SuperAPI AI Directory
Partner with us中文AI newsFavorites
All toolsAI codingPtah

Ptah

Ptah is an AI coding extension for Visual Studio Code, centered on an "AI coding symphony," namely vendor-agnostic AI orchestration combined with intelligent workspace analysis and multi-agent collaboration. It can scan and understand a user's codebase, automatically configure specialized AI agents, and schedule them to handle complex development tasks in parallel. The extension includes a built-in MCP server that provides 14 API namespaces, giving agents structured access to workspace analysis, LSP diagnostics, AST parsing, file search, dependency graphs, and editor state. It supports automatically identifying built-in agents from installed CLIs, configuring custom agents with your own providers and API keys, and generating, monitoring, guiding, and collecting background agent results through MCP tools. Ptah provides seven categories of orchestration workflows (feature development, bug fixing, refactoring, documentation, research, DevOps, and creative), with user approval checkpoints at each stage, along with native editor chat, execution tree visualization, session management, cost tracking, and a performance dashboard. It is licensed under FSL-1.1-MIT, which automatically converts to a full MIT license two years after release.

Open website

About this tool

Ptah is a Visual Studio Code extension published by Ptah Extensions, positioned as the "AI coding symphony for VS Code." It brings AI orchestration, workspace intelligence, and a built-in MCP server directly into the editor, aimed at developers who need multiple agents to handle complex development tasks in parallel.

[Main capabilities]

  1. Multi-agent orchestration: It can spawn multiple AI agents as headless background workers; the main agent dispatches subtasks and collects results, enabling true parallel multi-agent workflows.
  2. Agent sources: Built-in agents can be automatically identified from installed CLIs; custom agents can be configured with your own providers and API keys; and results can be generated, monitored, guided, and collected through MCP tools.
  3. Built-in MCP server: 14 API namespaces allow AI agents to gain structured access to workspace analysis, LSP diagnostics, AST parsing, file search, dependency graphs, and editor state through a single tool call.
  4. Stdio MCP server (ptah mcp-serve): Any MCP-compatible host can drive Ptah via stdio, and external orchestrators can generate, monitor, and guide agents and hand off the entire task to the Team Leader shell through the session_submit tool, without custom integration.
  5. Workspace scanning: An automated 6-step scan identifies project types, frameworks, and dependencies, covering more than 13 project types and generating project-specific agent configurations and rules.
  6. Skill plugins: Extensible orchestration workflows, code review, architecture patterns, content generation, and UI/UX design, currently available for Angular, React, NestJS, and NX workspaces.
  7. Editor chat: Native chat supports real-time execution tree visualization, session management, cost tracking, file attachments, and streaming text display.
  8. Performance dashboard: Provides real-time and historical analysis of costs, tokens, sessions, and agent performance, filterable by time range and exportable as CSV or JSON.
  9. Orchestration workflows: Provides seven workflow types—feature development, bug fixing, refactoring, documentation, research, DevOps, and creative—each with dedicated agent delegation and user approval checkpoints at every stage.

[How to use] The getting-started steps provided in the material are: install the extension; register at ptah.live to get a free 100-day Pro trial (no credit card required); inConfigure the AI provider in the sidebar settings; run the setup wizard to analyze the workspace; start chatting, or use /orchestrate for complex tasks. There are three authentication methods: API Key (billed per token, using your own key, recommended), Provider (use hundreds of models from third-party AI providers), Auto (automatically try all configured credentials).

[Use cases] Suitable for multi-agent collaborative development in VS Code, complex engineering that requires parallel processing of subtasks, teams that want to connect to external orchestrators via the standard MCP protocol, and frontend or full-stack workspaces such as Angular, React, NestJS, and NX.

[Limitations and notes] The materials do not specify the specific supported operating systems, IDE version requirements, detailed billing prices for each authentication method, pricing details after the free trial period ends, the maximum number of agents, or performance metrics. The skill plugin currently explicitly lists the supported workspaces as Angular, React, NestJS, and NX. Licensing uses the Functional Source License 1.1 (FSL-1.1-MIT), and each version converts to a full MIT license two years after release.

Related tools

Browse category