InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. automatic speech recognition model by netease-youdao · transformers

    Indexed Hugging Face Hub, netease-youdao 616 ♥otherUpdated 10 days ago

    netease-youdao/Confucius4-R2T2
  2. Engineering practices for market-data, trading and low-latency financial systems: hot/cold paths, bounded resources, ownership and independent review.

    Stale GitHub, be0hhh 8 ★Apache-2.0Updated 15 days ago

    git clone https://github.com/be0hhh/blazing-market.git
  3. Earlybird-29M

    Models

    automatic speech recognition model by sahilmahendrakar · transformers

    Indexed Hugging Face Hub, sahilmahendrakar 33 ♥mitUpdated 5 days ago

    sahilmahendrakar/Earlybird-29M
  4. infinity

    AI repositories

    Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

    Stale GitHub, michaelfeil 2,984 ★MITUpdated 6 days ago

    git clone https://github.com/michaelfeil/infinity.git
  5. pinot

    Agents & frameworks

    Apache Pinot: a real-time analytics database for low-latency SQL and vector search, serving user-facing and agent-facing applications

    Indexed GitHub, apache 6,175 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/apache/pinot.git
  6. voxlock

    Models

    audio to audio model by arbazsiddiqui

    Stale Hugging Face Hub, arbazsiddiqui 24 ♥apache-2.0Updated 35 days ago

    arbazsiddiqui/voxlock
  7. Vision-Agents

    Agents & frameworks

    Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

    Stale GitHub, GetStream 8,201 ★Apache-2.0Updated 13 days ago

    git clone https://github.com/GetStream/Vision-Agents.git
  8. A knowledge base and runnable curriculum from junior to distinguished engineer: CS foundations, DSA, system design, C++ and Python, quant and low-latency systems, agentic AI, cloud AI, developer toolchain, and shell and Unix engineering.

    Indexed GitHub, shreejitverma 26 ★MITUpdated yesterday

    git clone https://github.com/shreejitverma/The-Distinguished-Engineer.git
  9. Low-latency voice agents for real-time conversations.

    Indexed AETHER official model feed, Google Updated 2 months ago

  10. sublinear-time-solver

    MCP servers

    Rust + WASM sublinear-time solver for asymmetric diagonally dominant systems. Exposes Neumann series, push, and hybrid random-walk algorithms with npm/npx CLI and Flow-Nexus HTTP streaming for swarm cost propagation and verification.

    Stale GitHub, ruvnet 93 ★MITUpdated 5 days ago

    git clone https://github.com/ruvnet/sublinear-time-solver.git
  11. Yahoo Finance

    Public APIs

    Real time low latency Yahoo Finance API for stock market, crypto currencies, and currency exchange

    Indexed public-apis (GitHub list)

  12. kernel-mcp-server

    MCP servers

    Open-source MCP server for secure, low-latency cloud-browser automation on Kernel.

    Stale GitHub, kernel 39 ★MITUpdated 6 days ago

    git clone https://github.com/kernel/kernel-mcp-server.git
  13. Ultra-low-latency incremental line validator with chunk boundary reassembly and schema auditing

    Stale Official MCP Registry, io.github.alphaparkinc Updated 28 days ago 1 note

    https://github.com/Alpha-Park/genpark-streaming-ndjson-jsonl-schema-validator-skill/releases/download/v1.0.1/genpark-streaming-ndjson-jsonl-schema-validator-skill.mcpb
  14. TerraBlind

    Agents & frameworks

    TerraBlind is an open-source Terraria AI agent framework built on tModLoader, featuring autonomous gameplay, pathfinding, world perception, building, combat, and AI-driven decision-making with LLMs and low-latency decision models.

    Indexed GitHub, Reisenbug 79 ★MITUpdated yesterday

    git clone https://github.com/Reisenbug/TerraBlind.git
  15. Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

    Indexed OpenRouter model list, mistralai Updated 21 months ago

    mistralai/mistral-small-24b-instruct-2501
  16. NornicDB

    MCP servers

    Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.

    Indexed GitHub, orneryd 931 ★MITUpdated yesterday

    git clone https://github.com/orneryd/NornicDB.git
  17. GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...

    Indexed OpenRouter model list, openai Updated 11 months ago

    openai/gpt-5.2-chat
  18. GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

    Indexed OpenRouter model list, openai Updated 15 months ago

    openai/gpt-5-nano
  19. For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

    Indexed OpenRouter model list, openai Updated 19 months ago

    openai/gpt-4.1-nano
  20. GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

    Indexed OpenRouter model list, openai Updated 15 months ago

    openai/gpt-5-nano:batch
  21. For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

    Indexed OpenRouter model list, openai Updated 19 months ago

    openai/gpt-4.1-nano:batch
  22. Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

    Indexed OpenRouter model list, mistralai Updated 15 months ago

    mistralai/codestral-2508
  23. GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

    Indexed OpenRouter model list, openai Updated 8 months ago

    openai/gpt-5.4-nano
  24. GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

    Indexed OpenRouter model list, openai Updated 8 months ago

    openai/gpt-5.4-nano: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.