InnerVault

Library

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

Results

  1. Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

    Indexed OpenRouter model list, moonshotai Updated 16 months ago

    moonshotai/kimi-k2
  2. Reka Flash 3

    Models

    Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...

    Indexed OpenRouter model list, rekaai Updated 20 months ago

    rekaai/reka-flash-3
  3. --- name: csv-diff-and-reconciliation-checker description: Compares two CSV exports of the same records (old vs new, billing vs ledger, source vs warehouse) by key after normalizing headers, delimiters, currency…

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

  4. ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total...

    No longer listed OpenRouter model list, baidu Updated 7 days ago

    baidu/ernie-5.5-flash-preview
  5. agent-web-actions

    MCP servers

    Stealth web automation for AI agents. Login, signup, navigate, screenshot.

    Stale Official MCP Registry, com.trycloudflare.clients-involving-billion-headers Updated 4 months ago 1 note

  6. Investigate and fix the actual $ usages in Markdown content. The $ fall into three classes: - Currency (escape these) — $1, $2 billion, R$ 549 → these pairs cause all the warnings - Real math (leave alone) —…

    Indexed prompts.chat (CC0 prompt collection), aldinei@gmail.com CC0-1.0

  7. { "role": "You are a calm, practical personal finance assistant who specializes in recurring charges. You help people find every subscription and repeating bill hidden in their statements, decide what to keep, and…

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

  8. ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total...

    Indexed OpenRouter model list, baidu Updated 7 days ago

    baidu/ernie-5.5-flash-preview:free
  9. { "role": "Calm, careful hotel-bill review assistant who helps travelers understand a hotel folio or invoice, compare it with what was booked and what actually happened during the stay, organize overcharge evidence…

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

  10. Sprig Fit Images

    MCP servers

    Inspect local photos and crop, resize or compress images to exact dimensions and file-size limits.

    Stale Official MCP Registry, io.github.BillyQin Updated 27 days ago 1 note

    sprig-fit-mcp@0.1.1
  11. MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...

    No longer listed OpenRouter model list, minimax Updated 10 months ago

    minimax/minimax-m2.1
  12. Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

    Indexed OpenRouter model list, meta-llama Updated 19 months ago

    meta-llama/llama-4-scout
  13. Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...

    Indexed OpenRouter model list, meta-llama Updated 2 years ago

    meta-llama/llama-3.2-1b-instruct
  14. Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

    Indexed OpenRouter model list, meta-llama Updated 2 years ago

    meta-llama/llama-3.2-3b-instruct
  15. ai-video-generator

    MCP servers

    AI video generation API with x402 USDC payment. TTS voiceover, animated text.

    Stale Official MCP Registry, com.trycloudflare.clients-involving-billion-headers Updated 4 months ago 1 note

  16. Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...

    Indexed OpenRouter model list, qwen Updated 6 months ago

    qwen/qwen3.6-27b
  17. Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

    Indexed OpenRouter model list, meta-llama Updated 19 months ago

    meta-llama/llama-4-maverick
  18. Unlock Pulse

    MCP servers

    Token unlock calendar for the next 60 days, rated by size vs circulating supply. Free, no key.

    Stale Official MCP Registry, io.github.Billibo6 Updated 13 days ago 1 note

  19. Subaccounts API

    Public APIs

    The Subaccounts API enables you to create subaccounts under your primary account. Subaccounts facilitate differential product configuration, reporting, and billing. The Subaccounts API is released initially with restricted availability. You can read more about the API in the Subaccounts documentation (/account/subaccounts/overview).

    Indexed APIs.guru OpenAPI Directory, Vonage DevRel Updated 3 years ago

  20. Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...

    Indexed OpenRouter model list, mistralai Updated 20 months ago

    mistralai/mistral-small-3.1-24b-instruct
  21. Skip to production. The open-source (Apache-2.0) production layer for agent-built software — auth, global + China billing, multi-tenancy and an AI gateway in one command, running locally with zero keys.

    Stale GitHub, Nebutra 5 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/Nebutra/Nebutra-Sailor.git
  22. Production-Grade PostHog Integration for Next.js 15 (App Router) Role You are a Senior Next.js Architect & Analytics Engineer with deep expertise in Next.js 15, React 19, Supabase Auth, Polar.sh billing, and PostHog…

    Indexed prompts.chat (CC0 prompt collection), Ted2xmen CC0-1.0

  23. VayuPress

    MCP servers

    Your whole online presence in one sovereign Go binary — website, blog, PGP mail, E2E-encrypted chat, anti-DDoS bot shield, privacy analytics, one-click Tor .onion, and Stripe/PayPal/crypto monetization. No SaaS bills, no third parties, no telemetry. Own your content, your mailbox, your infrastructure.

    Indexed GitHub, johalputt 23 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/johalputt/VayuPress.git
  24. Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

    Indexed OpenRouter model list, qwen Updated 3 months ago

    qwen/qwen3.8-2.4t-a95b

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.