mirror of https://github.com/rtk-ai/rtk.git synced 2026-09-19 07:33:17 +08:00

Files

T

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

2.7 KiB

Raw Permalink Blame History

title, description, sidebar

title

description

sidebar

RTK Documentation

RTK (Rust Token Killer) — reduce LLM token consumption by 60-90% on common dev commands, with zero workflow changes

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 for the full list with savings percentages.

Get started

Installation — Install RTK and verify you have the right package
Quick Start — Connect to your AI assistant in 5 minutes
Supported Agents — Claude Code, Cursor, Copilot, Gemini, and more

Measure your savings

rtk gain           # total savings across all sessions
rtk gain --daily   # day-by-day breakdown
rtk gain --weekly  # weekly aggregation

See Token Savings Analytics for export formats and analysis workflows.

Analyze your usage

rtk discover       # find commands that ran without RTK (missed savings)
rtk session        # RTK adoption rate per Claude Code session

See Discover and Session for details.

2.7 KiB Raw Permalink Blame History