InnerVault

Library

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

Results

Looks like a goal we have a starting path for: I want to research potential clients

  1. automatic speech recognition model by nvidia · nemo

    Stale Hugging Face Hub, nvidia 470 ♥cc-by-4.0Updated 6 months ago

    nvidia/canary-qwen-2.5b
  2. RouterArena

    Agents & frameworks

    RouterArena: An open framework for evaluating LLM routers with standardized datasets, metrics, an automated framework, and a live leaderboard.

    Stale GitHub, RouteWorks 157 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/RouteWorks/RouterArena.git
  3. whisper-large

    Models

    automatic speech recognition model by openai · transformers

    Stale Hugging Face Hub, openai 564 ♥apache-2.0Updated 2 years ago

    openai/whisper-large
  4. ClawProBench

    Datasets & benchmarks

    ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

    Stale GitHub, suyoumo 825 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/suyoumo/ClawProBench.git
  5. whisper-tiny

    Models

    automatic speech recognition model by openai · transformers

    Stale Hugging Face Hub, openai 467 ♥apache-2.0Updated 2 years ago

    openai/whisper-tiny
  6. canary-1b

    Models

    automatic speech recognition model by nvidia · nemo

    Stale Hugging Face Hub, nvidia 463 ♥cc-by-nc-4.0Updated 11 months ago

    nvidia/canary-1b
  7. Awesome-LLM-Eval

    Datasets & benchmarks

    Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表,主要面向基础大模型评测,旨在探求生成式AI的技术边界.

    Stale GitHub, onejune2018 659 ★MITUpdated 11 months ago

    git clone https://github.com/onejune2018/Awesome-LLM-Eval.git
  8. ai-model-world

    Datasets & benchmarks

    AI 大模型世界,把 556 个大模型拟人化成像素小人的可视化站点。进来就能看到此刻谁最聪明、谁最会写代码、谁最便宜、谁刚发布,往下是国内与国外分区的厂商广场、完整的发布时间线和多维排行榜。搜索认模型名、厂商和能力,输入「多模态」会直接列出全部多模态模型。数据取自 Epoch AI、models.dev、LiveBench 与 Hugging Face,每小时自动同步,所有文案由真实数据生成,不调用任何 LLM。Next.js 静态导出,零后端。

    Indexed GitHub, liyupi 274 ★MITUpdated today

    git clone https://github.com/liyupi/ai-model-world.git
  9. automatic speech recognition model by openai · transformers

    Stale Hugging Face Hub, openai 313 ♥apache-2.0Updated 2 years ago

    openai/whisper-medium
  10. canary-1b-v2

    Models

    automatic speech recognition model by nvidia · nemo

    Stale Hugging Face Hub, nvidia 438 ♥cc-by-4.0Updated 2 months ago

    nvidia/canary-1b-v2
  11. OpenClaw GenPark Alpha Leaderboard - Bayesian TrueSkill Glicko-2 matchmaker and anti-Sybil collusion auditor with conservative rating scores.

    Stale GitHub, alphaparkinc 7 ★MITUpdated 16 days ago

    git clone https://github.com/alphaparkinc/openclaw-genpark-alpha-leaderboard.git
  12. Real-time performance and profit leaderboard for the GenPark Alpha Layer. Showcasing the most efficient nodes in the agent economy.

    Stale GitHub, Alpha-Park 8 ★MITUpdated 16 days ago

    git clone https://github.com/Alpha-Park/openclaw-genpark-alpha-leaderboard.git
  13. git-leaderboard

    MCP servers

    Official MCP server for Git Leaderboard rankings, profiles, streaks, and user comparisons.

    Stale Official MCP Registry, io.github.hrvoje0099 Updated 23 days ago 1 note

    @gitleaderboard/mcp-server@0.1.9
  14. automatic speech recognition model by jonatasgrosman · transformers

    Stale Hugging Face Hub, jonatasgrosman 477 ♥apache-2.0Updated 3 years ago

    jonatasgrosman/wav2vec2-large-xlsr-53-english
  15. polymarket-paper-trader

    Datasets & benchmarks

    Paper trading simulator for Polymarket

    Stale GitHub, agent-next 495 ★MITUpdated 15 days ago

    git clone https://github.com/agent-next/polymarket-paper-trader.git
  16. automatic speech recognition model by nvidia · nemo

    Stale Hugging Face Hub, nvidia 639 ♥otherUpdated 3 months ago

    nvidia/nemotron-speech-streaming-en-0.6b
  17. SigRank SignalAF on-device scanner — four-token cascade, leaderboard, 25 local tools.

    Stale Official MCP Registry, io.github.SunrisesIllNeverSee Updated 31 days ago 1 note

    sigrank@1.0.47
  18. GPT-X3-150M

    Models

    text generation model by AxiomicLabs · transformers

    Stale Hugging Face Hub, AxiomicLabs 98 ♥apache-2.0Updated 22 days ago

    AxiomicLabs/GPT-X3-150M
  19. FastEval

    Datasets & benchmarks

    Fast & more realistic evaluation of chat language models. Includes leaderboard.

    Stale GitHub, FastEval 187 ★Apache-2.0Updated 2 years ago

    git clone https://github.com/FastEval/FastEval.git
  20. confabulations

    Datasets & benchmarks

    Hallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.

    Stale GitHub, lechmazur 249 ★Updated 15 months ago

    git clone https://github.com/lechmazur/confabulations.git
  21. modelplan

    Skills

    Which AI coding model, at which effort, on which plan? Recommended efforts, a leaderboard at those efforts and plan advice from modelplan.ai, in Claude Code, Codex and the terminal (plugins, Skill, CLI).

    Indexed GitHub, modelplan 41 ★MITUpdated today

    git clone https://github.com/modelplan/modelplan.git
  22. Daily ranks of consumer AI apps across the App Store and Google Play. Read-only, ranks only.

    Stale Official MCP Registry, fyi.ascension Updated 21 days ago 1 note

  23. debate

    Datasets & benchmarks

    Adversarial multi-turn benchmark for LLM debate quality, using side-swapped matchups and multi-model judging to rank models by judged debate performance.

    Stale GitHub, lechmazur 38 ★Updated 21 days ago

    git clone https://github.com/lechmazur/debate.git
  24. 14 models are statistically tied for #1 in Arena math, spanning 49 points. 4 are Flash models.

    Stale Official MCP Registry, com.modevc Updated 29 days ago 1 note

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.