It ships with first-class subagents for each role — code-reviewer for severity-scored diff critique, security-reviewer for validated vulnerability findings, debugger for failure root-causing, and coder/implementer for the scoped edits that follow. All running in a single iterative loop, driven by the model of your choice, with full access to your repo, the shell, the web, and MCP tools.

It speaks the Agent Client Protocol (ACP), so it slots cleanly into ACP-aware editors like Zed and JetBrains. It loads Model Context Protocol (MCP) servers, so the same tools your other agents use just work. And it's hackable: subagents, skills, hooks, and plugins are all first-class extension points.

🎯 Review · Secure · Diagnose · then Create. One agent, one shell, one workflow. No tab-switching. No context loss. No magic.

🆕 What's New in 0.60.0

• Leaner leaf subagent prompts. All 12 built-in subagent roles now render a dedicated system_leaf.md prompt from shared Jinja partials instead of the full root system prompt, dropping root-only orchestration prose from every spawn (implementer prompt: ~7,270 → ~4,240 words) while keeping the root render byte-identical.
• Typed, fail-closed coding-artifact handoff. The <coding_artifact> contract is now rendered and extracted from a single CodingArtifact schema — exactly one end-of-message block, duplicate/undeclared keys rejected, and malformed artifacts surfaced distinctly to the judge instead of passing through as valid.
• Auto-updates never interrupt a running session. Updates are downloaded and staged with a verified manifest and applied before the next session (or at clean exit) instead of force-closing the active session mid-run; auto_update becomes a policy enum (off, notify, download, apply_on_exit) with legacy booleans still accepted, and the post-update smoke check verifies the upgraded binary and version.

Upgrade with pythinker update, pip install --upgrade pythinker-code==0.60.0, or use the native installer for your platform from the Releases page.

✨ Features

🖥️ Terminal-First

Plan, edit, run, and verify without leaving your shell. Every action is visible, scriptable, and auditable.

⚡ Shell Command Mode

Press Ctrl-X to drop into a direct shell prompt inside the agent. Run commands, then snap back into AI mode with full context preserved.

🧩 ACP IDE Integration

Run pythinker acp and any Agent Client Protocol editor — Zed, JetBrains, and more — gets a full Pythinker session inline.

🔌 MCP Tool Loading

Manage stdio and HTTP MCP servers with pythinker mcp. OAuth-backed servers, persistent config, ad-hoc files — all supported.

🤖 Subagents & Skills

Delegate focused work to built-in subagents. Load reusable instructions via /skill:<name> and bundled prompt flows via /flow:<name>. Use pythinker skill list, pythinker skill lock, and pythinker skill verify-lock to inspect project skills and pin their hashes in skills-lock.json.

🪝 Hooks & Plugins

Observe or block tool execution with hook events. Install community extensions with pythinker plugin.

🌐 Web & Visualization UIs

Optional web frontend and visualization frontend ship alongside the CLI for richer inspection workflows.

🤖 Bring Your Own Model

Swap providers and models per-session: --model openai/gpt-5.5, hosted Pythinker models, or your own keys.

📊 Local Benchmarks

Run /benchmark to execute deterministic local coding tasks through the active Pythinker session, with replayable artifacts and verification reports.

🧪 SWE-Style Fixtures

Run trusted local JSONL fixtures with /benchmark:swe --dataset <path> --trusted-dataset true when you want SWE-style task inputs without a hosted evaluator.

[!NOTE] Built-in shell commands such as cd are not yet supported in shell command mode.

⚡ Quick Start

Pythinker ships native installers for every platform. Pick the row that matches your OS — no Python, Node, or uv prerequisite.

Every artifact ships with a matching .sha256 file — verify before install on any platform with sha256sum, shasum -a 256, or Get-FileHash.

After install, on any OS:

pythinker --version            # confirm install
pythinker login                # (optional) authenticate a hosted provider
pythinker                      # start the interactive TUI

In-app updates — pythinker update queries the GitHub Releases API and re-runs the right installer for your build with SHA-256 verification. Set PYTHINKER_CLI_NO_AUTO_UPDATE=1 to disable the proactive startup check.

🪟 Windows — native installer

PythinkerSetup-0.60.0.exe is an Inno Setup wizard. Release builds are signed when Authenticode secrets are configured in CI; otherwise the installer ships unsigned. Installs per-user into %LOCALAPPDATA%\Programs\Pythinker, registers pythinker on your user PATH (HKCU\Environment), broadcasts WM_SETTINGCHANGE so new shells see the change. No UAC prompt.

# One-line install (downloads the native .exe, verifies SHA-256, runs per-user)
irm https://pythinker.com/install.ps1 | iex

# Or manually download the installer + checksum from the Releases page,
# verify with Get-FileHash, then run:
.\PythinkerSetup-0.60.0.exe

# Open a fresh PowerShell
pythinker --version

Per-machine install (IT-managed boxes): .\PythinkerSetup-0.60.0.exe /ALLUSERS installs to %ProgramFiles%\Pythinker and writes PATH to HKLM (requires admin).

Upgrade: pythinker update from inside the running app — it downloads the newest installer, verifies SHA-256, and launches the Inno installer with visible progress (/SILENT /NORESTART /CURRENTUSER /CLOSEAPPLICATIONS /NORESTARTAPPLICATIONS).

Uninstall: Apps & Features → Pythinker Code → Uninstall reverts both the files and the PATH edit.

🛡 First-launch SmartScreen warning — Until Authenticode secrets are configured in CI for a release, the installer ships unsigned and Windows shows "Windows protected your PC." Click More info → Run anyway. Use the published .sha256 as your integrity check until signing comes online.

— Homebrew tap

# 1. Install
brew install Pythoughts-labs/pythinker/pythinker-code
#    Homebr