高性能 CLI 代理，将 LLM token 消耗降低 60-90%

网站 • 安装 • 故障排除 • 架构 • Discord

英语 • 法语 • 中文 • 日语 • 韩语 • 西班牙语 • 葡萄牙语

---

rtk 在输出到达 LLM 上下文之前对命令输出进行过滤和压缩。单个 Rust 二进制文件，支持 100 多个命令，开销 <10ms。

Token 节省量（基于 30 分钟的 Claude Code 会话）

操作	频率	标准	rtk	节省比例
ls / tree	10 次	2,000	400	-80%
cat / read	20 次	40,000	12,000	-70%
grep / rg	8 次	16,000	3,200	-80%
git status	10 次	3,000	600	-80%
git diff	5 次	10,000	2,500	-75%
git log	5 次	2,500	500	-80%
git add/commit/push	8 次	1,600	120	-92%
cargo test / npm test	5 次	25,000	2,500	-90%
ruff check	3 次	3,000	600	-80%
pytest	4 次	8,000	800	-90%
go test	3 次	6,000	600	-90%
docker ps	3 次	900	180	-80%
总计		~118,000	~23,900	-80%

基于中型 TypeScript/Rust 项目的估计值。实际节省量因项目大小而异。

快速安装（Linux/macOS）

curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh

安装到 ~/.local/bin。如果需要，添加到 PATH：

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc # 或 ~/.zshrc

cargo install --git https://github.com/rtk-ai/rtk

从 releases 下载：

• macOS: rtk-x86_64-apple-darwin.tar.gz / rtk-aarch64-apple-darwin.tar.gz
• Linux: rtk-x86_64-unknown-linux-musl.tar.gz / rtk-aarch64-unknown-linux-gnu.tar.gz
• Windows: rtk-x86_64-pc-windows-msvc.zip

Windows 用户：解压 zip 并将 rtk.exe 放到 PATH 中的某个位置（例如 C:\Users\<你>\.local\bin）。从 命令提示符、PowerShell 或 Windows Terminal 运行 RTK —— 不要双击 .exe（会闪退）。完整的钩子系统在 Windows 上原生工作（以及在 WSL 中）。详情见下方 Windows 设置。

rtk --version # 应显示 "rtk 0.28.2" rtk gain # 应显示 token 节省统计信息

名称冲突警告：crates.io 上存在另一个名为 "rtk"（Rust Type Kit）的项目。如果 rtk gain 失败，说明你安装了错误的包。请改用上面的 cargo install --git 方式。

1. 为你的 AI 工具安装

rtk init -g # Claude Code / Copilot（默认） rtk init -g --gemini # Gemini CLI rtk init -g --codex # Codex (OpenAI) rtk init -g --agent cursor # Cursor rtk init -g --agent windsurf # Windsurf rtk init --agent cline # Cline / Roo Code rtk init --agent kilocode # Kilo Code rtk init --agent antigravity # Google Antigravity rtk init -g --agent pi # Pi rtk init --agent hermes # Hermes

2. 重启你的 AI 工具，然后测试

git status # 自动重写为 rtk git status

基于钩子的代理在执行前将 Bash 命令（例如 git status -> rtk git status）重写。基于插件的代理（包括 Hermes）使用其插件 API 在执行前重写命令。代理接收紧凑的输出而无需显式调用 rtk。

重要提示： 钩子仅对 Bash 工具调用生效。Claude Code 内置工具如 Read、Grep 和 Glob 不会经过 Bash 钩子，因此它们不会被自动重写。若想在这些工作流中获得 RTK 的紧凑输出，请使用 shell 命令（cat/head/tail、rg/grep、find）或直接调用 rtk read、rtk grep 或 rtk find。

不使用 rtk: 使用 rtk:

Claude --git status--> shell --> git Claude --git status--> RTK --> git ^ | ^ | | | ~2,000 tokens (raw) | | ~200 tokens | filter | +-----------------------------------+ +------- (filtered) ---+----------+

