prompt-caching repositories
Trending repositories tagged prompt-caching, ranked by trending score. Updated daily.
-
1
karanb192/cache-tax
Keep Claude Code’s prompt cache warm during breaks and show the estimated cost before a cold send.
GitHub · TypeScript · 447 stars · 61 forks · +68 stars in 24 hours · Trending score 3.09
-
2
HeyCubit/effortless
Mods for Claude Code. effortless picks the reasoning effort for every prompt and shows the cache countdown. textless (desktop app) shows art, quotes and chess instead of the wall of text while Claude works.
GitHub · HTML · 356 stars · 38 forks · +26 stars in 24 hours · Trending score 2.34
-
3
localixai/tokendoctor
tokendoctor: the same Claude Code for up to 38% less. Replays your own past sessions to show what each change would have saved, then changes only what you pick
GitHub · TypeScript · 171 stars · 12 forks · +7 stars in 24 hours · Trending score 2.20
-
4
ARahim3/cachebeat
A tiny Claude Code skill that keeps your prompt cache warm during idle sessions, so your next message reads from cache instead of paying full price.
GitHub · Shell · 90 stars · 11 forks · +19 stars in 24 hours · Trending score 2.19
-
5
paulbkim-dev/claude-code-cache-warmer
Claude Code mod that keeps the prompt cache warm and shows each refresh's cost and saving
GitHub · TypeScript · 26 stars · 2 forks · +12 stars in 24 hours · Trending score 1.88
-
6
archid21/rightsize
Make every Claude token count. rightsize picks the right model and effort for each prompt, while keeping cache and context costs low. It learns how you work and gets better over time.
GitHub · TypeScript · 48 stars · 13 forks · +3 stars in 24 hours · Trending score 1.76
-
7
chipfighter/context-attachment-manager
A local plugin for image-heavy chats in Codex, Claude Code and other AI agents: earlier images become short placeholders instead of going out with every message, the model fetches the original back by its ID (also after compaction), and the prompt cache keeps working.
GitHub · TypeScript · 813 stars · 76 forks · +7 stars in 24 hours · Trending score 1.69
-
8
NightFrost42/dsh-compaction-weave
Cache-friendly context compaction for DeepSeek Harness, with requirement retention, task continuity, history retrieval, and retries.
GitHub · JavaScript · 32 stars · 1 forks · +22 stars in 24 hours · Trending score 1.69
-
9
mralexivy/AutoMode
Self-tuning model and effort router for Claude Code. Picks Haiku, Sonnet or Opus per prompt, learns from your own sessions, keeps long chats cache-warm, adds risk floors and a review workflow. No key, no server.
GitHub · TypeScript · 80 stars · 1 forks · +4 stars in 24 hours · Trending score 1.68
-
10
inevolin/claude-code-usage-analysis
Empirical analysis of Claude Code token usage: auto-compaction sweet spots across 8 developer workflows and Claude Desktop vs. CLI overhead
GitHub · Python · 151 stars · 5 forks · +26 stars in 24 hours · Trending score 1.57
-
11
pleasedodisturb/awesome-llm-token-optimization
A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.
GitHub · Shell · 126 stars · 41 forks · +7 stars in 24 hours · Trending score 1.56
-
12
karanb192/claude-code-mods
Claude Mods and the tools to build them: a builder skill, then mods
GitHub · JavaScript · 49 stars · 9 forks · +7 stars in 24 hours · Trending score 1.56
-
13
WXK-AI/jev-opus
Claude Opus 5.5 with the effort level re-decided every step by the TypeSafe Jev reflex — without breaking the prompt cache. CLI + Claude Code plugin.
GitHub · TypeScript · 18 stars · 2 forks · +7 stars in 24 hours · Trending score 1.56
-
14
cablate/ctx-handoff-mod
Claude Code mod: hands off to a fresh conversation when context fills up, keeps the cache warm while you're away, and turns what you teach Claude into project notes
GitHub · TypeScript · 132 stars · 13 forks · +7 stars in 24 hours · Trending score 1.54
-
15
Wenaixi/dsh-ponytail
DeepSeek Harness plugin: DietrichGebert/ponytail lazy senior mode & 7-rung ladder port, 6 skills with bilingual descriptions & per-skill toggles, zero tools, zero-cache-miss | DeepSeek Harness 插件:DietrichGebert/ponytail 懒人 senior 模式与七阶梯子完美移植,6 个技能描述双语自由切换,各个技能自由开关,零 tool 注册,全场景零缓存破坏
GitHub · JavaScript · 50 stars · 2 forks · +4 stars in 24 hours · Trending score 1.15
-
16
crmne/copilot-triage
Simple issue triage without GitHub Agentic Workflows. One small Ruby script, cheap Copilot prompts, cached replies. Stop maintaining your issue bot.
GitHub · Ruby · 30 stars · 1 forks · +3 stars in 24 hours · Trending score 1.00
-
17
vayaan-labs/cache-maxxer
A Claude Code mod that keeps your cache warm, so you pay 96% less to re-read your conversation
GitHub · TypeScript · 13 stars · 2 forks · +3 stars in 24 hours · Trending score 0.93
-
18
wquguru/fable52-fps-repro
Fable 5.2 一句话生成 3D FPS 复现:4 个单文件演示、提示词与缓存账单 / One-prompt 3D FPS repro with demos, prompts & cost data
GitHub · HTML · 119 stars · 20 forks · 0 stars in 24 hours · Trending score 0.91
-
19
Vaan21th/daemonkey-agent
Local-first AI companion daemon — an agent harness with its own long-term memory. Remembers you, grows with you, extends and repairs itself. 跑在你自己电脑上的 AI 搭档守护进程:会记住你、随你成长、能自加技能、能自我修复。
GitHub · Python · 96 stars · 13 forks · +3 stars in 24 hours · Trending score 0.90
-
20
MerkyorLynn/Lynn
开源桌面 AI Agent 与 CLI:长期记忆、多 Agent、实时语音;Qwen3.8-27B Coder390 EfficientThink 本地 GGUF(llama.cpp Q2/Q3,内置 Q4 MTP)· Open-source desktop AI agent & CLI with Coder390 local models
GitHub · TypeScript · 73 stars · 5 forks · +2 stars in 24 hours · Trending score 0.75
-
21
rossoctl/context-guru
Context optimization for AI coding agents — lower token cost and latency without sacrificing accuracy.
GitHub · Go · 76 stars · 25 forks · +1 stars in 24 hours · Trending score 0.73
-
22
noah-thing/lunchbox
A shared agent room: Claude Code, Codex, Grok, Gemini and local models work as one team on one task, on the logins you already have. Free for Mac, Windows and Linux.
GitHub · TypeScript · 16 stars · 2 forks · 0 stars in 24 hours · Trending score 0.65
-
23
mlcyclops/lucidagentide
Security-First Agentic IDE Coding Harness
GitHub · TypeScript · 28 stars · 4 forks · +1 stars in 24 hours · Trending score 0.55
-
24
tokensafe-dev/tokensafe
Your AI agent is smart enough to code all day. Now it actually can. Local runtime firewall & zero-loss context optimizer for AI coding agents.
GitHub · Python · 47 stars · 2 forks · 0 stars in 24 hours · Trending score 0.54