@votadev/tooncode 2.2.1

package/README.md

@@ -0,0 +1,243 @@
+# ToonCode — Free AI Coding Agent CLI
+
+> **by VotaLab** | v2.0.0 | Claude Code alternative powered by free AI models
+
+```
+  ████████╗ ██████╗  ██████╗ ███╗   ██╗ ██████╗ ██████╗ ██████╗ ███████╗
+     ██║   ██║   ██║██║   ██║██╔██╗ ██║██║     ██║   ██║██║  ██║█████╗
+     ╚═╝    ╚═════╝  ╚═════╝ ╚═╝  ╚═══╝ ╚═════╝ ╚═════╝ ╚═════╝ ╚══════╝
+```
+
+ToonCode is a **free, open-source** AI coding agent that runs in your terminal. It uses free AI models (no API key needed) and provides a Claude Code-like experience with 20+ tools, multi-agent teams, browser automation, and more.
+
+---
+
+## Requirements
+
+- **Python 3.10+**
+- **Git**
+- **Node.js 16+** (optional, for npm install method)
+
+---
+
+## Installation
+
+### Method 1: One-line install (recommended)
+
+**Mac / Linux:**
+```bash
+curl -fsSL https://raw.githubusercontent.com/votalab/tooncode/main/install.sh | bash
+```
+
+**Windows (PowerShell):**
+```powershell
+irm https://raw.githubusercontent.com/votalab/tooncode/main/install.bat -OutFile install.bat; .\install.bat
+```
+
+### Method 2: Git clone (manual)
+
+```bash
+# Clone
+git clone https://github.com/votalab/tooncode.git ~/.tooncode
+
+# Install dependencies
+pip install -r ~/.tooncode/requirements.txt
+
+# Optional: Playwright for browser tool
+pip install playwright && playwright install chromium
+
+# Run
+python ~/.tooncode/tooncode.py
+```
+
+**Add to PATH (run from anywhere):**
+
+Mac/Linux — add to `~/.bashrc` or `~/.zshrc`:
+```bash
+alias tooncode="python ~/.tooncode/tooncode.py"
+```
+
+Windows — create `tooncode.cmd` in a PATH directory:
+```cmd
+@echo off
+python %USERPROFILE%\.tooncode\tooncode.py %*
+```
+
+### Method 3: npm
+
+```bash
+npm install -g tooncode
+```
+
+### Method 4: Copy the folder
+
+Just copy the entire `tooncode` folder anywhere and run:
+```bash
+cd /path/to/tooncode
+pip install -r requirements.txt
+python tooncode.py
+```
+
+---
+
+## Quick Start
+
+```bash
+tooncode                          # Start in current directory
+tooncode big-pickle              # Start with specific model
+tooncode minimax-m2.5-free ~/my-project  # Model + directory
+```
+
+---
+
+## Features
+
+### 20 Tools
+
+| Tool | Description |
+|------|-------------|
+| `bash` | Run shell commands (auto-detects PowerShell/bash) |
+| `read` | Read files with line numbers |
+| `write` | Create/overwrite files (shows diff) |
+| `edit` | String replacement in files (shows diff) |
+| `multi_edit` | Batch edits in one call |
+| `glob` | Find files by pattern |
+| `grep` | Search file contents with regex |
+| `list_dir` | Browse directory structure |
+| `web_search` | Search the web (DuckDuckGo) |
+| `web_fetch` | Fetch web page content |
+| `http` | Full HTTP client (GET/POST/PUT/DELETE + auth) |
+| `browser` | Playwright browser: open, click, fill, screenshot, console, network |
+| `screenshot` | Capture desktop/window screenshot |
+| `spawn_agent` | Spawn sub-agent (coder/reviewer/tester/researcher) |
+| `memory_save` | Save notes for future sessions |
+| `memory_search` | Search past memories |
+| `task_create/update/list` | Task management |
+| `bosshelp` | Escalate to Claude Code or fallback model |
+
+### Slash Commands
+
+| Command | Description |
+|---------|-------------|
+| `/help` | Show all commands |
+| `/model [name]` | Switch AI model |