四种策略按命令类型应用：

1. 智能过滤 - 移除噪声（注释、空白、样板代码）
2. 分组 - 聚合相似项（按目录分组文件，按类型分组错误）
3. 截断 - 保留相关上下文，切除冗余
4. 去重 - 将重复的日志行折叠并计数

常规命令

rtk ls . # Token 优化的目录树 rtk read file.rs # 智能文件读取 rtk read file.rs -l aggressive # 仅函数签名（去除函数体） rtk smart file.rs # 2 行启发式代码摘要 rtk find "*.rs" . # 紧凑的查找结果 rtk grep "pattern" . # 分组搜索结果 rtk diff file1 file2 # 浓缩差异（文件不同时退出码为 1）

Git 命令

rtk git status # 紧凑状态 rtk git log -n 10 # 单行提交记录 rtk git diff # 浓缩差异 rtk git add # -> "ok" rtk git commit -m "msg" # -> "ok abc1234" rtk git push # -> "ok main" rtk git pull # -> "ok 3 files +10 -2"

GitHub CLI

rtk gh pr list # 紧凑的 Pull Request 列表 rtk gh pr view 42 # PR 详情 + 检查信息 rtk gh issue list # 紧凑的 Issue 列表 rtk gh run list # 工作流运行状态

测试命令

rtk jest # Jest 紧凑输出（仅失败项） rtk vitest # Vitest 紧凑输出（仅失败项） rtk playwright test # E2E 结果（仅失败项） rtk pytest # Python 测试 (-90%) rtk go test # Go 测试 (NDJSON, -90%) rtk cargo test # Cargo 测试 (-90%) rtk rake test # Ruby minitest (-90%) rtk rspec # RSpec 测试 (JSON, -60%+) rtk err # 仅过滤任何命令的错误输出 rtk test # 通用测试包装器 - 仅失败项 (-90%)

Lint / 构建命令

rtk lint # ESLint 按规则/文件分组 rtk lint biome # 支持其他 linter rtk tsc # TypeScript 错误按文件分组 rtk next build # Next.js 构建紧凑输出 rtk prettier --check . # 需要格式化的文件 rtk cargo build # Cargo 构建 (-80%) rtk cargo clippy # Cargo clippy (-80%) rtk ruff check # Python linting (JSON, -80%) rtk golangci-lint run # Go linting (JSON, -85%) rtk rubocop # Ruby linting (JSON, -60%+)

包管理器命令

rtk pnpm list # 紧凑的依赖树 rtk uv run pytest # 保留 uv 环境，仅错误项 rtk pip list # Python 包（自动检测 uv） rtk pip outdated # 过期的包 rtk bundle install # Ruby gems（去除 "Using" 行） rtk prisma generate # Schema 生成（无 ASCII 艺术）

AWS 命令

rtk aws sts get-caller-identity # 单行身份信息 rtk aws ec2 describe-instances # 紧凑的实例列表 rtk aws lambda list-functions # 名称/运行时/内存（去除密钥） rtk aws logs get-log-events # 仅带时间戳的消息 rtk aws cloudformation describe-stack-events # 优先显示失败事件 rtk aws dynamodb scan # 解包类型注释 rtk aws iam list-roles # 去除策略文档 rtk aws s3 ls # 截断并支持 tee 恢复

容器与编排命令

rtk docker ps # 紧凑的容器列表 rtk docker images # 紧凑的镜像列表 rtk docker logs # 去重的日志 rtk docker compose ps # Compose 服务列表 rtk kubectl pods # 紧凑的 Pod 列表 rtk kubectl logs # 去重的日志 rtk kubectl services # 紧凑的服务列表 rtk oc get pods # OpenShift Pod 摘要 rtk oc get services # OpenShift 服务列表 rtk oc logs # 去重的日志

