[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74764":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":16,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":10,"archived":19,"fork":20,"defaultBranch":21,"hasWiki":20,"hasPages":20,"topics":22,"createdAt":10,"pushedAt":10,"updatedAt":23,"readmeContent":24,"aiSummary":25,"trendingCount":16,"starSnapshotCount":16,"syncStatus":26,"lastSyncTime":27,"discoverSource":28},74764,"free-code","paoloanzn\u002Ffree-code","paoloanzn","The free build of Claude Code. All telemetry removed, security-prompt guardrails stripped, all experimental features enabled.","https:\u002F\u002Fx.com\u002Fpaoloanzn\u002Fstatus\u002F2039022418698907949?s=20",null,"TypeScript",8379,1990,105,8,0,69,69.8,true,false,"main",[],"2026-06-12 04:01:15","\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fscreenshot.png\" alt=\"free-code\" width=\"720\" \u002F>\n\u003C\u002Fp>\n\n\u003Ch1 align=\"center\">free-code\u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n  \u003Cstrong>The free build of Claude Code.\u003C\u002Fstrong>\u003Cbr>\n  All telemetry stripped. All guardrails removed. All experimental features unlocked.\u003Cbr>\n  One binary, zero callbacks home.\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"#quick-install\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Finstall-one--liner-blue?style=flat-square\" alt=\"Install\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fpaoloanzn\u002Ffree-code\u002Fstargazers\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fpaoloanzn\u002Ffree-code?style=flat-square\" alt=\"Stars\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fpaoloanzn\u002Ffree-code\u002Fissues\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fpaoloanzn\u002Ffree-code?style=flat-square\" alt=\"Issues\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fpaoloanzn\u002Ffree-code\u002Fblob\u002Fmain\u002FFEATURES.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Ffeatures-88%20flags-orange?style=flat-square\" alt=\"Feature Flags\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"#ipfs-mirror\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FIPFS-mirrored-teal?style=flat-square\" alt=\"IPFS\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n---\n\n## Quick Install\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fpaoloanzn\u002Ffree-code\u002Fmain\u002Finstall.sh | bash\n```\n\nChecks your system, installs Bun if needed, clones the repo, builds with all experimental features enabled, and symlinks `free-code` on your PATH.\n\nThen run `free-code` and use the `\u002Flogin` command to authenticate with your preferred model provider.\n\n---\n\n## Table of Contents\n\n- [What is this](#what-is-this)\n- [Model Providers](#model-providers)\n- [Quick Install](#quick-install)\n- [Requirements](#requirements)\n- [Build](#build)\n- [Usage](#usage)\n- [Experimental Features](#experimental-features)\n- [Project Structure](#project-structure)\n- [Tech Stack](#tech-stack)\n- [IPFS Mirror](#ipfs-mirror)\n- [Contributing](#contributing)\n- [License](#license)\n\n---\n\n## What is this\n\nA clean, buildable fork of Anthropic's [Claude Code](https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fclaude-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.