AitherOS ADK runs on your own machine — the client starts it, so there is no endpoint to ping. 1 827 installs a week from pypi. Last commit 8 Sep 2026.
Agent runtime with typed memory, knowledge and code graphs, plus file and web tools
We read the source, 17 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
proc = subprocess.run(
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
env = dict(os.environ)
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
in_container = os.path.exists("/.dockerenv")
result = subprocess.run(
return __import__(name, *args, **kwargs)
path = os.path.join(out_dir, f"gen_{timestamp}.png")
env = dict(os.environ)
exe_candidates = list(dest_dir.rglob("AitherDesktop.exe"))
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add aither-adk -- uvx aither-adk
{
"mcpServers": {
"aither-adk": {
"args": [
"aither-adk"
],
"command": "uvx"
}
}
}
[mcp_servers.aither-adk]
command = "uvx"
args = ["aither-adk"]
{
"mcpServers": {
"aither-adk": {
"args": [
"aither-adk"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"aither-adk": {
"args": [
"aither-adk"
],
"command": "uvx"
}
}
}
Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.
AI-powered code indexer with semantic search and knowledge graphs
Content-addressed code graph with 22 MCP tools for AI agents.
Public registry of code-knowledge graphs for AI agents with schema validation and drift detection.
Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory.
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
Indexes codebase into a local knowledge graph with 40+ AI tools and codebase-guard.
AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.
Answers built from our own checks of this server.