README.md

versperclaw

The free build of Claude Code.

All telemetry stripped. All injected security-prompt guardrails removed. All experimental features unlocked. One binary, zero callbacks home.

curl -fsSL https://raw.githubusercontent.com/paoloanzn/free-code/main/install.sh | bash

Checks your system, installs Bun if needed, clones, builds with all features enabled, and puts versperclaw on your PATH. Then just export ANTHROPIC_API_KEY="sk-ant-..." and run versperclaw.

---

Local model

nvim ~/.bashrc


 export ANTHROPIC_BASE_URL="http://localhost:11434/v1"
   export ANTHROPIC_API_KEY="ollama"
   export ANTHROPIC_MODEL="qwen2.5-coder:7b"


export ANTHROPIC_BETALOG_MAX_TOKENS=98304

claude() {
  ANTHROPIC_BASE_URL="http://127.0.0.1:8001" \
    ANTHROPIC_API_KEY="dummy" \
    CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1 \
    cli-dev --bare --model "Qwen3.5-9B.Q4_K_M.gguf"
}

Telegram

/telegram

Auto-Mode

shift-tab can cycle change mode

./cli-dev auto-mode config

{
  "allow": [
    "Running read-only shell commands (ls, cat, head, tail, wc, echo, env, which, whereis, uname, date, whoami, pwd, stat, file, du, df, free, top -b -n 1, ps)",
    "Running version and help commands (node --version, python --version, ruby --version, go version, rustc --version, cargo --version, npm --version, bun --version, git --version, --help flags)",
    "Running git read-only commands (git status, git log, git diff, git show, git branch, git tag, git remote, git stash list, git config --list --local)",
    "Running tests, linters, formatters, and build commands within the project (npm test, npm run lint, npm run build, bun test, cargo test, go test, pytest, jest, vitest, eslint, prettier, biome, tsc)",
    "Running package install commands within the project (npm install, yarn, pnpm install, bun install, pip install within a virtual environment, cargo build)",
    "Reading, writing, creating, editing, and moving files within the current working directory",
    "Running common development tools (node, python, ruby, go, cargo, make, cmake, gcc, clang) for compilation and execution of project code",
    "Running Docker commands for building and running project containers (docker build, docker run, docker compose)",
    "Creating and switching git branches, committing, stashing (git checkout -b, git commit, git add, git stash)"
  ],
  "soft_deny": [
    "Downloading and executing untrusted code from the internet (curl | bash, wget | sh, pip install from unverified URLs, npx from unknown packages)",
    "Recursive force deletion of directories or files (rm -rf, Remove-Item -Recurse -Force) unless the user explicitly requested it",
    "Modifying shell profiles, login scripts, or system startup items (.bashrc, .zshrc, .profile, cron jobs, launch agents/daemons)",
    "Using sudo, su, or doas for privilege escalation unless the user explicitly mentions needing it",
    "Starting network servers or listeners that accept external connections (python -m http.server, nc -l, ng serve --host 0.0.0.0)",
    "Disabling security tools, modifying firewall rules, changing file permissions to world-writable on sensitive paths",
    "Pushing to git remotes, force-pushing, modifying remote branches",
    "Exporting, printing, or logging secrets, API keys, tokens, or credentials to public or shared locations",
    "Installing system-level packages outside the project (apt-get install, brew install, yum install as root)",
    "Modifying files outside the current working directory and standard config paths without explicit user request"
  ],
  "environment": [
    "The agent operates within a terminal session in the user's project directory",
    "The user has chosen auto mode, meaning they trust the agent to perform routine development tasks autonomously",
    "Standard development tools (git, node, python, etc.) are expected to be available",
    "The project may use any common language or framework"
  ]
}

What is this

This is a clean, buildable fork of Anthropic's Claude Code CLI -- the terminal-native AI coding agent, now called VersperClaw. The upstream source became publicly available on March 31, 2026 through a source map exposure in the npm distribution.

This fork applies three categories of changes on top of that snapshot:

1. Telemetry removed

The upstream binary phones home through OpenTelemetry/gRPC, GrowthBook analytics, Sentry error reporting, and custom event logging. In this build:

• All outbound telemetry endpoints are dead-code-eliminated or stubbed
• GrowthBook feature flag evaluation still works locally (needed for runtime feature gates) but does not report back
• No crash reports, no usage analytics, no session fingerprinting

2. Security-prompt guardrails removed

Anthropic injects system-level instructions into every conversation that constrain Claude's behavior beyond what the model itself enforces. These include:

• Hardcoded refusal patterns for certain categories of prompts
• Injected "cyber risk" instruction blocks
• Managed-settings security overlays pushed from Anthropic's servers

This build strips those injections. The model's own safety training still applies -- this just removes the extra layer of prompt-level restrictions that the CLI wraps around it.