基础设施即代码命令

rtk pulumi preview # 去除摘要头/URL/持续时间噪音 rtk pulumi up # 紧凑的应用输出 rtk pulumi destroy # 紧凑的销毁输出 rtk pulumi refresh # 偏离摘要 rtk pulumi stack # 堆栈元数据（去除所有者和时间戳）

通用工具命令

rtk json config.json # 不含值的结构 rtk deps # 依赖摘要 rtk env -f AWS # 过滤后的环境变量 rtk log app.log # 去重的日志 rtk curl # 截断并保存完整输出 rtk wget # 下载，去除进度条 rtk summary # 启发式摘要 rtk proxy # 原始透传并跟踪

统计数据

rtk gain # 摘要统计 rtk gain --graph # ASCII 图表（最近 30 天） rtk gain --history # 最近的命令历史 rtk gain --daily # 每日详细分析 rtk gain --all --format json # 用于仪表板的 JSON 导出

rtk discover # 查找错过的节省机会 rtk discover --all --since 7 # 所有项目，最近 7 天

rtk session # 显示近期会话中 RTK 的采用情况

选项

-u, --ultra-compact # ASCII 图标、内联格式（额外 token 节省） -v, --verbose # 增加详细程度 (-v, -vv, -vvv)

目录列表对比：

ls -la (45 行, ~800 tokens) # rtk ls (12 行, ~150 tokens)

drwxr-xr-x 15 user staff 480 ... my-project/ -rw-r--r-- 1 user staff 1234 ... +-- src/ (8 files) ... | +-- main.rs +-- Cargo.toml

Git 操作对比：

git push (15 行, ~200 tokens) # rtk git push (1 行, ~10 tokens)

Enumerating objects: 5, done. ok main Counting objects: 100% (5/5), done. Delta compression using up to 8 threads ...

测试输出对比：

cargo test (失败时 200+ 行) # rtk test cargo test (~20 行)

running 15 tests FAILED: 2/15 tests test utils::test_parse ... ok test_edge_case: assertion failed test utils::test_format ... ok test_overflow: panic at utils.rs:18 ...

钩子是使用 rtk 最高效的方式。它透明地拦截 Bash 命令并在执行前将其重写为 rtk 等价命令。

结果：在所有对话和子代理中实现 100% rtk 采用率，零 token 开销。

范围说明： 仅适用于 Bash 工具调用。Claude Code 内置工具如 Read、Grep 和 Glob 会绕过钩子，因此若想对这些工作流应用 RTK 过滤，请使用 shell 命令或显式 rtk 命令。

rtk init -g # 安装钩子 + RTK.md（推荐） rtk init -g --opencode # OpenCode 插件（而非 Claude Code） rtk init -g --auto-patch # 非交互模式 (CI/CD) rtk init -g --hook-only # 仅钩子，不含 RTK.md rtk init --show # 验证安装

安装后，重启 Claude Code。

RTK 在原生 Windows 上完全可用。从 v0.37.2 起，自动重写钩子作为 原生二进制命令（rtk hook claude）运行 —— 无需 Unix shell、bash 或 jq —— 因此命令可以在命令提示符、PowerShell 和 Windows Terminal 上透明重写，就像在 Linux 和 macOS 上一样。

1. 从 releases 下载并解压 rtk-x86_64-pc-windows-msvc.zip

2. 将 rtk.exe 添加到你的 PATH（例如 C:\Users<你>.local\bin）

High-performance CLI proxy that reduces LLM token consumption by 60-90%

Website • Install • Troubleshooting • Architecture • Discord

English • Francais • 中文 • 日本語 • 한국어 • Espanol • Português

---

rtk filters and compresses command outputs before they reach your LLM context. Single Rust binary, 100+ supported commands, <10ms overhead.