+| `/boss <task>` | Create task plan (uses Claude Code or own model) |
+| `/team <task>` | Multi-agent team: planner + frontend + backend + reviewer + tester |
+| `/plan` | Toggle Plan Mode (read-only) |
+| `/do` | Execute pending tasks |
+| `/tasks` | Show task progress |
+| `/continue`, `/c` | Continue where AI left off |
+| `/save`, `/s` | Save session |
+| `/resume`, `/r` | Load saved session |
+| `/compact` | Compress context |
+| `/memory` | Browse saved memories |
+| `/paste`, `/v` | Send clipboard content |
+| `/send <msg>` | Chat between ToonCode windows |
+| `/bg`, `/ps` | Manage background processes |
+| `/commit` | Git add & commit |
+| `/diff` | Git diff |
+| `/status` | Git status |
+| `/undo` | Undo last file edit |
+| `/init` | Create TOONCODE.md (auto-imports CLAUDE.md etc.) |
+| `/config` | Show/edit config |
+| `/skills` | List 32 built-in skills |
+| `/cost` | Token usage stats |
+
+### Multi-Agent Team
+
+```bash
+/team สร้างเว็บ portfolio           # Default: planner + frontend + backend
+/team สร้าง API --roles planner,backend,tester   # Custom roles
+```
+
+Agents coordinate automatically via shared channel:
+- 📋 **planner** — Creates plan, assigns work
+- 🎨 **frontend** — Builds UI (HTML/CSS/JS)
+- ⚙️ **backend** — Builds API/server logic
+- 🔍 **reviewer** — Reviews code, fixes bugs
+- 🧪 **tester** — Writes & runs tests
+
+### 32 Built-in Skills
+
+```bash
+/refactor src/utils.py    # Refactor code
+/review                    # Code review
+/test api/users.js         # Generate tests
+/fix                       # Fix bugs
+/explain server.py         # Explain code
+/optimize                  # Performance optimization
+/docker                    # Create Dockerfile
+/commit                    # Smart git commit
+/audit                     # Security audit
+```
+
+### Available Models
+
+| Model | Context | Notes |
+|-------|---------|-------|
+| `minimax-m2.5-free` | 200K | Default, good all-round |
+| `big-pickle` | 200K | Strong coding |
+| `nemotron-3-super-free` | 131K | Fast |
+| `gpt-5-nano` | 1M | Largest context |
+
+Auto-fallback: if a model fails, ToonCode automatically tries the next one.
+
+---
+
+## Project Context
+
+ToonCode auto-reads these files from your project:
+- `TOONCODE.md` — ToonCode project context
+- `CLAUDE.md` — Claude Code context (auto-imported)
+- `GEMINI.md` — Gemini context
+- `.cursorrules` — Cursor rules
+- `COPILOT.md` — Copilot instructions
+
+Run `/init` to auto-create `TOONCODE.md` with imported content.
+
+---
+
+## Browser Tool
+
+Requires Playwright:
+```bash
+pip install playwright && playwright install chromium
+```
+
+AI can control a real browser:
+```
+❯ เปิด google ค้นหา "ToonCode" แล้วสรุปผลลัพธ์
+
+AI → browser open https://google.com/search?q=ToonCode
+AI → browser text  (reads search results)
+AI → browser console  (checks JS errors)
+AI → browser screenshot  (captures page)
+```
+
+---
+
+## Update
+
+```bash
+cd ~/.tooncode && git pull
+```
+
+---
+
+## Cross-Platform
+
+| Feature | Windows | Mac | Linux |
+|---------|:-------:|:---:|:-----:|
+| All tools | ✅ | ✅ | ✅ |
+| Shell | PowerShell | bash | bash |
+| Screenshot | ImageGrab | screencapture | scrot |
+| Clipboard | Get-Clipboard | pbpaste | xclip |
+| Browser | ✅ | ✅ | ✅ |
+
+---
+
+## License
+
+MIT — Free to use, modify, and distribute.
+
+**Made with ❤️ by VotaLab**

