SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

ANOLISAagentic-os-org/ANOLISA

Provides observable, isolatable and optimizable runtime infrastructure for AI agents from the kernel level up,…

No ratings yet Rate this skill
Stars664
Forks138
Watchers664
Open Issues1.5k

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/agentic-os-org/ANOLISA.git

OverviewOverview

Key Features

Provides observable, isolatable and optimizable runtime infrastructure for AI agents from the kernel level up, so agent behavior on Linux is actually visible instead of a black box. Key capabilities include: 1. eBPF-based non-intrusive observation: traces an agent's system calls and execution path on Linux via eBPF without modifying its code, revealing what it actually does; 2. Runtime security and sandboxing: enforces runtime security protection and sandbox isolation to prevent agents from over-reaching system resources; 3. Context and memory management: centrally manages agent context engineering and memory to control context bloat; 4. Token optimization: optimizes token consumption across agent call chains to cut cost of long sessions and multi-turn tasks; 5. Observability output: turns agent execution into observable data for locating anomalies and performance bottlenecks.

Use Cases

Tracing real system calls when debugging abnormal agent behavior, deploying sandboxed isolation for untrusted agents, auditing agent runtime security risks, optimizing context and token overhead of long-session agents, and performing kernel-level performance analysis of agents on Linux servers.

Target Roles

AI / Algorithm Engineer, DevOps / Operations Engineer, Network & System Security Engineer, Backend Developer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID1835
Data sourceGitHub
Repositoryagentic-os-org/ANOLISA
CategoryDevelopment & Engineering / AI Agent Runtime & Observability
Primary languageRust
LicenseApache License 2.0
Default branchmain
GitHub repository ID1195873793
Node IDR_kgDOR0eWAQ
Rank#1028 (position within the source ranking)
Site-wide popularity rank#1182 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006008002026-09-302026-10-112026-09-30 · 6582026-10-11 · 664
  • Now664
  • Previous point · 09-30 658
  • vs previous point +6
  • 2 data points 11 days
0501001502026-09-302026-10-112026-09-30 · 1112026-10-11 · 138
  • Now138
  • Previous point · 09-30 111
  • vs previous point +27
  • 2 data points 11 days

TimelineTimeline

Repository created2026-03-30 06:33:067 months ago
Data last updated2026-10-26 12:07:4322 days ago
Last commit2026-10-11 06:48:431 months ago

CommitLatest commit

Version [v0.5.1] committed by pilichoumao. Update Category: Feature Addition & Enhancement. Commit details: fix(anolisa): retry cloud-init on new rounds. This update introduces new capabilities and module extensions.

ae50d48 v0.5.1 pilichoumao 2026-10-11

Next stepsNext steps