Token Savings (30-min Claude Code Session)

Operation	Frequency	Standard	rtk	Savings
ls / tree	10x	2,000	400	-80%
cat / read	20x	40,000	12,000	-70%
grep / rg	8x	16,000	3,200	-80%
git status	10x	3,000	600	-80%
git diff	5x	10,000	2,500	-75%
git log	5x	2,500	500	-80%
git add/commit/push	8x	1,600	120	-92%
cargo test / npm test	5x	25,000	2,500	-90%
ruff check	3x	3,000	600	-80%
pytest	4x	8,000	800	-90%
go test	3x	6,000	600	-90%
docker ps	3x	900	180	-80%
Total		~118,000	~23,900	-80%

Estimates based on medium-sized TypeScript/Rust projects. Actual savings vary by project size.

Quick Install (Linux/macOS)

curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh

Installs to ~/.local/bin. Add to PATH if needed:

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc  # or ~/.zshrc

cargo install --git https://github.com/rtk-ai/rtk

Download from releases:

• macOS: rtk-x86_64-apple-darwin.tar.gz / rtk-aarch64-apple-darwin.tar.gz
• Linux: rtk-x86_64-unknown-linux-musl.tar.gz / rtk-aarch64-unknown-linux-gnu.tar.gz
• Windows: rtk-x86_64-pc-windows-msvc.zip

Windows users : Extract the zip and place rtk.exe somewhere in your PATH (e.g. C:\Users\<you>\.local\bin). Run RTK from Command Prompt , PowerShell , or Windows Terminal — do not double-click the .exe (it will flash and close). The full hook system works natively on Windows (and in WSL). See Windows setup below for details.

rtk --version   # Should show "rtk 0.28.2"
rtk gain        # Should show token savings stats

Name collision warning : Another project named "rtk" (Rust Type Kit) exists on crates.io. If rtk gain fails, you have the wrong package. Use cargo install --git above instead.

# 1. Install for your AI tool
rtk init -g                     # Claude Code / Copilot (default)
rtk init -g --gemini            # Gemini CLI
rtk init -g --codex             # Codex (OpenAI)
rtk init -g --agent cursor      # Cursor
rtk init -g --agent windsurf    # Windsurf
rtk init --agent cline          # Cline / Roo Code
rtk init --agent kilocode       # Kilo Code
rtk init --agent antigravity    # Google Antigravity
rtk init -g --agent pi          # Pi
rtk init --agent hermes         # Hermes

# 2. Restart your AI tool, then test
git status  # Automatically rewritten to rtk git status

Hook-based agents rewrite Bash commands (e.g., git status -> rtk git status) before execution. Plugin-based agents, including Hermes, use their plugin API to rewrite commands before execution. The agent receives compact output without needing to call rtk explicitly.

Important: the hook only runs on Bash tool calls. Claude Code built-in tools like Read, Grep, and Glob do not pass through the Bash hook, so they are not auto-rewritten. To get RTK's compact output for those workflows, use shell commands (cat/head/tail, rg/grep, find) or call rtk read, rtk grep, or rtk find directly.

  Without rtk:                                    With rtk:

  Claude  --git status-->  shell  -->  git         Claude  --git status-->  RTK  -->  git
    ^                                   |            ^                      |          |
    |        ~2,000 tokens (raw)        |            |   ~200 tokens        | filter   |
    +-----------------------------------+            +------- (filtered) ---+----------+

Four strategies applied per command type:

1. Smart Filtering - Removes noise (comments, whitespace, boilerplate)
2. Grouping - Aggregates similar items (files by directory, errors by type)
3. Truncation - Keeps relevant context, cuts redundancy
4. Deduplication - Collapses repeated log lines with counts

rtk ls .                        # Token-optimized directory tree
rtk read file.rs                # Smart file reading
rtk read file.rs -l aggressive  # Signatures only (strips bodies)
rtk smart file.rs               # 2-line heuristic code summary
rtk find "*.rs" .               # Compact find results
rtk grep "pattern" .            # Grouped search results
rtk diff file1 file2            # Condensed diff (exit 1 if files differ)


