b9a498a3fd
CRITICAL FIX: chat.py had TWO execution paths causing inconsistent behavior: 1. Tool calling (correct) - used centralized command_patterns 2. Legacy JSON command parsing (broken) - bypassed SysadminTools This caused macha-chat to fail SSH connections while macha-ask worked. Changes: - Rewrote chat.py to use ONLY tool-calling architecture - All commands now go through SysadminTools.execute_command() - SSH commands use centralized command_patterns.py - conversation.py is now a lightweight wrapper for compatibility - Both macha-chat and macha-ask use the same code path - Updated module.nix to call chat.py directly Benefits: - Consistent behavior between macha-chat and macha-ask - Single execution path = easier to maintain - All SSH commands use explicit key paths - No more password prompts Fixes: - SSH from macha-chat now works correctly - Both interfaces use centralized command patterns
Macha - AI-Powered Autonomous System Administrator
Macha is an AI-powered autonomous system administrator for NixOS that monitors system health, diagnoses issues, and can take corrective actions with appropriate approval workflows.
Features
- Autonomous Monitoring: Continuous health checks with configurable intervals
- Multi-Host Management: SSH-based management of multiple NixOS hosts
- Tool Calling: Comprehensive system administration tools via Ollama LLM
- Queue-Based Architecture: Serialized LLM requests to prevent resource contention
- Knowledge Base: ChromaDB-backed learning system for operational wisdom
- Approval Workflows: Safety-first approach with configurable autonomy levels
- Notification System: Gotify integration for alerts
Quick Start
As a NixOS Flake Input
Add to your flake.nix:
{
inputs = {
nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable";
macha-autonomous.url = "git+https://git.coven.systems/lily/macha-autonomous";
};
outputs = { self, nixpkgs, macha-autonomous }: {
nixosConfigurations.yourhost = nixpkgs.lib.nixosSystem {
modules = [
macha-autonomous.nixosModules.default
{
services.macha-autonomous = {
enable = true;
autonomyLevel = "suggest"; # observe, suggest, auto-safe, auto-full
checkInterval = 300;
ollamaHost = "http://localhost:11434";
model = "gpt-oss:latest";
};
}
];
};
};
}
Configuration Options
See module.nix for full configuration options including:
- Autonomy levels (observe, suggest, auto-safe, auto-full)
- Check intervals
- Ollama host and model settings
- Git repository monitoring
- Service user/group configuration
CLI Tools
macha-chat- Interactive chat interfacemacha-ask- Single-question interfacemacha-check- Trigger immediate health checkmacha-approve- Approve pending actionsmacha-logs- View service logsmacha-issues- Query issue databasemacha-knowledge- Query knowledge basemacha-systems- List managed systemsmacha-notify- Send Gotify notification
Architecture
- Agent: Core AI logic with tool calling
- Orchestrator: Main monitoring loop
- Executor: Safe action execution
- Queue System: Serialized Ollama requests with priorities
- Context DB: ChromaDB for system context and learning
- Tools: System administration capabilities
Requirements
- NixOS with flakes enabled
- Ollama service running
- Python 3 with requests, psutil, chromadb
Documentation
See DESIGN.md for comprehensive architecture documentation.
License
[Add your license here]
Author
Lily Miller