvnw -B -ntp test -P live-api-tests
./mvnw -B -ntp test -pl infra ./mvnw -B -ntp test -pl domain ./mvnw -B -ntp test -pl application ./mvnw -B -ntp test -pl service ./mvnw -B -ntp test -pl client
OpenHuskyAgent 是一个 AI 工作人员,旨在为开发者提供一个强大的 AI 助手。它通过 ReAct 图形运行时、流式渲染和场景运行时策略等功能来实现其强大的能力。
OpenHuskyAgent 具有以下功能:ReAct 图形运行时、流式渲染和场景运行时策略等。这些功能使得 OpenHuskyAgent 成为一个强大的 AI 助手。
环境依赖与系统要求
安装 OpenHuskyAgent 有多种方式,包括使用 Docker、pip 和源码部署。以下是安装步骤的说明:
使用 OpenHuskyAgent 的步骤包括安装、启动服务、验证健康状态和打开 TUI 等。以下是使用教程的说明:
OpenHuskyAgent 的配置包括设置环境变量、MCP 和关键参数等。以下是配置说明的内容:
OpenHuskyAgent 提供了一个 Chatbot SSE API,用于与外部系统进行通信。以下是 API 的说明:
OpenHuskyAgent 的工作流包括模块测试等。以下是工作流和模块的说明:
OpenHuskyAgent是一个开源的MCP工具,提供Java语言的AI代理平台,支持浏览器自动化和聊天机器人等功能,适用于Feishu等应用,但其评分较低,可能存在一些风险和缺陷
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,OpenHuskyAgent 在MCP工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | OpenHuskyAgent |
| 原始描述 | 开源MCP工具:OpenHuskyAgent。⭐6 · Java |
| Topics | mcpagent-platformai-agentbrowser-automationchatbotfeishujava |
| GitHub | https://github.com/HandleCoding/OpenHuskyAgent |
| License | MIT |
| 语言 | Java |
收录时间:2026-05-30 · 更新时间:2026-05-30 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端