rtk git status                  # Compact status
rtk git log -n 10               # One-line commits
rtk git diff                    # Condensed diff
rtk git add                     # -> "ok"
rtk git commit -m "msg"         # -> "ok abc1234"
rtk git push                    # -> "ok main"
rtk git pull                    # -> "ok 3 files +10 -2"


rtk gh pr list                  # Compact PR listing
rtk gh pr view 42               # PR details + checks
rtk gh issue list               # Compact issue listing
rtk gh run list                 # Workflow run status


rtk jest                        # Jest compact (failures only)
rtk vitest                      # Vitest compact (failures only)
rtk playwright test             # E2E results (failures only)
rtk pytest                      # Python tests (-90%)
rtk go test                     # Go tests (NDJSON, -90%)
rtk cargo test                  # Cargo tests (-90%)
rtk rake test                   # Ruby minitest (-90%)
rtk rspec                       # RSpec tests (JSON, -60%+)
rtk err <cmd>                   # Filter errors only from any command
rtk test <cmd>                  # Generic test wrapper - failures only (-90%)


rtk lint                        # ESLint grouped by rule/file
rtk lint biome                  # Supports other linters
rtk tsc                         # TypeScript errors grouped by file
rtk next build                  # Next.js build compact
rtk prettier --check .          # Files needing formatting
rtk cargo build                 # Cargo build (-80%)
rtk cargo clippy                # Cargo clippy (-80%)
rtk ruff check                  # Python linting (JSON, -80%)
rtk golangci-lint run           # Go linting (JSON, -85%)
rtk rubocop                     # Ruby linting (JSON, -60%+)


rtk pnpm list                   # Compact dependency tree
rtk uv run pytest               # Preserve uv env, errors only
rtk pip list                    # Python packages (auto-detect uv)
rtk pip outdated                # Outdated packages
rtk bundle install              # Ruby gems (strip Using lines)
rtk prisma generate             # Schema generation (no ASCII art)


rtk aws sts get-caller-identity # One-line identity
rtk aws ec2 describe-instances  # Compact instance list
rtk aws lambda list-functions   # Name/runtime/memory (strips secrets)
rtk aws logs get-log-events     # Timestamped messages only
rtk aws cloudformation describe-stack-events  # Failures first
rtk aws dynamodb scan           # Unwraps type annotations
rtk aws iam list-roles          # Strips policy documents
rtk aws s3 ls                   # Truncated with tee recovery


rtk docker ps                   # Compact container list
rtk docker images               # Compact image list
rtk docker logs <container>     # Deduplicated logs
rtk docker compose ps           # Compose services
rtk kubectl pods                # Compact pod list
rtk kubectl logs <pod>          # Deduplicated logs
rtk kubectl services            # Compact service list
rtk oc get pods                 # OpenShift pod summary
rtk oc get services             # OpenShift service list
rtk oc logs <pod>               # Deduplicated logs


rtk pulumi preview              # Strip header/URL/duration noise
rtk pulumi up                   # Compact apply output
rtk pulumi destroy              # Compact destroy output
rtk pulumi refresh              # Drift summary
rtk pulumi stack                # Stack metadata (strips owner/timestamps)


rtk json config.json            # Structure without values
rtk deps                        # Dependencies summary
rtk env -f AWS                  # Filtered env vars
rtk log app.log                 # Deduplicated logs
rtk curl <url>                  # Truncate + save full output
rtk wget <url>                  # Download, strip progress bars
rtk summary <long command>      # Heuristic summary
rtk proxy <command>             # Raw passthrough + tracking


rtk gain                        # Summary stats
rtk gain --graph                # ASCII graph (last 30 days)
rtk gain --history              # Recent command history
rtk gain --daily                # Day-by-day breakdown
rtk gain --all --format json    # JSON export for dashboards

rtk discover                    # Find missed savings opportunities
rtk discover --all --since 7    # All projects, last 7 days

rtk session                     # Show RTK adoption across recent sessions


-u, --ultra-compact    # ASCII icons, inline format (extra token savings)
-v, --verbose          # Increase verbosity (-v, -vv, -vvv)

