AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Multi-Agent/
ptah-extension
ptah-extension logo

ptah-extension

Active·★ 29·MIT·Updated 2026-10-22

Ptah is an AI development environment that learns your codebase architecture and orchestrates a team of specialized agents. It provides persistent memory, sub-agent delegation, and automation capabilities across desktop, VS Code, and CLI surfaces for continuous delivery.

#AI Agent#Developer Tool#Codebase Analysis#Multi-Agent System#VS Code Extension#CI/CD Automation#Persistent Memory
© 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.

Guides
$ Install
$ npm i -g @hive-academy/ptah-cli
↗ Visit site★ GitHub
01

Features

01Persistent memory and deep codebase analysis through AST parsing and hybrid search.
02Orchestrates a team of specialized sub-agents (architect, backend, frontend, tester, reviewer) for various development tasks.
03Automated and scheduled runs for continuous delivery, including security reviews and dependency scans.
04Offers a unified experience across desktop application, VS Code extension, and headless CLI.
05Supports various LLM providers, including frontier models, OpenRouter, Ollama, and external CLIs.
02

Compatibility

Windows
OS
Verified via docs
macOS
OS
Verified via docs
Linux
OS
Verified via docs
VS Code
Editor
Verified via docs
NPM
Package Manager
Verified via docs
JavaScript
Language
Verified via docs
03

Quick start

1
$ npm i -g @hive-academy/ptah-cli
04

Use cases

↳Maintaining architectural consistency across large projects using persistent memory and codebase mapping.
↳Automating CI/CD pipelines, scheduled security reviews, and routine development tasks via its CLI and cron scheduler.
↳Facilitating collaborative development and code review processes with multiple AI agents acting as a tribunal.
↳Scaffolding new projects with AI-generated roadmaps and dedicated agent teams for rapid setup.
05

Alternatives

⚡Top VS:
VSmini_agent★37→VSzeroshot★2.0k→VShacker-bob★100→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
VS
AgenticOS
★24
→
mini_agent logo
mini_agent★ 37
A minimal AI agent built from scratch — no agent framework, just Python, the OpenAI SDK, and a `while` loop. Accompanies the Medium article "Build Your Own AI Agent from Scratch." Three execution modes: `local` (Ollama only), `remote` (cloud provider), `mixed` (local orchestrates, delegates to remote).
VSCompare→
zeroshot logo
zeroshot★ 2.0k
Your autonomous engineering team in a CLI. Point Zeroshot at an issue, walk away, and return to production-grade code. Supports Claude Code, OpenAI Codex, OpenCode, and Gemini CLI.
VSCompare→
hacker-bob logo
hacker-bob★ 100
A local MCP runtime that attacks what you own and only reports what it proved. 17 CVEs across 9 projects came out of this repo. Install: npx -y hacker-bob@latest install /path/to/project, then run /bob-evaluate target.com
VSCompare→
AgenticOS logo
AgenticOS★ 24
An open-source, self-hostable AI operating system and development workspace. Powered by Electron and React 19, it features multi-agent orchestration, full Model Context Protocol (MCP) support, native filesystem access, and an extensible tool ecosystem for autonomous software development.
VSCompare→
Agenvoy logo
Agenvoy★ 509
Make AI actually work for you - A personal agent that writes its own tools and repairs itself.
VSCompare→
vigil logo
vigil★ 397
Vigil - a 100% OpenSource AI system for machine-speed network defense
VSCompare→
claude-vibe-squad logo
claude-vibe-squad★ 164
Multi-model AI orchestration where behaviour is Markdown, not code. One coordinator routes scoped task packets to 71 role-based specialists across 5 model families (Codex / Claude / Gemini / Grok / Kimi) — each working in an isolated git worktree, each reviewed by a rival family before it lands. One tmux session, no server.
VSCompare→
omnigent logo
omnigent★ 11.0k
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
VSCompare→
See all alternatives →
Hive-Academy /
ptah-extension
↗

Provider-agnostic AI orchestration for VS Code. Intelligent workspace analysis, Code Execution MCP server, and project-adaptive multi-agent workflows — all natively integrated into VS Code.

29MIT
Last commit1d ago
StatusActive
CategoryMulti-Agent
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