package/__main__.py

@@ -0,0 +1,2 @@
+from tooncode import main
+main()

package/bin/postinstall.js

@@ -0,0 +1,81 @@
+#!/usr/bin/env node
+const { execSync } = require("child_process");
+const path = require("path");
+const fs = require("fs");
+
+const C = "\x1b[36m", G = "\x1b[32m", Y = "\x1b[33m", D = "\x1b[2m", X = "\x1b[0m";
+console.log(`\n${C}ToonCode${X} — Installing...\n`);
+
+function findPython() {
+  const cmds = process.platform === "win32" ? ["python", "python3", "py"] : ["python3", "python"];
+  for (const cmd of cmds) {
+    try {
+      const r = execSync(`${cmd} --version 2>&1`, { encoding: "utf-8" });
+      if (r.includes("Python 3")) return cmd;
+    } catch {}
+  }
+  return null;
+}
+
+function getVenvDir() {
+  return path.join(__dirname, "..", ".venv");
+}
+
+function getVenvPython() {
+  const venvDir = getVenvDir();
+  return process.platform === "win32"
+    ? path.join(venvDir, "Scripts", "python.exe")
+    : path.join(venvDir, "bin", "python");
+}
+
+function ensureVenv(python) {
+  const venvDir = getVenvDir();
+  const venvPy = getVenvPython();
+  if (!fs.existsSync(venvPy)) {
+    console.log(`${D}Creating virtual environment...${X}`);
+    execSync(`${python} -m venv "${venvDir}"`, { stdio: "pipe", timeout: 60000 });
+  }
+  return venvPy;
+}
+
+const python = findPython();
+if (!python) {
+  console.log(`${Y}Python 3.10+ not found. Install: https://python.org${X}\n`);
+  process.exit(0);
+}
+console.log(`${D}Python: ${python}${X}`);
+
+const req = path.join(__dirname, "..", "requirements.txt");
+if (!fs.existsSync(req)) { process.exit(0); }
+
+// Strategy 1: venv inside package (works on all OS)
+try {
+  const venvPy = ensureVenv(python);
+  console.log(`${D}Installing into venv...${X}`);
+  execSync(`"${venvPy}" -m pip install --quiet -r "${req}"`, {
+    stdio: ["ignore", "pipe", "pipe"], timeout: 120000
+  });
+  console.log(`${G}Dependencies installed (venv).${X}`);
+  console.log(`\n${G}ToonCode ready!${X} Run: ${C}tooncode${X}\n`);
+  process.exit(0);
+} catch (e) {
+  console.log(`${D}venv failed, trying system pip...${X}`);
+}
+
+// Strategy 2: system pip fallbacks
+const pipCmds = [
+  `${python} -m pip install --user --quiet --break-system-packages -r "${req}"`,
+  `${python} -m pip install --user --quiet -r "${req}"`,
+  `${python} -m pip install --quiet -r "${req}"`,
+];
+for (const cmd of pipCmds) {
+  try {
+    execSync(cmd, { stdio: ["ignore", "pipe", "pipe"], timeout: 120000 });
+    console.log(`${G}Dependencies installed (system).${X}`);
+    console.log(`\n${G}ToonCode ready!${X} Run: ${C}tooncode${X}\n`);
+    process.exit(0);
+  } catch {}
+}
+
+console.log(`${Y}Auto-install failed. Run manually:${X}`);
+console.log(`${C}  pip install --user httpx rich prompt_toolkit${X}\n`);

package/bin/tooncode.js

@@ -0,0 +1,104 @@
+#!/usr/bin/env node
+const { spawn, execSync } = require("child_process");
+const path = require("path");
+const fs = require("fs");
+
+const R = "\x1b[31m", G = "\x1b[32m", C = "\x1b[36m", D = "\x1b[2m", X = "\x1b[0m";
+
+function findPython() {
+  const cmds = process.platform === "win32" ? ["python", "python3", "py"] : ["python3", "python"];
+  for (const cmd of cmds) {
+    try {
+      const r = execSync(`${cmd} --version 2>&1`, { encoding: "utf-8" });
+      if (r.includes("Python 3")) return cmd;
+    } catch {}
+  }
+  return null;
+}
+
+function getVenvPython() {
+  const venvDir = path.join(__dirname, "..", ".venv");
+  return process.platform === "win32"
+    ? path.join(venvDir, "Scripts", "python.exe")
+    : path.join(venvDir, "bin", "python");
+}
+
+function checkDeps(py) {
+  try {
+    execSync(`"${py}" -c "import httpx, rich, prompt_toolkit" 2>&1`, { encoding: "utf-8" });
+    return true;
+  } catch { return false; }
+}
+
+function ensureVenv(sysPython) {
+  const venvDir = path.join(__dirname, "..", ".venv");
+  const venvPy = getVenvPython();
+  if (!fs.existsSync(venvPy)) {
+    console.log(`${C}Creating virtual environment...${X}`);
+    execSync(`${sysPython} -m venv "${venvDir}"`, { stdio: "pipe", timeout: 60000 });
+  }
+  return venvPy;
+}
+
+function installDeps(py) {
+  const req = path.join(__dirname, "..", "requirements.txt");
+  console.log(`${D}Installing dependencies...${X}`);
+  execSync(`"${py}" -m pip install --quiet -r "${req}"`, {
+    stdio: ["ignore", "pipe", "pipe"], timeout: 120000
+  });
+}
+
+// Find system Python
+const sysPython = findPython();
+if (!sysPython) {
+  console.error(`${R}Python 3.10+ required. Install: https://python.org${X}`);
+  process.exit(1);
+}
+
+// Determine which Python to use (prefer venv)
+let usePython;
+const venvPy = getVenvPython();
+
+if (fs.existsSync(venvPy) && checkDeps(venvPy)) {
+  // venv exists and has deps
+  usePython = venvPy;
+} else if (checkDeps(sysPython)) {
+  // system Python has deps
+  usePython = sysPython;
+} else {
+  // Need to install — try venv first
+  console.log(`${C}First run — setting up...${X}`);
+  try {
+    const vp = ensureVenv(sysPython);
+    installDeps(vp);
+    usePython = vp;
+    console.log(`${G}Ready.${X}\n`);
+  } catch {
+    // venv failed, try system pip
+    const fallbacks = [
+      `${sysPython} -m pip install --user --quiet --break-system-packages -r "${path.join(__dirname, "..", "requirements.txt")}"`,
+      `${sysPython} -m pip install --user --quiet -r "${path.join(__dirname, "..", "requirements.txt")}"`,
+    ];
+    let ok = false;
+    for (const cmd of fallbacks) {
+      try { execSync(cmd, { stdio: ["ignore", "pipe", "pipe"], timeout: 120000 }); ok = true; break; } catch {}
+    }
+    if (ok) {
+      usePython = sysPython;
+    } else {
+      console.error(`${R}Could not install dependencies.${X}`);
+      console.error(`${C}  ${sysPython} -m pip install httpx rich prompt_toolkit${X}`);
+      process.exit(1);
+    }
+  }
+}
+
+// Run tooncode
+const mainPy = path.join(__dirname, "..", "tooncode.py");
+const child = spawn(usePython, [mainPy, ...process.argv.slice(2)], {
+  stdio: "inherit",
+  cwd: process.cwd(),
+  env: { ...process.env, PYTHONIOENCODING: "utf-8" },
+});
+child.on("exit", (code) => process.exit(code || 0));
+child.on("error", (err) => { console.error(err.message); process.exit(1); });

