The Open-Source AI Coding Agent That Outperforms Claude Code

Features | Swarms | Installation | Quick Start | SDK | Docs | Contributing

LevelCode is an open-source AI coding assistant that edits your codebase through natural language instructions. Unlike single-model tools, LevelCode coordinates specialized agents that work together to understand your project and make precise changes.

LevelCode beats Claude Code at 61% vs 53% on our evaluations across 175+ coding tasks over multiple open-source repos that simulate real-world tasks.

When you ask LevelCode to "add authentication to my API," it coordinates:

1. File Picker Agent - Scans your codebase to understand the architecture and find relevant files
2. Planner Agent - Plans which files need changes and in what order
3. Editor Agent - Makes precise, contextual edits
4. Reviewer Agent - Validates changes before applying

This multi-agent approach delivers:

• Better context understanding
• More accurate edits
• Fewer errors compared to single-model tools

Unlike Claude Code which locks you into Anthropic's models, LevelCode supports any model on OpenRouter:

• Claude (Opus, Sonnet, Haiku)
• GPT-4o, GPT-5
• DeepSeek (V3, Coder)
• Qwen (Coder, 2.5)
• Gemini (Pro, Flash)
• Llama 3.3, Mistral
• And 200+ more models...

Build LevelCode into your applications with our production-ready SDK:

import { LevelCodeClient } from '@levelcode/sdk';

const client = new LevelCodeClient({
  apiKey: process.env.OPENROUTER_API_KEY, // or ANTHROPIC_API_KEY
  cwd: '/path/to/project',
});

const result = await client.run({
  agent: 'base',
  prompt: 'Add error handling to all API endpoints',
  handleEvent: (event) => console.log(event),
});

Create your own specialized agents with TypeScript generators:

export default {
  id: 'git-committer',
  displayName: 'Git Committer',
  model: 'openai/gpt-4o',
  toolNames: ['read_files', 'run_terminal_command', 'end_turn'],

  instructionsPrompt:
    'Create meaningful git commits by analyzing changes and crafting clear commit messages.',

  async *handleSteps() {
    yield { tool: 'run_terminal_command', command: 'git diff' };
    yield { tool: 'run_terminal_command', command: 'git log --oneline -5' };
    yield 'STEP_ALL';
  },
};

Scale beyond a single agent. LevelCode's Agent Swarm system lets you spin up an entire coordinated development team that works together on complex tasks -- each agent with a specialized role, communicating through a structured message protocol.

# Enable swarms
levelcode
> /team:enable

# Create a team with a project brief
> /team:create name="auth-team" brief="Build OAuth2 login with Google and GitHub providers"

# Monitor your swarm in real time
> /team:status

The swarm system automatically assigns agents to the right development phase and coordinates handoffs between them:

See the full Agent Swarms Guide for configuration, role definitions, custom team templates, and advanced workflows.

# Using npm (recommended)
npm install -g @levelcode/cli

# Using npx (no install needed)
npx @levelcode/cli

# Using bun
bun install -g @levelcode/cli

# Using npm
npm install @levelcode/sdk

# Using bun
bun add @levelcode/sdk

# Clone the repository
git clone https://github.com/yethikrishna/levelcode.git
cd levelcode

# Install dependencies
bun install

# Run in development mode
bun dev

• Node.js 18+ or Bun 1.3.5+
• Git (optional, for version control features)
• Terminal with ANSI color support

LevelCode works fully standalone — no backend server, no account, no login required. Just set your API key and start coding.

Choose one of the following:

# Option A: OpenRouter (200+ models including Claude, GPT, Gemini, DeepSeek, etc.)
export OPENROUTER_API_KEY="sk-or-v1-..."

# Option B: Anthropic (Claude models directly)
export ANTHROPIC_API_KEY="sk-ant-..."

Get your key from OpenRouter or Anthropic.

# Navigate to your project
cd your-project

# Start LevelCode
levelcode

That's it. No sign-up, no backend, no configuration needed.

Just tell LevelCode what you want:

• "Fix the SQL injection vulnerability in user registration"
• "Add rate limiting to all API endpoints"
• "Refactor the database connection code for better performance"
• "Add unit tests for the authentication module"

LevelCode will find the right files, make changes across your codebase, and validate everything works.

