PluginStackThinkRail
ThinkRail official site ↗Last checked against the official docs:
What it does
An open-source agentic IDE from a JetBrains incubator team, built around the pi coding agent. Each task gets its own git worktree with an editor, terminals and diff view, and you can run several agent sessions side by side with a token and cost readout for each. It keeps a spec graph in SPEC.md files, reads Agent Skills in place and connects the MCP servers in pi's mcp.json, keeping servers that a repository defines switched off until you approve them. You sign in with JetBrains AI or bring your own model provider; ThinkRail has no accounts of its own. v0.2.0 (2026-10-18) is the latest stable release; nightlies are also published. Apache-2.0.
How it is organized
- Workspaces: one git worktree per task, so parallel agents don't edit the same checkout.
- Sessions: several pi agent sessions at once, each with token usage and cost.
- Spec graph: requirements live in SPEC.md files that the agent reads and updates.
- Skills and MCP: Agent Skills are read from where they are. MCP servers come from pi's mcp.json; ThinkRail asks in the chat before tool calls a server doesn't mark read-only, unless you always allow that tool in the project.
Early-stage software
ThinkRail is at version 0.2 and published as a JetBrains incubator project, so expect changes between releases. The README says full extension support is still being added.
Who it's for
Developers who run several coding-agent tasks in parallel and want each in its own worktree with diffs and costs visible, and who are comfortable with an early-stage tool.
How to set it up
Desktop app: download it from the GitHub releases page (macOS 14 or later, Windows x64, Linux x64 or ARM64 on Ubuntu 24.04 or later). Or install the CLI on macOS or Linux:
bashcurl -fsSL https://raw.githubusercontent.com/JetBrains/thinkrail/main/install.sh | bashWindows (PowerShell):
powershellpowershell -c "irm https://raw.githubusercontent.com/JetBrains/thinkrail/main/install.ps1 | iex"Open a repository. You need git installed and a model provider (JetBrains AI sign-in or your own API key):
bashthinkrail ~/code/my-repoBasic usage events and error reports (no prompts or code, according to the README) are always sent, with an extra sharing option you can turn on. Start it with thinkrail --no-analytics or set THINKRAIL_NO_ANALYTICS=1 to stop them. The README notes the macOS CLI is signed but not notarized and the Linux builds are unsigned.
Check the official ThinkRail docs for the latest steps.
Frequently asked questions
Is it free?
The app is open source under Apache-2.0. You pay for model usage, either through a JetBrains AI subscription or your own provider's API.
What is pi?
pi is an open-source coding agent published on npm as @earendil-works/pi-coding-agent. ThinkRail runs pi sessions and adds the IDE, worktree and spec features around them, and it reads your existing pi configuration in ~/.pi/agent.
Example prompts
Create a new workspace for adding rate limiting to the API and draft a SPEC.md for it first.Run two sessions in parallel: one fixes the failing auth tests, one updates the README. Show me both diffs.Which MCP servers are configured for this workspace, and what tools do they expose?Made ThinkRail? Add the badge
If you like, show that ThinkRail is listed and hand-checked here. It's optional: listings are free and we never ask for a link back.
Get the Markdown or HTML
Markdown (for a GitHub README)
[](https://www.pluginstackai.com/plugins/thinkrail/)HTML (for a website)
<a href="https://www.pluginstackai.com/plugins/thinkrail/"><img src="https://www.pluginstackai.com/badge/hand-checked.svg" alt="Hand-checked on PluginStack" width="226" height="28"></a>Free: MCP Starter Checklist
After you set this tool up, use the one-page checklist so your next MCP server doesn't fail on first connect.
More Coding Agents
- Aider
Aider
Open-source AI pair programming in your terminal. It edits code in your local git repo and works with many LLMs (Claude, DeepSeek, OpenAI models and more).
- Anthropic
Claude Code
Anthropic's agentic coding tool. It reads your codebase, edits files, runs commands, works with git and connects to MCP servers. It runs in the terminal, with VS Code/JetBrains extensions, a desktop app and a web version too.
- OpenAI
Codex CLI
OpenAI's open-source coding agent that runs locally in your terminal. It reads and edits your code, runs commands and connects to MCP servers. Codex also comes as an IDE extension (VS Code, Cursor, Windsurf), a desktop app and a cloud version. Apache-2.0.
- Agentic AI Foundation (Linux Foundation)
goose
An open-source, general-purpose AI agent that runs on your machine as a desktop app (macOS, Linux, Windows), a CLI and an API. It isn't only for code: it also handles research, writing and automation. It supports 15+ model providers and connects to tools through MCP extensions. Originally from Block, now part of the Agentic AI Foundation. Apache-2.0.
- Anomaly
OpenCode
An open-source AI coding agent with a terminal UI, plus a desktop app (beta) and IDE support. It works with API keys from many LLM providers, and also has an optional curated model service called OpenCode Zen. It ships a full-access build agent and a read-only plan agent you switch between with Tab. The code is on GitHub at anomalyco/opencode (the older sst/opencode address redirects there). MIT licensed.
- OpenHands
OpenHands
An open-source platform for running coding agents. Its Agent Canvas app (labeled beta) is a self-hosted control center where you start agent conversations and set up automations (for example with Slack, GitHub or Linear). It runs the OpenHands agent by default and can also run Claude Code, Codex, OpenCode and other ACP-compatible agents, locally, in Docker, on VMs or in OpenHands Cloud. MIT licensed.