Directory listing:

# ls -la (45 lines, ~800 tokens)        # rtk ls (12 lines, ~150 tokens)
drwxr-xr-x  15 user staff 480 ...       my-project/
-rw-r--r--   1 user staff 1234 ...       +-- src/ (8 files)
...                                      |   +-- main.rs
                                         +-- Cargo.toml

Git operations:

# git push (15 lines, ~200 tokens)       # rtk git push (1 line, ~10 tokens)
Enumerating objects: 5, done.             ok main
Counting objects: 100% (5/5), done.
Delta compression using up to 8 threads
...

Test output:

# cargo test (200+ lines on failure)     # rtk test cargo test (~20 lines)
running 15 tests                          FAILED: 2/15 tests
test utils::test_parse ... ok               test_edge_case: assertion failed
test utils::test_format ... ok              test_overflow: panic at utils.rs:18
...

The most effective way to use rtk. The hook transparently intercepts Bash commands and rewrites them to rtk equivalents before execution.

Result : 100% rtk adoption across all conversations and subagents, zero token overhead.

Scope note: this only applies to Bash tool calls. Claude Code built-in tools such as Read, Grep, and Glob bypass the hook, so use shell commands or explicit rtk commands when you want RTK filtering there.

rtk init -g                 # Install hook + RTK.md (recommended)
rtk init -g --opencode      # OpenCode plugin (instead of Claude Code)
rtk init -g --auto-patch    # Non-interactive (CI/CD)
rtk init -g --hook-only     # Hook only, no RTK.md
rtk init --show             # Verify installation

After install, restart Claude Code.

RTK works fully on native Windows. Since v0.37.2 the auto-rewrite hook runs as a native binary command (rtk hook claude) — no Unix shell, bash, or jq required — so commands are rewritten transparently on Command Prompt, PowerShell, and Windows Terminal, just like on Linux and macOS.

# 1. Download and extract rtk-x86_64-pc-windows-msvc.zip from releases
# 2. Add rtk.exe to your PATH (e.g. C:\Users\<you>\.local\bin)
# 3. Initialize — installs the native binary hook
rtk init -g

Upgrading from an older install? If you set RTK up before v0.37.2 you may still have the legacy rtk-rewrite.sh shell hook (which does need a Unix shell). Re-run rtk init -g to migrate to the native binary hook.

Prerequisites : some filters shell out to ripgrep (rg). Install it and keep it on your PATH (e.g. winget install BurntSushi.ripgrep.MSVC) to avoid Binary 'rg' not found on PATH warnings.

Important : Do not double-click rtk.exe — it is a CLI tool that prints usage and exits immediately. Always run it from a terminal (Command Prompt, PowerShell, or Windows Terminal).

WSL also works and behaves exactly like Linux:

# Inside WSL
curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh
rtk init -g

Feature	Native Windows	WSL
Filters (cargo, git, etc.)	Full	Full
Auto-rewrite hook	Yes (native binary)	Yes
rtk init -g	Hook mode	Hook mode
rtk gain / analytics	Full	Full

RTK supports 14 AI coding tools. Each integration rewrites shell commands to rtk equivalents for 60-90% token savings where the agent supports command interception.

Tool	Install	Method
Claude Code	rtk init -g	PreToolUse hook (native binary)
GitHub Copilot (VS Code)	rtk init -g --copilot	PreToolUse hook — transparent rewrite
GitHub Copilot CLI	rtk init -g --copilot	PreToolUse deny-with-suggestion (CLI limitation)
Cursor	rtk init -g --agent cursor	preToolUse hook (hooks.json)
Gemini CLI	rtk init -g --gemini	BeforeTool hook
Codex	rtk init -g --codex	AGENTS.md + RTK.md instructions
Windsurf	rtk init -g --agent windsurf	.windsurfrules (project-scoped)
Cline / Roo Code	rtk init --agent cline	.clinerules (project-scoped)
OpenCode	rtk init -g --opencode	Plugin TS (tool.execute.before)
OpenClaw	openclaw plugins install ./openclaw	Plugin TS (before_tool_call)
Pi	rtk init -g --agent pi (global)	TypeScript extension (tool_call)
Hermes	rtk init --agent hermes	Python plugin adapter (terminal command mutation via rtk rewrite)
Mistral Vibe	Planned (#800)	Blocked on upstream
Kilo Code	rtk init --agent kilocode	.kilocode/rules/rtk-rules.md (project-scoped)
Google Antigravity	rtk init --agent antigravity	.agents/rules/antigravity-rtk-rules.md (project-scoped)