# Use FREE mode (lightweight, lower cost)
levelcode --free

# Use MAX mode (most capable)
levelcode --max

# Run in a specific directory
levelcode --cwd /path/to/project

# Continue a previous conversation
levelcode --continue

# Show all options
levelcode --help

import { LevelCodeClient } from '@levelcode/sdk';

// Works standalone — just provide your API key
const client = new LevelCodeClient({
  apiKey: process.env.OPENROUTER_API_KEY, // or ANTHROPIC_API_KEY
  cwd: process.cwd(),
});

// Run a coding task
const result = await client.run({
  agent: 'base',
  prompt: 'Add TypeScript types to all function parameters',
  handleEvent: (event) => {
    if (event.type === 'file_edit') {
      console.log(`Edited: ${event.filePath}`);
    }
  },
});

console.log('Output:', result.output);

import { LevelCodeClient, AgentDefinition } from '@levelcode/sdk';

const codeReviewer: AgentDefinition = {
  id: 'code-reviewer',
  displayName: 'Code Reviewer',
  model: 'anthropic/claude-3-opus',
  toolNames: ['read_files', 'grep', 'end_turn'],
  instructionsPrompt: `You are a senior code reviewer.
    Focus on security, performance, and maintainability.
    Provide actionable feedback with code examples.`,
};

const client = new LevelCodeClient({ apiKey: '...' });

const review = await client.run({
  agent: 'code-reviewer',
  agentDefinitions: [codeReviewer],
  prompt: 'Review the recent changes in src/auth/',
  handleEvent: console.log,
});

# .github/workflows/levelcode-review.yml
name: AI Code Review

on: [pull_request]

jobs:
  review:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Setup Bun
        uses: oven-sh/setup-bun@v1

      - name: Install LevelCode
        run: bun install -g @levelcode/cli

      - name: Run AI Review
        env:
          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
        run: levelcode "Review changes and suggest improvements" --output review.md

      - name: Post Review
        uses: actions/github-script@v7
        with:
          script: |
            const review = require('fs').readFileSync('review.md', 'utf8');
            github.rest.issues.createComment({
              issue_number: context.issue.number,
              owner: context.repo.owner,
              repo: context.repo.repo,
              body: review
            });

levelcode/
├── cli/                 # Terminal UI application
│   ├── src/            # CLI source code
│   ├── bin/            # CLI binaries
│   └── scripts/        # Build scripts
├── sdk/                 # TypeScript SDK
│   ├── src/            # SDK source code
│   └── e2e/            # End-to-end tests
├── agents/              # Multi-agent system
│   ├── base2/          # Base agent configurations
│   ├── editor/         # Code editing agents
│   ├── file-explorer/  # File discovery agents
│   ├── researcher/     # Documentation research
│   ├── reviewer/       # Code review agents
│   └── thinker/        # Planning agents
├── common/             # Shared utilities
├── packages/           # Internal packages
│   ├── agent-runtime/  # Agent execution runtime
│   └── internal/       # Internal utilities
├── web/                # Web dashboard (optional)
├── evals/              # Evaluation benchmarks
└── docs/               # Documentation

Create a levelcode.config.ts in your project root:

import { defineConfig } from '@levelcode/sdk';

export default defineConfig({
  // Default model
  model: 'anthropic/claude-3.5-sonnet',

  // Per-agent model overrides
  agents: {
    editor: {
      model: 'anthropic/claude-3-opus',
      maxTokens: 8000,
    },
    filePicker: {
      model: 'anthropic/claude-3-haiku',
    },
  },

  // Files to ignore
  ignore: [
    'node_modules/**',
    '*.lock',
    'dist/**',
    '.git/**',
  ],

  // Custom tools (optional)
  tools: [],
});

Standalone Mode: LevelCode runs fully standalone by default. No backend server, database, or account is needed. Just set one API key above and you're ready to go.

Hosted Mode: For team features, billing, and the agent marketplace, visit levelcode.ai.

We love contributions from the community! Whether you're fixing bugs, creating agents, or improving docs.

# Clone the repo
git clone https://github.com/yethikrishna/levelcode.git
cd levelcode

# Install dependencies
bun install

# Run in development mode
bun dev

# Run tests
bun test

# Type check
bun typecheck

• Bug Fixes - Help us squash bugs
• New Agents - Create specialized agents for specific tasks
• Model Support - Add new model provider integrations
• Documentation - Improve guides and examples
• Benchmarks - Add new evaluation tasks

See CONTRIBUTING.md for detailed guidelines.

• Standalone Mode (no backend required)
• Direct OpenRouter/Anthropic API support
• VS Code Extension
• JetBrains Plugin
• Web Interface
• Team Collaboration
• Self-Hosted Server Mode
• Plugin Marketplace

• Issues: GitHub Issues
• Discussions: GitHub Discussions
• Email: yethikrishnarcvn7a@gmail.com

LevelCode is open-source software licensed under the Apache License 2.0.

• Inspired by Claude Code, Aider, and Continue
• Powered by models from OpenRouter
• Thanks to all our contributors

Created by Yethikrishna R

If you find LevelCode useful, please consider giving it a star!