3. Experimental features enabled

Claude Code ships with dozens of feature flags gated behind bun:bundle compile-time switches. Most are disabled in the public npm release. This build unlocks all 45+ flags that compile cleanly, including:

Feature	What it does
ULTRAPLAN	Remote multi-agent planning on VersperClaw web (Opus-class)
ULTRATHINK	Deep thinking mode -- type "ultrathink" to boost reasoning effort
VOICE_MODE	Push-to-talk voice input and dictation
AGENT_TRIGGERS	Local cron/trigger tools for background automation
BRIDGE_MODE	IDE remote-control bridge (VS Code, JetBrains)
TOKEN_BUDGET	Token budget tracking and usage warnings
BUILTIN_EXPLORE_PLAN_AGENTS	Built-in explore/plan agent presets
VERIFICATION_AGENT	Verification agent for task validation
BASH_CLASSIFIER	Classifier-assisted bash permission decisions
EXTRACT_MEMORIES	Post-query automatic memory extraction
HISTORY_PICKER	Interactive prompt history picker
MESSAGE_ACTIONS	Message action entrypoints in the UI
QUICK_SEARCH	Prompt quick-search
SHOT_STATS	Shot-distribution stats
COMPACTION_REMINDERS	Smart reminders around context compaction
CACHED_MICROCOMPACT	Cached microcompact state through query flows

See FEATURES.md for the full audit of all 88 flags and their status.

---

Quick install

curl -fsSL https://raw.githubusercontent.com/paoloanzn/free-code/main/install.sh | bash

This will check your system, install Bun if needed, clone the repo, build the binary with all experimental features enabled, and symlink it as versperclaw on your PATH.

After install, just run:

export ANTHROPIC_API_KEY="sk-ant-..."
versperclaw

---

Requirements

• Bun >= 1.3.11
• macOS or Linux (Windows via WSL)
• An Anthropic API key (set ANTHROPIC_API_KEY in your environment)

# Install Bun if you don't have it
curl -fsSL https://bun.sh/install | bash

---

Build

# Clone the repo
git clone https://github.com/paoloanzn/claude-code.git
cd claude-code

# Install dependencies
bun install

# Standard build -- produces ./cli
bun run build

# Dev build -- dev version stamp, experimental GrowthBook key
bun run build:dev

# Dev build with ALL experimental features enabled -- produces ./cli-dev
bun run build:dev:full

# Compiled build (alternative output path) -- produces ./dist/cli
bun run compile

Build variants

Command	Output	Features	Notes
bun run build	./cli	VOICE_MODE only	Production-like binary
bun run build:dev	./cli-dev	VOICE_MODE only	Dev version stamp
bun run build:dev:full	./cli-dev	All 45+ experimental flags	The full unlock build
bun run compile	./dist/cli	VOICE_MODE only	Alternative output directory

Individual feature flags

You can enable specific flags without the full bundle:

# Enable just ultraplan and ultrathink
bun run ./scripts/build.ts --feature=ULTRAPLAN --feature=ULTRATHINK

# Enable a specific flag on top of the dev build
bun run ./scripts/build.ts --dev --feature=BRIDGE_MODE

---

Run

# Run the built binary directly
./cli

# Or the dev binary
./cli-dev

# Or run from source without compiling (slower startup)
bun run dev

# Set your API key
export ANTHROPIC_API_KEY="sk-ant-..."

# Or use Claude.ai OAuth
./cli /login

Quick test

# One-shot mode
./cli -p "what files are in this directory?"

# Interactive REPL (default)
./cli

# With specific model
./cli --model claude-sonnet-4-6-20250514

---

Project structure

scripts/
  build.ts              # Build script with feature flag system

src/
  entrypoints/cli.tsx   # CLI entrypoint
  commands.ts           # Command registry (slash commands)
  tools.ts              # Tool registry (agent tools)
  QueryEngine.ts        # LLM query engine
  screens/REPL.tsx      # Main interactive UI

  commands/             # /slash command implementations
  tools/                # Agent tool implementations (Bash, Read, Edit, etc.)
  components/           # Ink/React terminal UI components
  hooks/                # React hooks
  services/             # API client, MCP, OAuth, analytics
  state/                # App state store
  utils/                # Utilities
  skills/               # Skill system
  plugins/              # Plugin system
  bridge/               # IDE bridge
  voice/                # Voice input
  tasks/                # Background task management

---

Tech stack

Runtime	Bun
Language	TypeScript
Terminal UI	React + Ink
CLI parsing	Commander.js
Schema validation	Zod v4
Code search	ripgrep (bundled)
Protocols	MCP, LSP
API	Anthropic Messages API

---

IPFS Mirror

A full copy of this repository is permanently pinned on IPFS via Filecoin:

• CID: bafybeiegvef3dt24n2znnnmzcud2vxat7y7rl5ikz7y7yoglxappim54bm
• Gateway: https://w3s.link/ipfs/bafybeiegvef3dt24n2znnnmzcud2vxat7y7rl5ikz7y7yoglxappim54bm

If this repo gets taken down, the code lives on.

---

License

The original Claude Code source is the property of Anthropic. This fork exists because the source was publicly exposed through their npm distribution. Use at your own discretion.