Library
87,622 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
-
courseatlas
MCP serversSearch and read the free AI School curriculum: lessons, course tracks, full lesson text.
Source for courseatlas (opens github.com) @reneturcios/courseatlas@0.1.0 -
kurdvoice
MCP serversKurdish speech tools: Sorani and Kurmanji text-to-speech and transcription, voices and plans.
Source for kurdvoice (opens github.com) @reneturcios/kurdvoice@0.1.0 -
lawclause
MCP serversSearch and cite privacy law clauses: GDPR and UAE PDPL texts, documents and versions.
Source for lawclause (opens github.com) @reneturcios/lawclause@0.1.0 -
Persian Wikipedia
MCP serversRead-only Persian Wikipedia (fa.wikipedia.org): search, summaries, article text, nearby places.
Source for Persian Wikipedia (opens github.com) persian-wikipedia-mcp@0.1.0 -
wiremark
SkillsText-based wireframing format that embeds in markdown like Mermaid. Familiar component names, indented to show containment, rendered in a hand-drawn style. Agent-first — trivial for LLMs to read and write.
Source for wiremark (opens github.com) git clone https://github.com/Blackburn-Labs/wiremark.git -
Upstage: Solar Mini 4
ModelsSolar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...
Source for Upstage: Solar Mini 4 (opens openrouter.ai) upstage/solar-mini4 -
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
Source for NVIDIA: Nemotron 3.5 Lightning (opens openrouter.ai) nvidia/nemotron-3.5-lightning -
Meta: Muse Glimmer 30B
ModelsMuse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...
Source for Meta: Muse Glimmer 30B (opens openrouter.ai) meta/muse-glimmer-30b -
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Source for DeepSeek: DeepSeek V4 Flash 0731 (opens openrouter.ai) deepseek/deepseek-v4-flash-0731 -
AionLabs: Aion-3.0
ModelsAion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...
Source for AionLabs: Aion-3.0 (opens openrouter.ai) aion-labs/aion-3.0 -
Sakana: Fugu Ultra
ModelsFugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
Source for Sakana: Fugu Ultra (opens openrouter.ai) sakana/fugu-ultra -
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
Source for NVIDIA: Nemotron 3 Ultra (free) (opens openrouter.ai) nvidia/nemotron-3-ultra-550b-a55b:free -
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Source for DeepSeek: DeepSeek V4 Flash 0423 (opens openrouter.ai) deepseek/deepseek-v4-flash -
Google: Lyria 3 Clip Preview
Models30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...
Source for Google: Lyria 3 Clip Preview (opens openrouter.ai) google/lyria-3-clip-preview -
AionLabs: Aion-2.0
ModelsAion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....
Source for AionLabs: Aion-2.0 (opens openrouter.ai) aion-labs/aion-2.0 -
ByteDance Seed: Seed 1.6
ModelsSeed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.
Source for ByteDance Seed: Seed 1.6 (opens openrouter.ai) bytedance-seed/seed-1.6 -
MoonshotAI: Kimi K2 Thinking
ModelsKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
Source for MoonshotAI: Kimi K2 Thinking (opens openrouter.ai) moonshotai/kimi-k2-thinking -
Perplexity: Sonar Pro Search
ModelsExclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...
Source for Perplexity: Sonar Pro Search (opens openrouter.ai) perplexity/sonar-pro-search -
Z.ai: GLM 4.6
ModelsCompared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
Source for Z.ai: GLM 4.6 (opens openrouter.ai) z-ai/glm-4.6 -
MoonshotAI: Kimi K2 0905
ModelsKimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
Source for MoonshotAI: Kimi K2 0905 (opens openrouter.ai) moonshotai/kimi-k2-0905 -
Nous: Hermes 4 405B
ModelsHermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
Source for Nous: Hermes 4 405B (opens openrouter.ai) nousresearch/hermes-4-405b -
Venice: Uncensored
ModelsVenice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...
Source for Venice: Uncensored (opens openrouter.ai) cognitivecomputations/dolphin-mistral-24b-venice-edition -
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...
Source for Tencent: Hunyuan A13B Instruct (opens openrouter.ai) tencent/hunyuan-a13b-instruct -
MiniMax: MiniMax M1
ModelsMiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...
Source for MiniMax: MiniMax M1 (opens openrouter.ai) minimax/minimax-m1
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.