Runtime Configuration

Anda stores runtime state in ~/.anda by default. The main configuration file is ~/.anda/config.yaml, created automatically on first launch. Optional MCP server configuration lives in ~/.anda/mcp.json.

Model Providers

The active provider must include family, model, and api_base. api_key can be written in the config file or left empty and supplied through an environment variable.

model:
  active: "deepseek-v4-pro"
  providers:
    - family: anthropic
      model: "deepseek-v4-pro"
      api_base: "https://api.deepseek.com/anthropic"
      api_key: "YOUR_API_KEY"
      labels: ["pro", "brain"]
      disabled: false

Supported model API key environment variables include:

OPENAI_API_KEY
ANTHROPIC_API_KEY
GEMINI_API_KEY
GOOGLE_API_KEY
DEEPSEEK_API_KEY
MINIMAX_API_KEY
MIMO_API_KEY
MOONSHOT_API_KEY
KIMI_API_KEY
BIGMODEL_API_KEY
GLM_API_KEY

Common Top-Level Settings

Setting	Purpose
addr	Local gateway address, default 127.0.0.1:8042.
sandbox	When true, shell execution goes through ~/.anda/sandbox.
https_proxy	Proxy used for model and channel requests.
model	Model providers for the agent and memory brain.
transcription	Provider for voice input and audio attachment transcription.
tts	Provider for voice playback.
channels	Telegram, WeChat, Discord, Lark/Feishu, and other channel configuration.

MCP Servers

Anda Bot can connect to MCP servers through stdio child processes or HTTP endpoints. Put a portable MCP configuration in ~/.anda/mcp.json, then restart the daemon. The file accepts both mcpServers and servers as the root key so you can paste configs from other MCP-compatible tools with minimal changes.

{
  "mcpServers": {
    "filesystem": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "$ANDA_WORKSPACE"]
    },
    "remote": {
      "type": "http",
      "url": "https://mcp.example.com/mcp",
      "headers": {
        "Authorization": "Bearer ${MCP_REMOTE_TOKEN}"
      }
    }
  }
}

Remote MCP tools appear as Anda tools named like mcp_<server_id>_<remote_tool>. Config strings support $VAR and ${VAR} environment expansion. ANDA_HOME and ANDA_WORKSPACE are built in. For stdio servers, command is spawned directly without a shell; when cwd is omitted, the first Anda workspace is used. If type is omitted, Anda infers stdio from command or http from url.

The agent can also add a server at runtime with add_mcp_server. Set persist: false for the current daemon only, or persist: true to save the server into ~/.anda/mcp.json for future restarts. Its server fields mirror one mcp.json entry: type, command, args, env, cwd, url, headers, enabled, include, and exclude, plus the tool-only id and persist fields.

Local Directory Structure

~/.anda/
  config.yaml
  mcp.json
  anda-daemon.pid
  channels/
  db/
  keys/
    anda_bot.key
    user.key
  logs/
  bundled-skills/
  sandbox/
  skills/
  skills-manifest.json
  skill-backups/
  skill-trash/
  workspace/

Directory	Contents
db/	Local memory, conversations, channel state, cron state, object state, and related data.
keys/	Local signing keys for the daemon and user.
logs/	Daemon and CLI logs.
channels/	Channel runtime state.
bundled-skills/	Release-managed skills installed by Anda updates.
sandbox/	Shell isolation directory when sandboxing is enabled.
skills/	Personal runtime skills created, cloned, or edited by the user.
skills-manifest.json	Local enable/disable and reload metadata for the skill library.
skill-backups/	Timestamped backups created before Dashboard skill edits.
skill-trash/	Deleted Personal skills moved aside before removal.
workspace/	Default workspace for file and shell tools.

Privacy Boundary

Anda local state, memory graph, conversations, channel state, cron state, keys, logs, and workspace data are stored on your machine by default.

However, model providers may still receive prompts, tool-result summaries, and memory formation or recall requests. Choose trusted providers, private endpoints, or proxy policies according to your privacy needs.

tip

Use anda --home /path/to/.anda when you need isolated data for different identities, projects, or tests.