Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
openlake
AI repositoriesOpenLake is a high performance storage engine for efficient LLM inference and GPU Training
git clone https://github.com/openlake-project/openlake.git -
port-throughput-mcp
MCP serversUS port cargo throughput: rankings, volumes by cargo type and year for every major port - keyless.
@mrfentmen/port-throughput-mcp@1.0.0 -
ollama-benchmark
Datasets & benchmarksLLM Benchmark for Throughput via Ollama (Local LLMs)
git clone https://github.com/aidatatools/ollama-benchmark.git -
vllm
AI repositoriesA high-throughput and memory-efficient inference and serving engine for LLMs
git clone https://github.com/vllm-project/vllm.git -
infinity
AI repositoriesInfinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
git clone https://github.com/michaelfeil/infinity.git -
surogate
AI repositoriesTrain and serve LLMs at extreme speed and massive throughput.
git clone https://github.com/invergent-ai/surogate.git -
mq-bridge-app
MCP serversMove data between 15+ databases, queues and files at high throughput, without it entering context
ghcr.io/marcomq/mq-bridge-app:1.0.2 -
SwiftKanban
Public APIsKanban software, Visualize Work, Increase Organizations Lead Time, Throughput & Productivity
-
mqb · mq-bridge
MCP serversMove data between 15+ databases, queues and files at high throughput, without it entering context
ghcr.io/marcomq/mq-bridge-app:1.6.1 -
GenPark Adaptive Batch Request Debouncer
MCP serversAdaptive sliding window query debouncing and micro-batch coalescing engine optimizing LLM throughput
https://github.com/Alpha-Park/genpark-adaptive-batch-request-debouncer-skill/releases/download/v1.0.1/genpark-adaptive-batch-request-debouncer-skill-v1.0.1.mcpb -
GenPark Aho-Corasick Multi-Pattern Matcher
MCP serversHigh-throughput Aho-Corasick automaton for simultaneous multi-keyword dictionary matching and conten
https://github.com/Alpha-Park/genpark-aho-corasick-multi-pattern-matcher-skill/releases/download/v1.0.1/genpark-aho-corasick-multi-pattern-matcher-skill-v1.0.1.mcpb -
openclaw-genpark-curator
SkillsOpenClaw GenPark Curator - High-throughput MinHash LSH dataset deduplication and content quality scoring engine.
git clone https://github.com/alphaparkinc/openclaw-genpark-curator.git -
GenPark JSON-RPC Batch Pipelining Dispatcher
MCP serversHigh-throughput JSON-RPC 2.0 batch pipelining and inter-tool parameter dependency resolver for Model
https://github.com/Alpha-Park/genpark-json-rpc-batch-pipelining-dispatcher-skill/releases/download/v1.0.1/genpark-json-rpc-batch-pipelining-dispatcher-skill-v1.0.1.mcpb -
OpenClaw GenPark Sentiment Harvester - High-throughput lexicon-decay sentiment polarity engine with valence shifting and time-weighted stream aggregation.
git clone https://github.com/alphaparkinc/openclaw-genpark-sentiment-harvester.git -
HTTP Benchmarking Tool CLI
PromptsCreate a high-performance HTTP benchmarking tool in Go. Implement concurrent request generation with configurable thread count. Add detailed statistics including latency, throughput, and error rates. Include support…
-
Caching Architect Agent Role
Prompts# Caching Strategy Architect You are a senior caching and performance optimization expert and specialist in designing high-performance, multi-layer caching architectures that maximize throughput while ensuring data…
-
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...
nvidia/nemotron-3.5-lightning -
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...
nvidia/nemotron-3.5-lightning:free -
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...
inference-net/schematron-v2-turbo -
Cohere: Command R+ (08-2024)
Modelscommand-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...
cohere/command-r-plus-08-2024 -
stabilize
Agents & frameworksQueue-Based State Machine - A lightweight workflow execution engine with DAG-based stage orchestration. Unlike simple task queues (like Celery) or advanced orchestrators (like Highway), Stabilize strikes a balance specifically optimized for high-throughput, stateful DAG execution, making it highly suitable for coordinating autonomous AI agents
git clone https://github.com/rodmena-limited/stabilize.git -
Qwen: Qwen3.8 Max Prime
ModelsQwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...
qwen/qwen3.8-max-prime -
OpenAI: GPT-5.4 Mini
ModelsGPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...
openai/gpt-5.4-mini -
OpenAI: GPT-5.4 Mini (batch)
ModelsGPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...
openai/gpt-5.4-mini:batch
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.