员工
| 员工 | 当前状态 | 下一步 | 运行与装配摘要 | ||
|---|---|---|---|---|---|
|
|
|
|
|
|
当前视图下无员工
可以切换到其他工作视图，或调整阶段、风险、关键字筛选后再试。
商家 / 业务单元
总览
The current OpenFang embedded console is reserved for internal operations, implementation, and runtime support.
Merchant and partner accounts should use their dedicated workspaces instead of this internal console.
Select an agent to start chatting
Choose an agent from the sidebar or go to the Agents tab to create a new one.
Execution Approvals
No approvals
When agents request permission for sensitive actions, they'll appear here.
Workflows
Try the Visual Builder to drag and drop workflow steps.
| Name | Steps | Created | Actions |
|---|---|---|---|
No workflows yet
Chain multiple agents into automated pipelines with branching, fan-out, and loops.
Scheduler
*/5 * * * * (every 5 min) or
0 9 * * 1-5 (weekdays at 9am). You can also run any job
manually with the "Run Now" button.
| Name | Schedule | Agent | Status | Last Run | Next Run | Actions |
|---|---|---|---|---|---|---|
|
|
No scheduled jobs
Create a cron job to run agents on a recurring schedule. Jobs are stored persistently and survive restarts.
| Agent | Pattern | Prompt | Fires | Enabled | Created | Actions |
|---|---|---|---|---|---|---|
No event triggers
Create event triggers on the Workflows page to fire agents in response to system events.
| Time | Name | Type | Status | Total Runs |
|---|---|---|---|---|
No run history yet
Run history will appear here after scheduled jobs or triggers execute.
Channels
当前筛选下没有可展示的能力项。
执行单元
能力包
技能
- 系统预置 — bundled skill 属于 system preset layer，不等价于 repo 已安装
- Repo 定义 — `repo_dirs` 用来承载平台 skill definition 与 catalog 来源
- 已安装 — 仅表示当前 repo skills 目录里真实存在的技能定义
- 员工候选 — 只有进入数字员工候选池的技能才应作为默认装配候选
当前没有系统目录技能
这里会展示系统预置、repo 和 runtime 层能看到的全部技能目录。你也可以继续浏览外部市场，或用快速开始创建自己的技能。
ClawHub 可能暂时不可用，OpenClaw 生态目录托管在 clawhub.ai。
没有找到与“”相关的技能
可以换一个关键词，或直接按分类浏览。
MCP 服务（Model Context Protocol）
MCP 服务会把 GitHub、文件系统、数据库、外部 API 等工具接入到 Agent 与技能运行时中。
可在 config.toml 的 [mcp_servers] 下统一配置。
当前没有配置 MCP 服务
MCP 服务会为 Agent 扩展外部工具，可先把服务定义加到 `config.toml`：
[[mcp_servers]] name = "filesystem" timeout_secs = 30 [mcp_servers.transport] type = "stdio" command = "npx" args = ["-y", "@modelcontextprotocol/server-filesystem", "/path"]
OpenFang 支持所有兼容 OpenClaw 协议的 MCP 服务。
快速开始技能
一键创建 prompt-only 技能，把领域知识或工作规范直接注入到系统提示词中，无需额外代码。
- 系统预置 — bundled hands 属于 system preset layer，不等于员工已装配
- Repo 定义 — `repo_dirs` 承载 O2O preset hands 等 definition catalog 来源
- 员工绑定 — DB binding 决定数字员工实际选用哪些 hand
- 员工候选 — 只有声明为数字员工候选的 hand 才应进入默认装配视图
当前没有可用能力包
Hands 是可治理的能力包资源。等内核加载 bundled / source / runtime 定义后，这里会展示完整定义库。
当前没有活跃能力包
可先回到定义库选择要启用的 hand；每次启用都会生成对应的运行实例。
设置
LLM Providers
OpenFang supports 12 LLM providers out of the box. Configure API keys to unlock models from each provider. Set environment variables and restart, or use the form below to save keys directly.
