ANOLISA Agent OS Layer
A terminal, context-efficiency, and execution-layer toolkit for existing AI agent stacks.
- Source repo
- agentic-os-org/ANOLISA
- Stars
- ★ 652
- Last updated
- today
- License
- Apache-2.0
- Primary language
- Rust
- FA score
- 45/100 · Major gaps
At a glance
- Works with
- Universal · cross-platform
- You'll need
- Typical use
- A platform team already running an agent framework and sandbox can add cosh-ng when its agents need a structured terminal interface for Shell and system work.
- Main limitation
- The README explicitly identifies only Linux and macOS; it provides no evidence of Windows support.
- Source review
- 45/100 · Major gaps
What does this agent do, and when should you use it?
ANOLISA is a server-side operating layer for AI agent workloads, with ANOLISA CLI as its common installation entry point. Its cosh-ng component gives agents a structured, predictable interface for Shell and system operations. Token-less sits between an agent and its model to compress tool schemas and tool responses, while retaining references for removed array items. Agent Memory, SkillFS, and AgentSight cover cross-session context reuse, on-demand Skill mounting, and Token-spend recording. The execution-environment direction includes Agent Sec Core for isolating risky operations and ws-ckpt for workspace recovery points; the README identifies Linux and macOS as supported platforms.
After installation, operators can run anolisa install cosh-ng or anolisa install tokenless, then start the agent-native shell with cosh-ng. Token-less uses ResponseCompressor and SchemaCompressor on tool responses and schemas entering context; the documented example drops blacklisted debug and trace fields, null metadata, and empty tags / extra values. Removed array items retain a retrievable <<tokenless:KEY>> marker, making that compression reversible. Agent Memory reuses context across sessions, SkillFS exposes Skills as views and mounts them on demand, and AgentSight records where Tokens are spent. Agent Sec Core is described as isolating risky operations, while ws-ckpt preserves recovery points for workspace changes.
- A platform team already running an agent framework and sandbox can add cosh-ng when its agents need a structured terminal interface for Shell and system work.
- An agent application whose tool outputs contain debug data, nulls, empty fields, or redundant arrays can use Token-less before those responses enter model context.
- A team running recurring agent sessions can evaluate Agent Memory when it wants to reuse context across sessions.
- A developer organization with many Skills can use SkillFS when only the relevant Skills should be mounted into context for a given task.
- An operations team investigating context cost can use AgentSight to record where Tokens are actually spent.
- A workspace-oriented agent environment can assess ws-ckpt for recovery points and Agent Sec Core for risky-operation isolation.
How do you install or deploy this agent?
The documented installation command is:
curl -fsSL https://get.agentic-os.sh | bashInstall the desired components:
anolisa install cosh-ng
anolisa install tokenlessThe README identifies Linux and macOS as platforms. This installation path requires network access and curl; no API key, account, or other credential requirement is documented.
How do you use this agent?
After installing cosh-ng, run:
cosh-ngThis enters the agent-native shell. The README also says an existing agent can be pointed at cosh-ng. Once Token-less is installed, it applies to tool calls; the supplied documentation does not provide an additional configuration command, so validate compression behavior and retrieval-marker handling in the target workflow.
What are this agent's strengths and limitations?
- It is designed to retain the Shell, agent framework, and sandbox already in use instead of replacing the execution stack.
- Token-less covers both tool schemas and tool responses, while preserving retrievable
<<tokenless:KEY>>references for removed array items. - Its context-efficiency components span session reuse, on-demand Skill mounting, and Token-spend recording rather than only response compression.
- The execution-environment scope includes both risky-operation isolation and workspace recovery points.
- The README explicitly identifies only Linux and macOS; it provides no evidence of Windows support.
- The published Token-reduction figures apply to tool responses and schemas entering context, not proportionally to the entire session bill.
- Initial setup executes a remotely fetched script through
curl, which requires network access and may need to pass organizational software-installation review. - Although it is described as working with existing frameworks and sandboxes, no named framework, model provider, or platform integration is documented, so compatibility needs validation.
- Agent Sec Core and ws-ckpt are presented as execution-environment capabilities being built out, without documented isolation semantics, recovery procedures, or configuration details.
How does this agent compare with similar options?
ANOLISA is positioned as an added layer around an existing Shell, agent framework, and sandbox, rather than as a replacement for those systems.
Key facts side by side with the most closely related agents.
| Agent | Source review | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|
| ANOLISA Agent OS Layer This agent | 45 · Major gaps | ★ 652 | today | Rust | — |
| Archestra | 71 · Some gaps | ★ 4.3k | today | TypeScript | Codex · Claude Code · OpenAI API · Claude API |
| Arize Phoenix | 61 · Some gaps | ★ 12k | today | Python | OpenAI API · Claude API |
| Adrian | 59 · Major gaps | ★ 568 | 8d ago | Python | Claude Code · OpenAI API · Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows security mechanisms (user approval, isolation, rollback) but mostly descriptive, lacking implementation details. Deductions: least privilege not concretely configured; user confirmation not detailed; data flow transparency only mentions token compression; sensitive data handling not explicit; dependency security lacks vulnerability scanning or locked versions; external effects not clear; rollback only mentions ws-ckpt without recovery process; source attribution unverified.
Self-consistency is good, README and docs align, but some component descriptions don't fully match code. Deductions: dependency availability lacks complete list or verification; failure messages lack concrete examples.
Target audience and scenarios clear (terminal, token cost, execution environment), capability boundaries described, but trigger precision insufficient (e.g., token compression trigger conditions not explicit). Environment fit has Linux/macOS notes but not all components covered.
Information architecture clear with README, user guide, quick start; install notes exist but rely on external script; naming stability not explicit; examples and FAQ partial; known limitations not fully covered; license clear; changelog exists but not detailed; maintenance responsibility not explicit.
Output usability has examples, marginal value clear (token savings), but cost-benefit not quantified (e.g., performance overhead).
Claims partially traceable (e.g., token savings data), but lack independent verification; cross-source corroboration insufficient; facts and inferences not clearly separated.
- Install script via curl poses supply chain risk; review script content.
- Token savings claims lack test methodology or independent verification.
- Security mechanisms (user approval, isolation) are mostly descriptive; verify actual implementation.
FAQ
Do Token-less savings equal the total model-session cost reduction?
Does Token-less require changes to agent-framework code?
Is compressed information permanently lost?
<<tokenless:KEY>> marker, intended to make compression reversible.What credentials are required for installation?
curl.