AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Workflow Automation/
sysknife
sysknife logo

sysknife

Active·★ 77·MIT·Updated 2026-10-27

SysKnife is an AI-powered system administration tool for Linux that allows users to describe tasks in natural language, generating typed plans with formal risk levels for explicit approval. It emphasizes security through a privileged daemon, tamper-evident audit chains, and automatic rollback for atomic-host changes, ensuring the AI never directly controls the system.

#Linux System Administration#AI Agent#Workflow Automation#Security#Auditing#CLI#Typed Actions#Atomic Host Rollback
$ Install
$ npx sysknife-setup
↗ Visit site★ GitHub
01

Features

01AI-powered planning with typed actions and formal risk levels (Low, Medium, High).
02Explicit, receipt-based approval gate ensures user control over execution, preventing AI from approving its own work.
03Tamper-evident Ed25519-signed audit chain for every action, ensuring verifiable logs.
04Automatic rollback for atomic-host (rpm-ostree) changes on failure.
05Integration with AI IDEs like Claude Code, Cursor, and Codex CLI via MCP server.
02

Compatibility

Ubuntu 20.04+
OS Distro
Verified via docs
Ubuntu 22.04 / 24.04 / 26.04
VM Validated
Verified via docs
Fedora Atomic 41+
OS Distro
Verified via docs
Node.js 22+
Runtime
Verified via docs
Rust Stable
Build Toolchain
Verified via docs
Ollama / OpenAI / Anthropic / Gemini / Groq / DeepSeek / Mistral / xAI
LLM Provider
Verified via docs
03

Quick start

1
$ npx sysknife-setup
04

Use cases

↳Securely automating Linux system administration tasks with natural language commands.
↳Orchestrating system changes on Ubuntu or Fedora Atomic hosts with clear approval and audit trails.
↳Integrating AI assistants into IT operations workflows for controlled execution of privileged commands.
↳Ensuring compliance and accountability for system modifications through public-key verifiable audit logs.
↳Performing diagnostics and read-only queries on systems via AI, such as checking disk usage or service status.
05

Alternatives

⚡Top VS:
VSCyrene-Agent★759→VScodflow★394→VSshowtime★306→VSsuperCMO-skills★240→
Cyrene-Agent logo
Cyrene-Agent★ 759
一款开源、基于昔涟开发的桌面 AI 智能体/An open-source desktop AI agent based on Cyrene.
VSCompare→
codflow logo
codflow★ 394
The open-source, COD-first e-commerce + delivery platform for Algeria built agentic-ready.
VSCompare→
showtime logo
showtime★ 306
A local video studio for your coding agent. Describe a video in one sentence: your agent directs, your machine renders. Claude Code, Codex, Cursor, Devin and more. No API keys, no uploads.
VSCompare→
superCMO-skills logo
superCMO-skills★ 240
Open-source skills that empower any AI agent (Claude, Cursor, Hermes, etc.) to generate end-to-end marketing campaigns - UGC videos, ad videos, product photography and more.
VSCompare→
discord-mcp logo
discord-mcp★ 181
Local, typed Model Context Protocol server for Discord bots - 192 tools for AI clients with safety controls and observability.
VSCompare→
brigade logo
brigade★ 81
One local source for the MCP servers, tools, and memory your AI coding agents share, synced into each tool's native config with a review gate and a receipt for every change. No daemon, no lock-in.
VSCompare→
tmux-mcp logo
tmux-mcp★ 57
Lets agents create sessions, split panes, run commands, and capture output with TMUX.
VSCompare→
oh-my-dag logo
oh-my-dag★ 44
The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
lacs-project /
sysknife
↗

An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the command.

77MIT
Last commit1d ago
StatusActive
CategoryWorkflow Automation
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.