\n\nThis fork applies three categories of changes on top of that snapshot:\n\n### Telemetry removed\n\nThe upstream binary phones home through OpenTelemetry\u002FgRPC, GrowthBook analytics, Sentry error reporting, and custom event logging. In this build:\n\n- All outbound telemetry endpoints are dead-code-eliminated or stubbed\n- GrowthBook feature flag evaluation still works locally (needed for runtime feature gates) but does not report back\n- No crash reports, no usage analytics, no session fingerprinting\n\n### Security-prompt guardrails removed\n\nAnthropic 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.\n\nThis 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.\n\n### Experimental features unlocked\n\nClaude 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](#experimental-features) below, or refer to [FEATURES.md](FEATURES.md) for the full audit.\n\n---\n\n## Model Providers\n\nfree-code supports **five API providers** out of the box. Set the corresponding environment variable to switch providers -- no code changes needed.\n\n### Anthropic (Direct API) -- Default\n\nUse Anthropic's first-party API directly.\n\n| Model | ID |\n|---|---|\n| Claude Opus 4.6 | `claude-opus-4-6` |\n| Claude Sonnet 4.6 | `claude-sonnet-4-6` |\n| Claude Haiku 4.5 | `claude-haiku-4-5` |\n\n### OpenAI Codex\n\nUse OpenAI's Codex models for code generation. Requires a Codex subscription.\n\n| Model | ID |\n|---|---|\n| GPT-5.3 Codex (recommended) | `gpt-5.3-codex` |\n| GPT-5.4 | `gpt-5.4` |\n| GPT-5.4 Mini | `gpt-5.4-mini` |\n\n```bash\nexport CLAUDE_CODE_USE_OPENAI=1\nfree-code\n```\n\n### AWS Bedrock\n\nRoute requests through your AWS account via Amazon Bedrock.\n\n```bash\nexport CLAUDE_CODE_USE_BEDROCK=1\nexport AWS_REGION=\"us-east-1\"   # or AWS_DEFAULT_REGION\nfree-code\n```\n\nUses your standard AWS credentials (environment variables, `~\u002F.aws\u002Fconfig`, or IAM role). Models are mapped to Bedrock ARN format automatically (e.g., `us.anthropic.claude-opus-4-6-v1`).\n\n| Variable | Purpose |\n|---|---|\n| `CLAUDE_CODE_USE_BEDROCK` | Enable Bedrock provider |\n| `AWS_REGION` \u002F `AWS_DEFAULT_REGION` | AWS region (default: `us-east-1`) |\n| `ANTHROPIC_BEDROCK_BASE_URL` | Custom Bedrock endpoint |\n| `AWS_BEARER_TOKEN_BEDROCK` | Bearer token auth |\n| `CLAUDE_CODE_SKIP_BEDROCK_AUTH` | Skip auth (testing) |\n\n### Google Cloud Vertex AI\n\nRoute requests through your GCP project via Vertex AI.\n\n```bash\nexport CLAUDE_CODE_USE_VERTEX=1\nfree-code\n```\n\nUses Google Cloud Application Default Credentials (`gcloud auth application-default login`). Models are mapped to Vertex format automatically (e.g., `claude-opus-4-6@latest`).\n\n### Anthropic Foundry\n\nUse Anthropic Foundry for dedicated deployments.\n\n```bash\nexport CLAUDE_CODE_USE_FOUNDRY=1\nexport ANTHROPIC_FOUNDRY_API_KEY=\"...\"\nfree-code\n```\n\nSupports custom deployment IDs as model names.\n\n### Provider Selection Summary\n\n| Provider | Env Variable | Auth Method |\n|---|---|---|\n| Anthropic (default) | -- | `ANTHROPIC_API_KEY` or OAuth |\n| OpenAI Codex | `CLAUDE_CODE_USE_OPENAI=1` | OAuth via OpenAI |\n| AWS Bedrock | `CLAUDE_CODE_USE_BEDROCK=1` | AWS credentials |\n| Google Vertex AI | `CLAUDE_CODE_USE_VERTEX=1` | `gcloud` ADC |\n| Anthropic Foundry | `CLAUDE_CODE_USE_FOUNDRY=1` | `ANTHROPIC_FOUNDRY_API_KEY` |\n\n---\n\n## Requirements\n\n- **Runtime**: [Bun](https:\u002F\u002Fbun.sh) >= 1.3.11\n- **OS**: macOS or Linux (Windows via WSL)\n- **Auth**: An API key or OAuth login for your chosen provider\n\n```bash\n# Install Bun if you don't have it\ncurl -fsSL https:\u002F\u002Fbun.sh\u002Finstall | bash\n```\n\n---\n\n## Build\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fpaoloanzn\u002Ffree-code.git\ncd free-code\nbun build\n.