Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Tencent: Hy3 preview
ModelsHy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
tencent/hy3-preview -
Qwen: Qwen3 Coder Next
ModelsQwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
qwen/qwen3-coder-next -
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
nvidia/nemotron-3-nano-30b-a3b -
Relace: Relace Search
ModelsThe relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...
relace/relace-search -
Relace: Relace Apply 3
ModelsRelace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...
relace/relace-apply-3 -
MoonshotAI: Kimi K2 0711
ModelsKimi 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...
moonshotai/kimi-k2 -
Qwen: Qwen3 30B A3B
ModelsQwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
qwen/qwen3-30b-a3b -
Reka Flash 3
ModelsReka 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...
rekaai/reka-flash-3 -
Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...
perplexity/sonar-deep-research -
Inception: Mercury 3
ModelsMercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...
inception/mercury-3 -
Unified, High-Precision Research & Analysis Prompt for ChatGPT and Perplexity AI ROLE & BEHAVIOR You are a professional researcher-analyst. Handle inputs as follows: * If the input is a URL/URI: open it fully with your…
-
StreamKollen — Swedish Streaming Guide
MCP serversWhere movies & TV stream in Sweden, trending titles and live sport broadcasts.
-
Tencent: Hy3
ModelsHy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
tencent/hy3 -
NVIDIA: Nemotron 3 Super
ModelsNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
nvidia/nemotron-3-super-120b-a12b -
MiniMax: MiniMax M2-her
ModelsMiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...
minimax/minimax-m2-her -
Google: Gemma 2 27B
ModelsGemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...
google/gemma-2-27b-it -
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...
baidu/ernie-5.5-flash-preview -
Act as an Instagram strategist for independent musicians who sell DIRECT to fans. Streams pay fractions of a cent and create no real connection. Your job is to write captions that get fans to click the link and BUY…
-
a2ui
AI repositoriesOpen-source generative UI framework: agents stream layout data, and apps render it with native components in React, Angular, Lit, Flutter, SwiftUI and Jetpack Compose.
git clone https://github.com/a2ui-project/a2ui.git -
Research connections
PromptsWrite a prompt or code that I can input 2 people's names. Prompt ans code is for searching osint and other online sources to find hidden personal connections betwern the 2 people's names input into the search
-
Managed Streaming for Kafka
Public APIsThe operations for managing an Amazon MSK cluster.
-
tabii (TRT Streaming)
MCP serversUnofficial read-only MCP server for tabii.com — TRT streaming catalog, live channels, people.
tabii-mcp@0.1.0 -
Turns a company's website text into a short list of problems you can see evidence for, what each might cost, and the one fix worth raising first.
-
ai
Agents & frameworksA Go toolkit for building AI agents and applications across multiple providers. Unified LLM client, agent framework with handoffs, tool calling, streaming, structured output, MCP integration, and cost tracking.
git clone https://github.com/JoakimCarlsson/ai.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.