package/package.json

@@ -0,0 +1,42 @@
+{
+  "name": "@votadev/tooncode",
+  "version": "2.2.1",
+  "description": "Free AI Coding Agent CLI — Claude Code alternative powered by free models. 20 tools, multi-agent team, browser automation, MCP servers.",
+  "author": "VotaLab",
+  "license": "MIT",
+  "keywords": [
+    "ai",
+    "coding",
+    "agent",
+    "cli",
+    "claude",
+    "free",
+    "tooncode",
+    "copilot",
+    "cursor"
+  ],
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/votalab/tooncode.git"
+  },
+  "homepage": "https://github.com/votalab/tooncode#readme",
+  "bin": {
+    "tooncode": "bin/tooncode.js"
+  },
+  "files": [
+    "bin/",
+    "tooncode.py",
+    "__main__.py",
+    "skills/",
+    "requirements.txt",
+    "setup.py",
+    "tooncode.cmd",
+    "README.md"
+  ],
+  "scripts": {
+    "postinstall": "node bin/postinstall.js"
+  },
+  "engines": {
+    "node": ">=16"
+  }
+}

package/requirements.txt

@@ -0,0 +1,4 @@
+httpx>=0.27.0
+rich>=13.0.0
+prompt_toolkit>=3.0.0
+textual>=1.0.0

package/setup.py

@@ -0,0 +1,22 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="tooncode",
+    version="2.0.0",
+    description="AI Coding Agent CLI - Free, single-file, Claude Code alternative",
+    author="VotaLab",
+    py_modules=["tooncode", "tui"],
+    python_requires=">=3.10",
+    install_requires=[
+        "httpx>=0.27.0",
+        "rich>=13.0.0",
+        "prompt_toolkit>=3.0.0",
+        "textual>=1.0.0",
+    ],
+    entry_points={
+        "console_scripts": [
+            "tooncode=tooncode:main",
+            "tooncode-tui=tui:ToonCodeApp.run",
+        ],
+    },
+)

package/skills/api/endpoint.md

@@ -0,0 +1,16 @@
+---
+name: endpoint
+description: Create a new API endpoint
+---
+
+Create API endpoint: {{input}}
+
+1. Detect framework (FastAPI, Express, Gin, etc.)
+2. Create the endpoint with:
+   - Route handler with proper HTTP method
+   - Input validation (Pydantic, Zod, etc.)
+   - Error handling with proper status codes
+   - Response serialization
+3. Add to router/app
+4. Write tests for the endpoint
+5. Update API docs if applicable