For per-agent setup details, override controls, and graceful degradation, see the Supported Agents guide. The Hermes plugin source and tests live in hooks/hermes/; installed Hermes runtime files still live under ~/.hermes/plugins/rtk-rewrite/.

~/.config/rtk/config.toml (macOS: ~/Library/Application Support/rtk/config.toml):

[hooks]
exclude_commands = ["curl", "playwright"]  # skip rewrite for these

[tee]
enabled = true          # save raw output on failure (default: true)
mode = "failures"       # "failures", "always", or "never"

When a command fails, RTK saves the full unfiltered output so the LLM can read it without re-executing:

FAILED: 2/15 tests
[full output: ~/.local/share/rtk/tee/1707753600_cargo_test.log]

For the full config reference (all sections, env vars, per-project filters), see the Configuration guide.

rtk init -g --uninstall     # Remove hook, RTK.md, settings.json entry
cargo uninstall rtk          # Remove binary
brew uninstall rtk           # If installed via Homebrew

RTK can collect anonymous, aggregate usage metrics once per day. Telemetry is disabled by default and requires explicit opt-in consent (GDPR Art. 6, 7) during rtk init or via rtk telemetry enable. This data helps us build a better product: identifying which commands need filters, which filters need improvement, and how much value RTK delivers. For the full list of fields, data handling, and contributor guidelines, see docs/TELEMETRY.md.

What is collected and why:

Category	Data	Why
Identity	Salted device hash (SHA-256, not reversible)	Count unique installations without tracking individuals
Environment	RTK version, OS, architecture, install method	Know which platforms to support and test
Usage volume	Command count (24h), total commands, tokens saved (24h/30d/total)	Measure adoption and value delivered
Quality	Top 5 passthrough commands (0% savings), parse failure count, commands with <30% savings	Identify missing filters and weak ones to improve
Ecosystem	Command category distribution (e.g. git 45%, cargo 20%, js 15%)	Prioritize filter development for popular ecosystems
Retention	Days since first use, active days in last 30	Understand engagement and detect churn
Adoption	AI agent hook type (claude/gemini/codex), custom TOML filter count	Track integration coverage and DSL adoption
Configuration	Whether config.toml exists, number of excluded commands, project count	Understand user maturity and customization patterns
Features	Usage counts for meta-commands (gain, discover, proxy, verify)	Know which RTK features are valued vs unused
Economics	Estimated USD savings (based on API token pricing)	Quantify the value RTK provides to users

All data is aggregate counts or anonymized command names (first 3 words, no arguments). Top commands report only tool names (e.g. "git", "cargo"), never full command lines.

What is NOT collected: source code, file paths, command arguments, secrets, environment variables, personal data, or repository contents.

Manage telemetry:

rtk telemetry status     # Check current consent state
rtk telemetry enable     # Give consent (interactive prompt)
rtk telemetry disable    # Withdraw consent — stops all collection immediately
rtk telemetry forget     # Withdraw consent + delete all local data + request server-side erasure

Override via environment:

export RTK_TELEMETRY_DISABLED=1   # Blocks telemetry regardless of consent

Contributions welcome! Please open an issue or PR on GitHub.

Join the community on Discord.

Apache License 2.0 - see LICENSE for details.

See DISCLAIMER.md.