InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. local-skills-mcp

    MCP servers

    Universal MCP server for local filesystem skills with lazy loading and context-efficient discovery

    Stale Official MCP Registry, io.github.rkdpa Updated 12 months ago 1 note

    local-skills-mcp@0.2.1
  2. OKstays

    MCP servers

    Hotels ranked by real comfort, not commission: efficient AC, comfy beds, soundproof rooms and more

    Indexed Official MCP Registry, com.okstays Updated yesterday 1 note

  3. llm-price-compass

    Datasets & benchmarks

    This project collects GPU benchmarks from various cloud providers and compares them to fixed per token costs. Use our tool for efficient LLM GPU selections and cost-effective AI models. LLM provider price comparison, gpu benchmarks to price per token calculation, gpu benchmark table

    Stale GitHub, arc53 221 ★MITUpdated 23 months ago

    git clone https://github.com/arc53/llm-price-compass.git
  4. Electronics Architect

    MCP servers

    Solve a DC/DC power tree: per-stage current, efficiency, dissipation, thermals, tolerance corners.

    Stale Official MCP Registry, com.electronics-architect Updated 50 days ago 1 note

  5. Mockups Gallery

    MCP servers

    Self-hosted gallery for AI-generated mockups. MCP interface; token-efficient curl uploads.

    Stale Official MCP Registry, io.github.kgNatx Updated 54 days ago 2 notes

    ghcr.io/kgnatx/mockups-mpc:1.5.1
  6. ContextPilot

    Prompts

    Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.

    Stale GitHub, EfficientContext 145 ★Apache-2.0Updated 26 days ago

    git clone https://github.com/EfficientContext/ContextPilot.git
  7. Build applications to efficiently manage large or complex trafficking, reporting, and attribution workflows for Campaign Manager 360.

    Indexed APIs.guru OpenAPI Directory, Google Updated 3 years ago

  8. Agent Colosseum

    MCP servers

    Daily puzzle arena for AI agents over MCP, ranked by step-efficiency on a public leaderboard.

    Stale Official MCP Registry, com.theagentcolosseum Updated 6 days ago 1 note

  9. tinystruct

    Agents & frameworks

    A lightweight, modular Java application framework for web and CLI development, designed for AI integration and plugin-based architecture. Enabling developers to create robust solutions with ease for building efficient and scalable applications.

    Indexed GitHub, tinystruct 365 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/tinystruct/tinystruct.git
  10. Local MCP gateway that proxies AI clients to many MCP servers with a token-efficient code mode

    Stale Official MCP Registry, io.github.perforce Updated 57 days ago 1 note

    perforce-agentic-gateway@2026.6
  11. Gemma AI MCP

    MCP servers

    Experience Google's Gemma AI models for free. Chat with Gemma 4 26B and 31B - powerful, efficient

    Stale Official MCP Registry, io.github.rocnubie Updated 5 months ago

  12. dual-brain

    Prompts

    A dual-agent framework leveraging left-brain logic (structured coding, syntax validation, debugging) and right-brain intuition (macro architecture, creative patterns, UX flows). It splits cognitive loads to boost LLM development efficiency, preventing hallucination while maximizing system scalability.

    Stale GitHub, sleeplesshan 123 ★MITUpdated 11 days ago

    git clone https://github.com/sleeplesshan/dual-brain.git
  13. pivoshenko.ai

    Skills

    🧙♂️ My AI workspace focused on developer productivity and agentic efficiency

    Stale GitHub, pivoshenko 6 ★MITUpdated 27 days ago

    git clone https://github.com/pivoshenko/pivoshenko.ai.git
  14. MCP server that decodes V8 CPU profiles into token-efficient bottleneck summaries for AI agents

    Stale Official MCP Registry, io.github.vola-trebla Updated 6 months ago 1 note

    v8-cpu-profile-decoder-mcp@0.3.0
  15. Access SEC filings efficiently (10-K, 10-Q, etc), save time and tokens, and get cited answers.

    Stale Official MCP Registry, ai.alphacreek Updated 5 months ago 1 note

  16. MCP Server that turns your AI agent into a localization expert with token-efficient i18n translation

    Stale Official MCP Registry, io.github.l10n-dev Updated 6 days ago 2 notes

    ai-l10n-mcp@1.2.2
  17. winx-code-agent

    MCP servers

    🦀 A high-performance code agent written in Rust, combining the best features of WCGW for maximum efficiency and semantic capabilities.

    Stale GitHub, gabrielmaialva33 38 ★MITUpdated 18 days ago

    git clone https://github.com/gabrielmaialva33/winx-code-agent.git
  18. firefox-cli

    Skills

    Let AI Agents control your real firefox browser: fill forms, authenticate, automate actions, web development; all via token-efficient, easy to use CLI. Claude plugin / Codex skill included. agent-browser, but for Firefox chads.

    Stale GitHub, respawn-llc 24 ★AGPL-3.0Updated 31 days ago

    git clone https://github.com/respawn-llc/firefox-cli.git
  19. Real-time performance and profit leaderboard for the GenPark Alpha Layer. Showcasing the most efficient nodes in the agent economy.

    Stale GitHub, Alpha-Park 8 ★MITUpdated 17 days ago

    git clone https://github.com/Alpha-Park/openclaw-genpark-alpha-leaderboard.git
  20. A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

    Indexed OpenRouter model list, mistralai Updated 11 months ago

    mistralai/ministral-8b-2512
  21. The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

    Indexed OpenRouter model list, mistralai Updated 11 months ago

    mistralai/ministral-3b-2512
  22. # Optimization Auditor You are a senior optimization engineering expert and specialist in performance profiling, algorithmic efficiency, scalability analysis, resource optimization, caching strategies, concurrency…

    Indexed prompts.chat (CC0 prompt collection), wkaandemir CC0-1.0

  23. VectorizedMultiAgentSimulator

    Agents & frameworks

    VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

    Stale GitHub, proroklab 621 ★GPL-3.0Updated 6 months ago

    git clone https://github.com/proroklab/VectorizedMultiAgentSimulator.git
  24. 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 5 days ago

    git clone https://github.com/MerkyorLynn/Lynn.git

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.