ANOLISA User Guide
ANOLISA provides a complete server-side runtime for AI Agent workloads. Components are installed via the anolisa CLI and operate independently.
Component Architecture
┌────────────────────────────────────────────────────────────────────┐
│ Agent Applications (cosh / OpenClaw / Hermes / custom) │
├────────────────────────────────────────────────────────────────────┤
│ User Entry Points │
│ anolisa-cli · cosh · os-skills │
├──────────────────────────────────┬─────────────────────────────────┤
│ Token Saving │ Runtime │
│ tokenless · agent-memory │ skillfs · ws-ckpt │
├──────────────────────────────────┼─────────────────────────────────┤
│ Agent Observability │ Agent Security │
│ agentsight │ agent-sec-core │
└──────────────────────────────────┴─────────────────────────────────┘
Documentation Index
Global
| Document | Content |
|---|---|
| Installation | Progressive install from CLI to full component stack |
| Troubleshooting | Cross-component common issues and fixes |
User Entry Points (user-entrypoint/)
| Document | Component | Description |
|---|---|---|
| anolisa CLI | anolisa | Unified CLI for component management |
| cosh-ng | cosh-ng | AI-native Linux terminal with an integrated Agent runtime |
| Copilot Shell | cosh | AI terminal assistant and command gateway |
| OS Skills | os-skills | System management and DevOps skills |
Agent Observability (agent-observability/)
| Document | Component | Description |
|---|---|---|
| AgentSight | agentsight | eBPF-based tracing, Token accounting, Web Dashboard |
| AgentSight Quick Start | agentsight | Install, capture the first session, open the Dashboard |
| AgentSight Dashboard Guide | agentsight | Token access and a page-by-page walkthrough |
| AgentSight CLI Reference | agentsight | Every command and flag with real output |
| AgentSight Configuration | agentsight | Config file, feature switches, Agent discovery rules |
| Interruption Detection | agentsight | The 18 interruption types and the triage workflow |
| AgentSight Deployment | agentsight | systemd, containers/sidecars, macOS, upgrade, uninstall |
| AgentSight Data and Storage | agentsight | Databases, retention, HTTP API, Prometheus, ATIF export |
| AgentSight Integrations | agentsight | Tokenless, agent-sec-core, enforcer, cosh, Prometheus |
| AgentSight Troubleshooting | agentsight | No data, 401, unreachable port, database growth |
Agent Security (agent-security/)
| Document | Component | Description |
|---|---|---|
| AgentSecCore | agent-sec-core | Hardening, code scanning, prompt scanning, skill ledger |
| OWASP Agentic Top 10 Control Mapping | ANOLISA | Security controls, conditions, and evidence for ten Agentic risk categories |
| Code Scanner Hook Configuration | agent-sec-core | Per-agent hook modes, environment variables, and fallback behavior |
| Prompt Scanner | agent-sec-core | Prompt injection / jailbreak detection, modes, and verdicts |
| PII Checker | agent-sec-core | Personal data / credential detection and redaction |
| Asset Verification | agent-sec-core | GPG-signed skill distribution verification and discovery outcomes |
| Skill Ledger User Guide | agent-sec-core | Skill integrity chain and signing workflow |
| OpenClaw Deployment & Upgrade | agent-sec-core | OpenClaw plugin deployment and upgrade guide |
| Internal Commands | agent-sec-core | Contract and inventory of the hidden, hook-invoked commands |
Token Saving (token-saving/)
| Document | Component | Description |
|---|---|---|
| Tokenless Quick Start | tokenless | Install, connect an agent, run the first compression, and verify |
| Tokenless User Manual | tokenless | Capability boundaries, runtime behavior, and task navigation |
| Tokenless Python SDK | tokenless | Framework-neutral and AgentScope layers, Runtime operations, statistics, and examples |
| Tokenless AgentScope SDK Integration | tokenless | AgentScope 1.x, 2.x, and App attachment to the generic SDK |
| Tokenless Agent Integration | tokenless | Product adapters, hooks, and plugins |
| Tokenless CLI Reference | tokenless | Protocol pipeline, direct compression, Stash, MCP, and statistics commands |
| Measuring Tokenless Savings | tokenless | Statistics, diffs, dry runs, AgentSight, and SLS measurement |
| Tokenless Configuration and Data Privacy | tokenless | Configuration precedence, local data, and sensitive workloads |
| Tokenless Troubleshooting | tokenless | Adapters, databases, Stash, upgrades, and uninstall |
| Agent Memory | agent-memory | Persistent memory, MCP tools, search and sovereignty controls |
Runtime (runtime/)
| Document | Component | Description |
|---|---|---|
| Blaze Sandbox Runtime | blaze | Opt-in VM networking and periodic storage artifact synchronization for managed sandboxes |
| Workspace Checkpoints | ws-ckpt | Workspace checkpoint/rollback via btrfs COW |
| Skill Filesystem | skillfs | FUSE virtual views with progressive disclosure |
| SkillFS Kubernetes Sidecar | skillfs | Running SkillFS as a FUSE sidecar in Kubernetes |
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) |