ANOLISA User Guide
Use this manual to install, configure, and operate ANOLISA components for Agent workloads. Begin with the Quickstart for a first result, or open a component's manual for its setup and reference chapters. Shared installation, build, test, and troubleshooting instructions are grouped under Getting started.
Getting started
- Quickstart
- Images and cloud services
- Installation
- ANOLISA CLI
- Building and deployment
- Testing
- Troubleshooting
User Entrypoint Layer
- cosh (cosh-ng): An AI-native terminal that preserves your existing shell experience, with natural-language tasks, tools, and Skills.
- OS Skills: An OS handbook for AI Agents, covering system administration, monitoring, security, DevOps automation, and more.
AW Unified Stack Layer
- AW: A unified architecture connecting Agent frameworks with extensible AI-native system software.
Agent Semantic Layer
- AgentSight: Observe Agent execution through trajectories, LLM calls, and Token usage.
- Agent Security Core: OS-level security kernel for AI Agents.
- Tokenless: Reduce AI Agent Token usage through tool output compression, tool schema simplification, command rewriting, and other techniques.
- Agent Memory: Give Agents searchable, persistent memory to retain and reuse information across sessions.
- SkillFS: Organize Skills into stable filesystem views for Agents to discover and read on demand.
- Workspace Checkpoint: Create Agent workspace snapshots, compare file differences, and roll back changes when needed.
- ktuner: Inspect Linux kernel parameters, get tuning recommendations, and apply or roll back changes.
Terminology
| Term | Meaning |
|---|---|
| Component | A software unit implementing a specific capability (e.g. tokenless) |
| Adapter | A bridge package connecting a component to an Agent framework |
| system mode | Installation requiring root privileges (sudo anolisa install) |
| user mode | Installation into user-local paths (no sudo required) |