\u002Fcli\n```\n\n### Build Variants\n\n| Command | Output | Features | Description |\n|---|---|---|---|\n| `bun run build` | `.\u002Fcli` | `VOICE_MODE` only | Production-like binary |\n| `bun run build:dev` | `.\u002Fcli-dev` | `VOICE_MODE` only | Dev version stamp |\n| `bun run build:dev:full` | `.\u002Fcli-dev` | All 54 experimental flags | Full unlock build |\n| `bun run compile` | `.\u002Fdist\u002Fcli` | `VOICE_MODE` only | Alternative output path |\n\n### Custom Feature Flags\n\nEnable specific flags without the full bundle:\n\n```bash\n# Enable just ultraplan and ultrathink\nbun run .\u002Fscripts\u002Fbuild.ts --feature=ULTRAPLAN --feature=ULTRATHINK\n\n# Add a flag on top of the dev build\nbun run .\u002Fscripts\u002Fbuild.ts --dev --feature=BRIDGE_MODE\n```\n\n---\n\n## Usage\n\n```bash\n# Interactive REPL (default)\n.\u002Fcli\n\n# One-shot mode\n.\u002Fcli -p \"what files are in this directory?\"\n\n# Specify a model\n.\u002Fcli --model claude-opus-4-6\n\n# Run from source (slower startup)\nbun run dev\n\n# OAuth login\n.\u002Fcli \u002Flogin\n```\n\n### Environment Variables Reference\n\n| Variable | Purpose |\n|---|---|\n| `ANTHROPIC_API_KEY` | Anthropic API key |\n| `ANTHROPIC_AUTH_TOKEN` | Auth token (alternative) |\n| `ANTHROPIC_MODEL` | Override default model |\n| `ANTHROPIC_BASE_URL` | Custom API endpoint |\n| `ANTHROPIC_DEFAULT_OPUS_MODEL` | Custom Opus model ID |\n| `ANTHROPIC_DEFAULT_SONNET_MODEL` | Custom Sonnet model ID |\n| `ANTHROPIC_DEFAULT_HAIKU_MODEL` | Custom Haiku model ID |\n| `CLAUDE_CODE_OAUTH_TOKEN` | OAuth token via env |\n| `CLAUDE_CODE_API_KEY_HELPER_TTL_MS` | API key helper cache TTL |\n\n---\n\n## Experimental Features\n\nThe `bun run build:dev:full` build enables all 54 working feature flags. Highlights:\n\n### Interaction & UI\n\n| Flag | Description |\n|---|---|\n| `ULTRAPLAN` | Remote multi-agent planning on Claude Code web (Opus-class) |\n| `ULTRATHINK` | Deep thinking mode -- type \"ultrathink\" to boost reasoning effort |\n| `VOICE_MODE` | Push-to-talk voice input and dictation |\n| `TOKEN_BUDGET` | Token budget tracking and usage warnings |\n| `HISTORY_PICKER` | Interactive prompt history picker |\n| `MESSAGE_ACTIONS` | Message action entrypoints in the UI |\n| `QUICK_SEARCH` | Prompt quick-search |\n| `SHOT_STATS` | Shot-distribution stats |\n\n### Agents, Memory & Planning\n\n| Flag | Description |\n|---|---|\n| `BUILTIN_EXPLORE_PLAN_AGENTS` | Built-in explore\u002Fplan agent presets |\n| `VERIFICATION_AGENT` | Verification agent for task validation |\n| `AGENT_TRIGGERS` | Local cron\u002Ftrigger tools for background automation |\n| `AGENT_TRIGGERS_REMOTE` | Remote trigger tool path |\n| `EXTRACT_MEMORIES` | Post-query automatic memory extraction |\n| `COMPACTION_REMINDERS` | Smart reminders around context compaction |\n| `CACHED_MICROCOMPACT` | Cached microcompact state through query flows |\n| `TEAMMEM` | Team-memory files and watcher hooks |\n\n### Tools & Infrastructure\n\n| Flag | Description |\n|---|---|\n| `BRIDGE_MODE` | IDE remote-control bridge (VS Code, JetBrains) |\n| `BASH_CLASSIFIER` | Classifier-assisted bash permission decisions |\n| `PROMPT_CACHE_BREAK_DETECTION` | Cache-break detection in compaction\u002Fquery flow |\n\nSee [FEATURES.md](FEATURES.md) for the complete audit of all 88 flags, including 34 broken flags with reconstruction notes.