freecodexyz /free-code
The free build of Claude Code. All telemetry removed, security-prompt guardrails stripped, all experimental features enabled.
★ 8,819⑂ 2,024👁 100⑃ 33● 13▤ 0
+2
日增长
8,819
stars
2,024
forks
100
watchers
33
prs
13
issues
0
releases
README
free-code The free build of Claude Code. All telemetry stripped. All guardrails removed. All experimental features unlocked. One binary, zero callbacks home. --- Quick Install bash curl -fsSL https://raw.githubusercontent.com/paoloanzn/free-code/main/install.sh | bash Checks your system, installs Bun if needed, clones the repo, builds with all experimental features enabled, and symlinks free-code on your PATH. Then run free-code and use the /login command to authenticate with your preferred model provider. --- Table of Contents - What is this - Model Providers - Quick Install - Requirements - Build - Usage - Experimental Features - Project Structure - Tech Stack - IPFS Mirror - Contributing - License --- What is this A clean, buildable fork of Anthropic's Claude Code CLI -- the terminal-native AI coding agent. 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: 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 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, injected "cyber risk" instruction blocks, and 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. Experimental features unlocked Claude Code ships with 88 feature flags gated behind bun:bundle compile-time switches. Most are disabled in the public npm release. This build unlocks all 54 flags that compile cleanly. See Experimental Features below, or refer to FEATURES.md for the full audit. --- Model Providers free-code supports five API providers out of the box. Set the corresponding environment variable to switch providers -- no code changes needed. Anthropic (Direct API) -- Default Use Anthropic's first-party API directly. | Model | ID | |---|---| | Claude Opus 4.6 | claude-opus-4-6 | | Claude Sonnet 4.6 | claude-sonnet-4-6 | | Claude Haiku 4.5 | claude-haiku-4-5 | OpenAI Codex Use OpenAI's Codex models for code generation. Requires a Codex subscription. | Model | ID | |---|---| | GPT-5.3 Codex (recommended) | gpt-5.3-codex | | GPT-5.4 | gpt-5.4 | | GPT-5.4 Mini | gpt-5.4-mini | bash export CLAUDE_CODE_USE_OPENAI=1 free-code AWS Bedrock Route requests through your AWS a
Top issues
#23--dangerously-skip-permissions ?2 comments · 2026-04-06#22Ban from anthropic ?2 comments · 2026-04-05#40Windows support without WSL21 comments · 2026-07-03#35支持deepseek41 comments · 2026-04-25#29Bug: "zsh: killed" on macOS Apple Silicon (M4) due to corrupted Mach-O signature in compiled binary1 comments · 2026-04-12#20Nvidia NIM OpenAI-kompatible API + Kimi K2 Integration (ANTHROPIC_BASE_URL Hack)1 comments · 2026-04-03#49How to run Claude Code free with AgentRouter0 comments · 2026-09-15#38[BUG] Free Code resubmits a tool result after a post-tool provider disconnect0 comments · 2026-06-19