Build AI agent fleets. 3 lines, any backend, local or cloud. Effort-based model routing, 48 identities, knowledge graph memory, fleet orchestration.
接入配置
选择客户端，复制配置，再按项目文档补齐环境变量。
claude mcp add aitheros-adk --env AITHERIUM_API_KEY='<AITHERIUM_API_KEY>' -- uvx aither-adk~/.codex/config.toml
[mcp_servers.aitheros-adk]
command = "uvx"
args = ["aither-adk"]
env = { AITHERIUM_API_KEY = "<AITHERIUM_API_KEY>" }
# codex mcp add aitheros-adk --env AITHERIUM_API_KEY='<AITHERIUM_API_KEY>' -- uvx aither-adk~/.cursor/mcp.json
{
"mcpServers": {
"aitheros-adk": {
"command": "uvx",
"args": [
"aither-adk"
],
"env": {
"AITHERIUM_API_KEY": "<AITHERIUM_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"aitheros-adk": {
"type": "stdio",
"command": "uvx",
"args": [
"aither-adk"
],
"env": {
"AITHERIUM_API_KEY": "<AITHERIUM_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"aitheros-adk": {
"command": "uvx",
"args": [
"aither-adk"
],
"env": {
"AITHERIUM_API_KEY": "<AITHERIUM_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"aitheros-adk": {
"command": "uvx",
"args": [
"aither-adk"
],
"env": {
"AITHERIUM_API_KEY": "<AITHERIUM_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"aitheros-adk": {
"command": "uvx",
"args": [
"aither-adk"
],
"env": {
"AITHERIUM_API_KEY": "<AITHERIUM_API_KEY>"
}
}
}
}需要的环境变量
AITHERIUM_API_KEY
把占位值换成你自己的密钥；不要把密钥提交到代码仓库。