caveman repositories

Trending repositories tagged caveman, ranked by trending score. Updated daily.

  1. 1
    JuliusBrussee/caveman

    why use many token when few token do trick. Skill + local proxy for coding agents: shorter answers, smaller tool output, every original recoverable.

    GitHub · Go · 122,048 stars · 7,118 forks · +429 stars in 24 hours · Trending score 5.09

  2. 2
    JayPokale/Chisle

    Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.

    GitHub · JavaScript · 1,251 stars · 79 forks · 0 stars in 24 hours · Trending score 1.73

  3. 3
    danielle34/cavewoman

    Caveman prompting, measured. A two-channel evaluation framework for prompt compression and LLM token efficiency: what input vs output compression costs in dollars, accuracy, and whether the reasoning changes. Compress the output not the prompt!! 9 models, 5 benchmarks, 10 languages. EMNLP 2026 Main

    GitHub · Python · 21 stars · 2 forks · +5 stars in 24 hours · Trending score 1.29

  4. 4
    mydisha/keirouter

    Your friendly, blazing-fast, self-hostable AI gateway

    GitHub · Go · 167 stars · 56 forks · +4 stars in 24 hours · Trending score 1.28

  5. 5
    JuliusBrussee/cavegemma

    LoRA fine-tune Gemma 4 31B to speak caveman-mode natively. Style: github.com/JuliusBrussee/caveman

    GitHub · Python · 123 stars · 15 forks · 0 stars in 24 hours · Trending score 0.94

  6. 6
    KurutoDenzeru/tersio

    ✂️ Token saver & usage tracker for coding agents: terse caveman replies, compact RTK shell output, lean Ponytail code, Headroom compression, pstack rigor, and a gain dashboard — one-command combos over one shared extension tree.

    GitHub · TypeScript · 37 stars · 6 forks · 0 stars in 24 hours · Trending score 0.45

  7. 7
    JuliusBrussee/cavemem

    Frozen — cross-agent persistent memory for coding assistants. Still works; the compressed-memory core now ships inside JuliusBrussee/caveman.

    GitHub · TypeScript · 679 stars · 56 forks · 0 stars in 24 hours · Trending score 0.43

  8. 8
    ilien-dev/sharur

    Cut Claude Code token usage and cost with a one-line output style. Shorter replies than Concise on every Claude model: 29% fewer output tokens and 23% lower cost on Opus 5.5. Benchmarked.

    GitHub · Python · 11 stars · 0 forks · +1 stars in 24 hours · Trending score 0.39

  9. 9
    simpletibr/simplicio

    🔥 Save up to 96% cost — more than Caveman (65%) or RTK (80%). AI coding agent: chat, map, edit, multi-agent. Single Rust binary.

    GitHub · Python · 30 stars · 0 forks · 0 stars in 24 hours · Trending score 0.10

  10. 10
    Gildaciolopes/agentic-dev-stack

    Smart vibe coding with Claude Code: multi-agent orchestration (Opus plans; Sonnet, Haiku, Gemini, Codex and free models execute), Spec Kit SDD, caveman + RTK + graphify token savings, sandboxed secrets, self-healing free models and a Hermes AI assistant. macOS, Linux, Windows.

    GitHub · TypeScript · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.07