GStars
    rtk-ai

    rtk-ai/rtk

    CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

    cli
    developer-tools
    llm
    agentic-coding
    ai-coding
    anthropic
    claude-code
    command-line-tool
    Rust
    Apache-2.0
    86.1K stars
    5.5K forks
    216 GitHub watchers
    Updated Nov 11, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    5 releases in the last 90 days, the latest today, with 195 contributors on GitHub.

    Peaked at #5 in the weekly ranking the week of Apr 26, its best in the past year.

    Use Cases & Benefits

    • Provides a high-performance CLI proxy that reduces large language model token consumption by 60-90% on common developer commands.
    • Delivers significant token savings with minimal overhead using smart filtering, grouping, truncation, and deduplication in a single Rust binary.
    • Use for optimizing token usage in AI-assisted coding workflows with tools like Claude Code, GitHub Copilot, and Gemini CLI.
    • Use for compressing and summarizing outputs of test runners and build tools to reduce verbosity and token costs in CI/CD pipelines.
    • Use for compactly viewing and managing cloud resources, container statuses, and package dependencies with token-efficient command outputs.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Apache 2.0

    Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.

    Community files

    • README: present
    • Contributing guide: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

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

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

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

    Excerpt from the rtk-ai/rtk README on GitHub (Apache-2.0 license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Aug 14: +60Aug 29: +73Sep 2: +57Sep 3: +185Sep 4: +119Sep 5: +57Sep 6: +452Sep 7: +184Sep 8: +250Sep 9: +172Sep 10: +152Sep 11: +140Sep 12: +108Sep 13: +87Sep 14: +183Sep 15: +158Sep 16: +207Sep 17: +145Sep 18: +62Sep 19: +90Sep 20: +60Oct 4: +31Oct 7: +39Oct 17: +98

    +10,100 stars over 90 days across 35 snapshot days; best day +452 on Sep 6.

    Forks

    5.5K+732

    Open issues

    1.7K-294

    Compared with peers in CLI

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth

    View category →
    rtk-ai/rtk compared with CLI repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    morluto/rea450.0K+22.9K7516 days ago
    mattpocock/skills320.9K+9.5K7512 days ago
    vercel-labs/agent-desktop21.4K+8.7K755 days ago
    stablyai/orca121.4K+6.7K75today
    vercel-labs/agent-browser49.2K+3.8K751 day ago
    rtk-ai/rtk86.1K—75today
    Category median121.4K+8.7K75—
    Compare rtk with rea, skills, agent-desktop →

    Discover Repositories

    Search across tracked repositories by name or description