No providers found
Provider information could not be loaded. Check that the API is running.
Model Catalog
Browse all available models across providers. Models marked "Available" have their provider configured and ready to use.
Add Custom Model
| Model | Provider | Tier | Context | Input Cost | Output Cost | Status | |
|---|---|---|---|---|---|---|---|
| Tool | Description |
|---|---|
Runtime Configuration
View and edit the active configuration. Changes are applied immediately. For advanced edits, modify config.toml in your OpenFang data directory.
sha2 SHA-256 ·
hmac HMAC-SHA256 ·
subtle constant-time ·
ed25519-dalek signing ·
zeroize secret wiping ·
rand randomness ·
governor rate limiting
Peer Networking (OFP)
Link multiple OpenFang instances into a mesh via the OFP wire protocol.
| Node | Address | State | Agents | Protocol |
|---|---|---|---|---|
No peers connected
Add a [network] section to config.toml with shared_secret and peer addresses.
A2A External Agents
Discovered agents on other OpenFang/A2A-compatible instances that this node can communicate with.
| Name | URL | Description |
|---|---|---|
Budget & Spending Limits
Monitor and control spending across all agents.
Top Spenders (Today)
| Agent | Today | Hourly Limit | Daily Limit | Monthly Limit |
|---|---|---|---|---|
- Converts agent.yaml to agent.toml with proper capabilities
- Maps tools (read_file → file_read, execute_command → shell_exec, etc.)
- Merges channel configs into config.toml
- Copies workspace files and memory data
分析
| Model | Calls | Input Tokens | Output Tokens | Cost | Usage |
|---|---|---|---|---|---|
No model usage data yet.
| Agent | Total Tokens | Tool Calls |
|---|---|---|
No agent usage data yet.
| Model | Provider | Tier | Input Tokens | Output Tokens | Calls | Cost | Cost Share |
|---|---|---|---|---|---|---|---|
Inbox
会话
| Session | Agent | Messages | Created | Actions |
|---|---|---|---|---|
Agent Memory
Each agent has its own key-value memory store. Agents use memory to persist preferences, notes, and context between conversations.
| Key | Value | Actions |
|---|---|---|
|
|
|
No keys stored
This agent has no memory entries yet. Agents create memory entries automatically during conversations, or you can add them manually.
Select an Agent
Choose an agent from the dropdown above to browse and edit its memory store.
日志与审计
No log entries yet
Activity will appear here as agents run.
| # | Timestamp | Agent | Action | Detail | Outcome |
|---|---|---|---|---|---|
No audit entries yet
Activity will appear here as agents operate.
Agent Comms
Connection Error
Platform Setup Wizard
这个向导只负责 OpenFang 平台本身的首次准备：连接 LLM Provider、可选验证基础渠道、以及保留一个工程型 Agent 试运行入口。真正的数字员工入职、primary agent 创建与能力装配，请从员工页进入。
约 2 分钟，可随时跳过。若你的目标是上线数字员工，请优先回到员工页继续装配主线。
Connect an LLM Provider
OpenFang needs at least one LLM provider to power your agents. Select a provider and enter your API key.
Provider Already Configured
You already have at least one provider set up. You can continue to the next step or configure additional providers.
Create An Optional Starter Agent
This step is optional. It keeps the legacy agent lab usable, but primary agents for digital employees should now be created from the employee onboarding flow.
Try Your Agent
Send a quick message to test your new agent. Try one of the suggestions below or type your own.
Connect a Channel Optional
Channels let your agent communicate via messaging platforms. This is optional — you can always use the built-in web chat.
You can skip this step. The built-in web chat is always available from the Agents page. Add channels any time from Settings → Channels.
You're All Set!
OpenFang is configured and ready to go. Here is a summary of what was set up:
运行态总览
| Provider | Status | Models | Latency |
|---|---|---|---|