AitherOS ADK — Claude Code MCP server: what it does, how to install
Connects an agent runtime with SQLite knowledge graphs, effort-based routing, and subagent delegation. Useful for keeping long-term memory across chats and dispatching tasks to helper agents.
claude mcp add --env AITHERIDENTITY_URL=<AITHERIDENTITY_URL> --env AITHERIUM_API_KEY=<AITHERIUM_API_KEY> --transport stdio aitheros-adk -- uvx aither-adkWhat AitherOS ADK does
The runtime serves as an MCP bridge executed via uvx aither-adk. It maintains an embedded knowledge store inside a local SQLite database. During conversations, entities and connections get parsed and saved automatically. Search queries combine classic keyword matching with semantic retrieval. No external graph databases are required.
Model dispatch relies on an internal effort rating scaled from 1 to 10. Routine questions go to lightweight engines, while heavy analytical tasks reach deep reasoning systems. You can swap execution backends during runtime between local runtimes like llama.cpp and cloud providers such as Anthropic or OpenAI. Multiple agents coordinate using the built-in ask_agent capability.
Without valid AITHERIUM_API_KEY and AITHERIDENTITY_URL variables, the server fails to authenticate. On Windows machines, Python script directories might also need manual registration inside your user PATH.
What it helps with
- Store conversational entities in a local SQLite knowledge graph
- Route prompts across models according to task difficulty scores
- Delegate subtasks to specialized agents using the
ask_agenttool - Switch inference backends on the fly between local engines and cloud APIs
- Query historical context with combined semantic and keyword search
Example prompts for the agent
- Search the knowledge graph for previous notes on our architecture
- Hand this debugging task over to a subagent using
ask_agent - Evaluate task complexity and assign a high-effort model for code refactoring
How to install AitherOS ADK
Platform CLI
claude mcp add --env AITHERIDENTITY_URL=<AITHERIDENTITY_URL> --env AITHERIUM_API_KEY=<AITHERIUM_API_KEY> --transport stdio aitheros-adk -- uvx aither-adkReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from aither-adk <command>
Platform CLI
codex mcp add aitheros-adk --env AITHERIDENTITY_URL=<AITHERIDENTITY_URL> --env AITHERIUM_API_KEY=<AITHERIUM_API_KEY> -- uvx aither-adkReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from aither-adk <command>
Config file
{
"mcpServers": {
"aitheros-adk": {
"command": "uvx",
"args": [
"aither-adk"
],
"env": {
"AITHERIDENTITY_URL": "<AITHERIDENTITY_URL>",
"AITHERIUM_API_KEY": "<AITHERIUM_API_KEY>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from aither-adk <command>
Config file
{
"servers": {
"aitheros-adk": {
"type": "stdio",
"command": "uvx",
"args": [
"aither-adk"
],
"env": {
"AITHERIDENTITY_URL": "<AITHERIDENTITY_URL>",
"AITHERIUM_API_KEY": "<AITHERIUM_API_KEY>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from aither-adk <command>
Platform CLI
gemini mcp add -e AITHERIDENTITY_URL=<AITHERIDENTITY_URL> -e AITHERIUM_API_KEY=<AITHERIUM_API_KEY> aitheros-adk uvx aither-adkReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from aither-adk <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about AitherOS ADK
How do I install AitherOS ADK in Claude Code?
Run `claude mcp add --env AITHERIDENTITY_URL=<AITHERIDENTITY_URL> --env AITHERIUM_API_KEY=<AITHERIUM_API_KEY> --transport stdio aitheros-adk -- uvx aither-adk`. Replace the placeholder tokens with your actual environment values.
What does AitherOS ADK do?
It provides agent runtimes with long-term SQLite graph memory, effort-based model routing, and multi-agent coordination. It also supports runtime switching between local inference hardware and external cloud backends.
Does the knowledge graph require an external database service?
No, all relational memory is stored locally in an embedded SQLite file. It processes entities and relationships on your machine without external cloud databases.
