AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompareGuides
Submit Tool
ToolsCategoriesTrendingNewCompareGuides
Home/
Dev Tooling/
agent
agent logo

agent

Active·★ 1.8k·Updated 2026-07-06
★ Trending★ Hidden Gem

Stakpak is an open-source AI agent for the terminal aimed at infrastructure work: generating infrastructure code, debugging Kubernetes, configuring CI/CD and automating deployments. Its README builds the pitch on safety. Dynamic secret substitution lets the model work with credentials without seeing the real values, and a privacy mode redacts things like IP addresses and AWS account IDs. Warden guardrails apply network-level policies that block destructive operations before they run, and MCP traffic uses mutual TLS. Curated DevOps knowledge ships as rulebooks, and you can add your own playbooks and policies; the agent also keeps persistent knowledge about incidents and your environment.

Install with Homebrew (`brew tap stakpak/stakpak` then `brew install stakpak`), a release binary from GitHub Releases, or a Docker image (`ghcr.io/stakpak/agent:latest`) that includes common tools such as docker, kubectl and cloud CLIs; the front page also shows a `curl | sh` installer. Then run `stakpak`: either create a Stakpak API key in a browser flow (the README says no card is required) or write `~/.stakpak/config.toml` with your own Anthropic, OpenAI or other provider keys. GitHub shows no detected license, so check the repository for the terms before using it at work.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-11.

License
Apache-2.0
Latest release
v0.3.88 · 2026-06-10
Last commit
2026-07-06
Contributors
21
Forks
198
Open issues and PRs
43
First published
2024-12-10

Source: GitHub, npm and PyPI public APIs.

#AI Agent#DevOps#Security#Infrastructure Automation#Terminal#Coding
$ Install
$ curl -sSL https://stakpak.dev/install.sh | sh
↗ Visit site★ GitHub
01

Features

01Secret Substitution: The LLM works with your credentials without ever seeing them.
02Warden Guardrails: Network-level policies block destructive operations before they run.
03DevOps Playbooks & Rulebooks: Curated library of DevOps knowledge and customizable agent behavior.
04Infrastructure Code Indexing: Automatic local indexing and semantic search for various infrastructure code.
05Asynchronous Task Management & Real-time Progress Streaming: Manage background commands and get real-time progress updates.
02

Why choose it

+Secret substitution keeps real credentials out of the model's view
+Network-level guardrails block destructive operations before they run
+Privacy mode redacts IP addresses and account IDs
+Bring your own Anthropic or OpenAI keys, or use a Stakpak key
03

Trade-offs

!The safety claims are the project's own; review what it can reach before pointing it at production
!No license is detected by GitHub, so reuse terms are unclear
!Using a Stakpak API key means your sessions go through their service
!The front page installer pipes a remote script into a shell; read it first
04

Compatibility

Anthropic
Supported
Verified via docs
OpenAI
Supported
Verified via docs
Ollama
Supported
Verified via docs
LM Studio
Supported
Verified via docs
Zed Editor
Native Integration
Verified via docs
05

Quick start

1
$ curl -sSL https://stakpak.dev/install.sh | sh
06

Use cases

↳Generating infrastructure code (Terraform, Kubernetes, Dockerfile).
↳Debugging Kubernetes and configuring CI/CD pipelines.
↳Automating secure and controlled infrastructure deployments.
07

Alternatives

CopilotKit logo
CopilotKit★ 38.0k
React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic Frontend.
1Panel logo
1Panel★ 37.2k
🔥 1Panel provides an intuitive web interface and MCP Server to manage websites, files, containers, databases, and LLMs on a Linux server.
ragflow logo
ragflow★ 92.2k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Context7 logo
Context7★ 63.0k
MCP Server that provides up-to-date code documentation for LLMs and AI code editors.
GitHub MCP Server logo
GitHub MCP Server★ 33.6k
GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).
n8n logo
n8n★ 207.3k
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Microsoft AutoGen logo
Microsoft AutoGen★ 61.4k
A framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.
CrewAI logo
CrewAI★ 59.7k
Framework for orchestrating role-playing, autonomous AI agents. By working together, your Crew can tackle complex tasks.
See all alternatives →

Featured in these lists

  • Open-Source Security Tools for MCP Servers and AI Agents

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
Stats
GitHub Stars★ 1.8k
Last commit3mo ago
StatusActive
License—
CategoryDev Tooling
Trend (30d)
+0k↑ 3.9%
Links
Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

Ad
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.