InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. copilot-cache-scout

    Agents & frameworks

    Multi-Agent Code Review Cost Benchmark 2026: Librarian vs Prompt Cache

    Indexed GitHub, PROrunner926 114 ★Updated today

    git clone https://github.com/PROrunner926/copilot-cache-scout.git
  2. Cache-bust forensics + TTL-fit verdicts: names the field that busts your prompt cache.

    Stale Official MCP Registry, com.textforagents Updated 25 days ago 1 note

  3. cachebeat

    Tools & apps

    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.

    Stale GitHub, ARahim3 71 ★MITUpdated 34 days ago

    git clone https://github.com/ARahim3/cachebeat.git
  4. DeepSeek-Reasonix

    Agents & frameworks

    A reliable coding agent for complex software engineering tasks.

    IndexedArchived GitHub, esengine 36.1k ★MITUpdated 4 days ago 1 note

    git clone https://github.com/esengine/DeepSeek-Reasonix.git
  5. contexere

    Agents & frameworks

    The one place for the skills, keys and memory of every agent you use. Formerly OMNI.

    Stale GitHub, fajarhide 377 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/fajarhide/contexere.git
  6. Lynkr

    Tools & apps

    Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.

    Indexed GitHub, Fast-Editor 640 ★Apache-2.0Updated yesterday

    git clone https://github.com/Fast-Editor/Lynkr.git
  7. always-accompany

    Agents & frameworks

    Companionship, chat, coding, and work share one memory and context framework — the kind of AI you see in science fiction: it keeps you company, and it gets things done with you.(这是一个基于上下文和注意力机制做的一个多元化的agent项目)

    Stale GitHub, beilusaiying 471 ★AGPL-3.0Updated 3 months ago

    git clone https://github.com/beilusaiying/always-accompany.git
  8. killi

    MCP servers

    Open-source AI coding agent for your terminal, written in Rust. One 7 MB native binary for Apple Silicon Macs, ~18 MB RAM, 70–90% prompt-cache hits. Works with OpenAI, Anthropic and any compatible LLM; MCP, subagents, plan mode, skills, hooks, AGENTS.md. A lightweight Claude Code / Codex CLI alternative.

    Indexed GitHub, timwuhaotian 56 ★MITUpdated today

    git clone https://github.com/timwuhaotian/killi.git
  9. superior-skills

    Prompts

    Build smarter. Work superior. An opinionated rule set for AI coding agents to create original interfaces, compelling content, and production-ready code.

    Stale GitHub, KodekaTeam 53 ★MITUpdated 8 days ago

    git clone https://github.com/KodekaTeam/superior-skills.git
  10. TokenSafe

    MCP servers

    Reduce your AI bills by up to 99% locally: focused code, warm prompt caches & zero secret leaks.

    Indexed Official MCP Registry, dev.tokensafe 41 ★Updated today 2 notes

    tokensafe@4.1.3
  11. A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.

    Indexed GitHub, pleasedodisturb 123 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/pleasedodisturb/awesome-llm-token-optimization.git
  12. somtum

    Skills

    Long-term memory for Claude Code and Codex that meters every token it spends

    Indexed GitHub, riz007 7 ★MITUpdated 3 days ago

    git clone https://github.com/riz007/somtum.git
  13. Lynn

    Agents & frameworks

    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

    Indexed GitHub, MerkyorLynn 71 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/MerkyorLynn/Lynn.git
  14. awesome-ai-tokenomics

    Docs & tutorials

    A curated list on AI token economics: what tokens cost, where they get wasted, and how to cut the bill. Tools, benchmarks, papers, and copy-paste configs for the token economy of LLMs and coding agents.

    Indexed GitHub, QuesmaOrg 219 ★CC0-1.0Updated 3 days ago

    git clone https://github.com/QuesmaOrg/awesome-ai-tokenomics.git
  15. token-optimizer-mcp

    MCP servers

    91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.

    Indexed GitHub, ooples 583 ★MITUpdated today

    git clone https://github.com/ooples/token-optimizer-mcp.git
  16. 安卓AI聊天端:开箱即聊,无损导入酒馆卡,专属RP模式,高定制主题,创造模式,RAG记忆,缓存强省用量,防空回,主动信息,前端卡支持,QQbot,AI群聊,插件系统,强兼容中转站。手机移动端原生支持,求 Star 收藏⭐Android AI Chatbox: lossless SillyTavern card import, aggressive cache optimization, Jev decisions, multi-dimensional memory, anti-blank-reply, proactive messages, AI group chat, SillyTavern themes, plugin system, Native mobile.RikkaHub

    Indexed GitHub, MiaoWuNYA 208 ★AGPL-3.0Updated today

    git clone https://github.com/MiaoWuNYA/rikkahub-sillytavern-android.git
  17. DoboCache

    MCP servers

    Stabilizes LLM prompt-cache prefixes so provider caching hits. One command setup, no baseURL edit.

    Indexed Official MCP Registry, io.github.dobo123123 Updated today 1 note

    dobocache@0.9.2
  18. Claude API Pricing

    MCP servers

    Current Claude API prices and cost estimates with prompt caching and Batch API pricing.

    Stale Official MCP Registry, app.agentwright Updated 6 days ago 1 note

  19. Cryptographic 563-leaf LLM rate oracle, context-cliff auditor, and prompt cache optimizer.

    Stale Official MCP Registry, io.github.cooyun Updated 15 days ago 1 note

  20. Estimate 2026 enterprise LLM API token costs, prompt caching savings, and developer benchmarks.

    Stale Official MCP Registry, com.omnitoolcalc Updated 5 days ago 1 note

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.