package/skills/api/mock.md

@@ -0,0 +1,15 @@
+---
+name: mock
+description: Generate mock API server or test doubles
+---
+
+Create mocks for: {{input}}
+
+1. Read the API/interface definitions
+2. Generate:
+   - Mock server (for frontend dev)
+   - Test doubles (for unit tests)
+   - Fixture data (realistic responses)
+3. Match the real API contract exactly
+4. Include: success responses, error responses, edge cases
+5. Make configurable (delay, error rate, custom responses)

package/skills/arch/diagram.md

@@ -0,0 +1,14 @@
+---
+name: diagram
+description: Generate architecture diagram (Mermaid)
+---
+
+Analyze the project and generate architecture diagrams in Mermaid format:
+
+1. Read project structure and imports
+2. Generate diagrams:
+   - **System overview** - components and their connections
+   - **Data flow** - how data moves through the system
+   - **Class/module diagram** - key classes and relationships
+3. Output as Mermaid code blocks (renders in GitHub/VS Code)
+4. Keep it high-level and readable

package/skills/arch/pattern.md

@@ -0,0 +1,15 @@
+---
+name: pattern
+description: Apply a design pattern to code
+---
+
+Apply design pattern: {{input}}
+
+1. Analyze current code structure
+2. Identify which pattern fits (or use the one specified):
+   - Creational: Factory, Builder, Singleton
+   - Structural: Adapter, Decorator, Facade
+   - Behavioral: Observer, Strategy, Command
+3. Refactor to apply the pattern
+4. Explain: why this pattern, what problem it solves
+5. Show before/after comparison

package/skills/arch/split.md

@@ -0,0 +1,16 @@
+---
+name: split
+description: Split large file into modules
+---
+
+Split {{input}} into smaller modules:
+
+1. Analyze the file - identify logical groups of functions/classes
+2. Plan the split:
+   - Group by responsibility (single responsibility principle)
+   - Identify shared utilities
+   - Map dependencies between groups
+3. Create new files with proper names
+4. Move code, update all imports
+5. Verify nothing is broken (run tests or import check)
+6. Show the new structure

package/skills/code/convert.md

@@ -0,0 +1,15 @@
+---
+name: convert
+description: Convert code between languages
+---
+
+Convert: {{input}}
+
+1. Read the source code
+2. Convert to the target language preserving:
+   - Logic and algorithm
+   - Error handling patterns
+   - Naming conventions (adapt to target language style)
+   - Comments explaining non-obvious parts
+3. Use idiomatic patterns of the target language
+4. Write the converted file

package/skills/code/deps.md

@@ -0,0 +1,15 @@
+---
+name: deps
+description: Analyze and manage dependencies
+---
+
+Analyze dependencies in this project:
+
+1. List all dependencies and their versions
+2. Check for:
+   - Outdated packages (major/minor/patch)
+   - Known vulnerabilities (npm audit / pip-audit / cargo audit)
+   - Unused dependencies
+   - Missing dependencies
+3. Suggest updates with risk assessment
+4. If {{input}} = "update": apply safe updates (patch/minor only)

package/skills/code/explain.md

@@ -0,0 +1,13 @@
+---
+name: explain
+description: Explain code in detail
+---
+
+Read {{input}} and explain:
+- What it does (high level overview)
+- How it works (step by step walkthrough)
+- Key design decisions and patterns used
+- Dependencies and integrations
+- Potential gotchas or known limitations
+
+Keep it clear for someone new to the codebase.

package/skills/code/lint.md

@@ -0,0 +1,23 @@
+---
+name: lint
+description: Lint and auto-fix code (auto-detect or specify)
+---
+
+Lint target: {{input}}
+
+## If a file was specified:
+Lint that specific file.
+
+## If nothing specified (auto-detect):
+1. Detect project language from files present
+2. Find the linter config or use defaults
+3. Lint entire project
+
+## Actions:
+- Python: run `ruff check --fix .` then `ruff format .` (or black/isort)
+- JS/TS: run `eslint --fix .` then `prettier --write .`
+- Go: run `gofmt -w .` then `go vet ./...`
+- Rust: run `cargo clippy --fix`
+
+If linter not installed, fix issues manually by reading files and applying style fixes.
+Report: fixed count, remaining issues that need manual fix.

package/skills/code/optimize.md

@@ -0,0 +1,11 @@
+---
+name: optimize
+description: Optimize code for performance
+---
+
+Analyze {{input}} for performance:
+1. Profile / identify bottlenecks
+2. Check: unnecessary loops, N+1 queries, memory leaks, blocking calls
+3. Suggest optimizations with expected impact
+4. Implement the changes
+5. Benchmark before/after if possible