JSPM

  • Created
  • Published
  • Downloads 139
  • Score
    100M100P100Q86717F
  • License Apache-2.0

RunCode — AI coding agent powered by 41+ models. Pay per use with USDC.

Package Exports

    This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@blockrun/runcode) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

    Readme

    RunCode

    Open-source AI coding agent. 41+ models. Pay per use with USDC.


    npm version License: Apache-2.0 TypeScript x402 Telegram


    Why RunCode?

    Claude Code Cursor Aider RunCode
    Models Claude only Mixed (limited) Bring your key 41+ models, one tool
    Pricing $200/mo subscription $20/mo + usage Free + API costs Pay per request
    Payment Credit card Credit card API keys USDC — no accounts
    Open source No No Yes Yes
    Switch models mid-session No No Yes Yes

    RunCode gives you the same agent capabilities — file editing, shell commands, web search, sub-agents — across every major model provider. You pay only for what you use, with stablecoin. No API keys to manage, no accounts to create, no subscriptions to cancel.

    Quick Start

    npm install -g @blockrun/runcode
    runcode setup base     # Create a wallet (one-time)
    runcode                # Launch — picks model interactively

    That's it. Fund the wallet address with USDC on Base, or use free models immediately.

    Features

    Agent Capabilities

    RunCode is a full coding agent with 10 built-in tools:

    Tool Description
    Read Read files with line numbers
    Write Create or overwrite files
    Edit Targeted find-and-replace edits
    Bash Run shell commands with timeout
    Glob Find files by pattern
    Grep Search file contents (uses ripgrep)
    WebSearch Search the web
    WebFetch Fetch and read web pages
    Agent Spawn sub-agents for parallel tasks
    Task Track tasks within a session

    Model Selection

    Launch with the interactive model picker, or specify directly:

    runcode                          # Interactive picker
    runcode -m sonnet                # Claude Sonnet 4.6
    runcode -m gpt                   # GPT-5.4
    runcode -m deepseek              # DeepSeek V3
    runcode -m free                  # Nemotron Ultra 253B (free)

    Switch models mid-session:

    /model              # Interactive picker
    /model flash        # Switch to Gemini 2.5 Flash
    /cost               # Check session cost
    All model shortcuts (30+)
    Shortcut Model Price (in/out per 1M)
    sonnet Claude Sonnet 4.6 $3 / $15
    opus Claude Opus 4.6 $5 / $25
    gpt GPT-5.4 $2.5 / $15
    gemini Gemini 2.5 Pro $1.25 / $10
    flash Gemini 2.5 Flash $0.15 / $0.6
    deepseek DeepSeek V3 $0.28 / $0.42
    r1 DeepSeek R1 $0.28 / $0.42
    haiku Claude Haiku 4.5 $0.8 / $4
    mini GPT-5 Mini $0.25 / $2
    nano GPT-5 Nano $0.05 / $0.4
    o3 O3 $2 / $8
    o4 O4 Mini $1.1 / $4.4
    grok Grok 3 varies
    free Nemotron Ultra 253B FREE
    devstral Devstral 2 123B FREE
    qwen-coder Qwen3 Coder 480B FREE
    maverick Llama 4 Maverick FREE

    Token Optimization

    Seven layers of automatic optimization keep context usage low and costs down:

    1. Thinking block stripping — removes old reasoning from history
    2. Tool result budgeting — caps large outputs at 50K chars with preview
    3. Microcompaction — clears old tool results (keeps last 8)
    4. Time-based cleanup — clears stale results after 60min idle
    5. Auto-compact — summarizes history when approaching context limit
    6. Adaptive max_tokens — starts at 8K, escalates to 64K on demand
    7. Prompt-too-long recovery — auto-compacts and retries up to 3x

    Permission System

    By default, read-only tools run automatically. Destructive tools (Write, Edit, Bash) prompt for permission:

      Permission required: Bash
      Execute: rm -rf node_modules
    
      Allow? [y]es / [n]o / [a]lways:

    Use --trust to skip all prompts:

    runcode --trust

    Configure rules in ~/.blockrun/runcode-permissions.json:

    {
      "allow": ["Bash(git *)"],
      "deny": ["Bash(rm -rf *)"]
    }

    Streaming Tool Execution

    Concurrent-safe tools (Read, Glob, Grep) start executing while the model is still streaming. Sequential tools (Write, Edit, Bash) wait for the full response. This reduces latency on multi-tool turns.

    Proxy Mode

    Use any model through Claude Code by running RunCode as a payment proxy. It translates between OpenAI and Anthropic formats, handles x402 payments, and adds automatic fallback when a model is unavailable.

    runcode proxy                    # Start payment proxy on :8402
    runcode proxy -m deepseek        # With default model

    One-command setup for Claude Code:

    runcode init                     # Auto-configures Claude Code + LaunchAgent

    This writes the proxy endpoint into Claude Code's config and installs a macOS LaunchAgent so the proxy starts automatically on login. Run runcode uninit to undo.

    How it works:

    Claude Code → RunCode proxy (:8402) → BlockRun API → 41+ models
                     ↓
              x402 payment (USDC)
              SSE format translation
              Auto-fallback on failure

    Payment

    RunCode uses the x402 protocol for pay-per-request payments with USDC stablecoins. No accounts, no API keys, no subscriptions.

    Supported chains:

    • Base (default) — Coinbase L2, low fees
    • Solana — also low fees

    Setup:

    runcode setup base     # or: runcode setup solana

    Fund the wallet address with USDC. Free models work without funding.

    What does it cost?

    Model ~Cost per request
    Free models (Nemotron, etc.) $0
    DeepSeek V3 ~$0.001
    Gemini Flash ~$0.001
    Claude Sonnet ~$0.01
    GPT-5.4 ~$0.01
    Claude Opus ~$0.05

    Typical usage: $5-20/month for active development.

    Commands

    Command Description
    runcode Start the agent (interactive model picker)
    runcode -m <model> Start with a specific model
    runcode --trust Start in trust mode (no permission prompts)
    runcode --debug Start with debug logging
    runcode setup [base|solana] Create payment wallet
    runcode balance Check USDC balance
    runcode models List all models with pricing
    runcode stats View usage statistics and savings
    runcode config list View configuration
    runcode proxy Run as payment proxy for Claude Code
    runcode init Auto-configure Claude Code + LaunchAgent
    runcode uninit Remove Claude Code proxy config

    Session Commands

    Command Description
    /model Interactive model picker
    /model <name> Switch model (shortcut or full ID)
    /cost Show session cost and savings
    /help List all commands
    /exit Quit

    Architecture

    src/
    ├── agent/                  # Core agent loop, LLM client, token optimization
    ├── tools/                  # 10 built-in tools (read, write, edit, bash, ...)
    ├── ui/                     # Terminal UI + model picker
    ├── proxy/                  # Payment proxy for Claude Code
    ├── router/                 # Smart model routing
    ├── commands/               # CLI commands (setup, balance, stats, ...)
    ├── wallet/                 # Wallet management
    ├── stats/                  # Usage tracking
    ├── config.ts               # Global configuration
    └── index.ts                # Entry point

    Development

    git clone https://github.com/BlockRunAI/runcode.git
    cd runcode
    npm install
    npm run build
    node dist/index.js --help

    Contributing

    Contributions are welcome. Please open an issue first to discuss what you'd like to change.

    License

    Apache License 2.0