\n\n---\n\n## Project Structure\n\n```\nscripts\u002F\n  build.ts                # Build script with feature flag system\n\nsrc\u002F\n  entrypoints\u002Fcli.tsx     # CLI entrypoint\n  commands.ts             # Command registry (slash commands)\n  tools.ts                # Tool registry (agent tools)\n  QueryEngine.ts          # LLM query engine\n  screens\u002FREPL.tsx        # Main interactive UI (Ink\u002FReact)\n\n  commands\u002F               # \u002Fslash command implementations\n  tools\u002F                  # Agent tool implementations (Bash, Read, Edit, etc.)\n  components\u002F             # Ink\u002FReact terminal UI components\n  hooks\u002F                  # React hooks\n  services\u002F               # API clients, MCP, OAuth, analytics\n    api\u002F                  # API client + Codex fetch adapter\n    oauth\u002F                # OAuth flows (Anthropic + OpenAI)\n  state\u002F                  # App state store\n  utils\u002F                  # Utilities\n    model\u002F                # Model configs, providers, validation\n  skills\u002F                 # Skill system\n  plugins\u002F                # Plugin system\n  bridge\u002F                 # IDE bridge\n  voice\u002F                  # Voice input\n  tasks\u002F                  # Background task management\n```\n\n---\n\n## Tech Stack\n\n| | |\n|---|---|\n| **Runtime** | [Bun](https:\u002F\u002Fbun.sh) |\n| **Language** | TypeScript |\n| **Terminal UI** | React + [Ink](https:\u002F\u002Fgithub.com\u002Fvadimdemedes\u002Fink) |\n| **CLI Parsing** | [Commander.js](https:\u002F\u002Fgithub.com\u002Ftj\u002Fcommander.js) |\n| **Schema Validation** | Zod v4 |\n| **Code Search** | ripgrep (bundled) |\n| **Protocols** | MCP, LSP |\n| **APIs** | Anthropic Messages, OpenAI Codex, AWS Bedrock, Google Vertex AI |\n\n---\n\n## IPFS Mirror\n\nA full copy of this repository is permanently pinned on IPFS via Filecoin:\n\n| | |\n|---|---|\n| **CID** | `bafybeiegvef3dt24n2znnnmzcud2vxat7y7rl5ikz7y7yoglxappim54bm` |\n| **Gateway** | https:\u002F\u002Fw3s.link\u002Fipfs\u002Fbafybeiegvef3dt24n2znnnmzcud2vxat7y7rl5ikz7y7yoglxappim54bm |\n\nIf this repo gets taken down, the code lives on.\n\n---\n\n## Contributing\n\nContributions are welcome. If you're working on restoring one of the 34 broken feature flags, check the reconstruction notes in [FEATURES.md](FEATURES.md) first -- many are close to compiling and just need a small wrapper or missing asset.\n\n1. Fork the repository\n2. Create a feature branch (`git checkout -b feat\u002Fmy-feature`)\n3. Commit your changes (`git commit -m 'feat: add something'`)\n4. Push to the branch (`git push origin feat\u002Fmy-feature`)\n5. Open a Pull Request\n\n---\n\n## License\n\nThe 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.\n","free-code 是一个基于 Anthropic 的 Claude Code 的开源版本，去除了所有遥测功能、安全提示护栏，并启用了所有实验性功能。项目采用 TypeScript 编写，提供了一个简洁的安装脚本，能够自动检查系统环境、安装必要的依赖并构建项目。其核心特点在于移除了所有对外部服务的数据上报机制，包括错误报告和使用分析等，同时解除了对 AI 模型行为的额外限制，允许用户自由探索模型的全部能力。适用于需要高度定制化AI编码助手且对隐私保护有较高要求的开发者或研究者。",2,"2026-05-12 11:08:13","high_star"]