Files
rtk-ai__rtk/docs/guide/index.md
Florian BRUNIAUX 4c9b528206 docs: Adrien review — hierarchy, counts, consistency, gaps
Hierarchy:
- Move troubleshooting.md and what-rtk-covers.md to guide/resources/
- Add guide/resources/telemetry.md (adapted from docs/TELEMETRY.md,
  user-facing: consent, opt-out, GDPR rights — without internal sections)

Content fixes:
- Remove all hardcoded counts (9 ecosystems, 12 agents, 60+, 7 more)
  replaced with qualitative language throughout
- Unify DB filename: tracking.db → history.db everywhere
  (canonical: src/core/constants.rs HISTORY_DB)
- installation.md: replace bare `cargo install rtk` with warning +
  explicit git URL to avoid Rust Type Kit name collision
- supported-agents.md: remove hardcoded agent count
- quick-start.md: remove hardcoded ecosystem list, link to what-rtk-covers

New content:
- gain.md: add --quota section explaining pro/5x/20x tier meanings
- gain.md: add callout linking to discover.md (find missed savings)
- index.md: add "Analyze your usage" section (rtk discover, rtk session)
- configuration.md: clarify ignore_dirs/ignore_files scope, add prose
  link to telemetry.md
- what-rtk-covers.md: clarify --ultra-compact vs git -u short flag conflict

Cross-references:
- All internal links updated for new resources/ paths
- index.md: link to troubleshooting, telemetry, what-rtk-covers, analytics
- discover.md: updated relative link to troubleshooting

README:
- Add Core team section (Patrick Szymkowiak, Florian Bruniaux, Adrien Eppling)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-14 14:17:58 +02:00

66 lines
2.7 KiB
Markdown

---
title: RTK Documentation
description: RTK (Rust Token Killer) — reduce LLM token consumption by 60-90% on common dev commands, with zero workflow changes
sidebar:
order: 1
---
# RTK — Rust Token Killer
RTK is a CLI proxy that sits between your AI assistant and your development tools. It filters command output before it reaches the LLM, keeping only what matters and discarding boilerplate, progress bars, and noise.
**Result:** 60-90% fewer tokens consumed per command, without changing how you work. You run `git status` as usual — RTK's hook intercepts it, filters the output, and the LLM sees a compact 3-line summary instead of 40 lines.
## How it works
```
Your AI assistant runs: git status
↓
Hook intercepts (PreToolUse)
↓
rtk git status (transparent rewrite)
↓
Raw output: 40 lines → Filtered: 3 lines
~800 tokens → ~60 tokens (92% saved)
↓
LLM sees the compact output
```
Zero config changes to your workflow. The hook handles everything automatically.
## What RTK optimizes
Dozens of commands across all major ecosystems — Git, Cargo/Rust, JavaScript, Python, Go, Ruby, .NET, Docker/Kubernetes, and more. See [What RTK Optimizes](./resources/what-rtk-covers.md) for the full list with savings percentages.
## Get started
1. **[Installation](./getting-started/installation.md)** — Install RTK and verify you have the right package
2. **[Quick Start](./getting-started/quick-start.md)** — Connect to your AI assistant in 5 minutes
3. **[Supported Agents](./getting-started/supported-agents.md)** — Claude Code, Cursor, Copilot, Gemini, and more
## Measure your savings
```bash
rtk gain # total savings across all sessions
rtk gain --daily # day-by-day breakdown
rtk gain --weekly # weekly aggregation
```
See [Token Savings Analytics](./analytics/gain.md) for export formats and analysis workflows.
## Analyze your usage
```bash
rtk discover # find commands that ran without RTK (missed savings)
rtk session # RTK adoption rate per Claude Code session
```
See [Discover and Session](./analytics/discover.md) for details.
## Further reading
- [Configuration](./getting-started/configuration.md) — config.toml, global flags, env vars, tee recovery
- [Troubleshooting](./resources/troubleshooting.md) — common issues and fixes
- [Telemetry & Privacy](./resources/telemetry.md) — what RTK collects and how to opt out
- [ARCHITECTURE.md](https://github.com/rtk-ai/rtk/blob/master/ARCHITECTURE.md) — system design for contributors