InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. Omni-SafetyBench

    Datasets & benchmarks

    [ACM MM 2026 Oral] Code for paper "Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models".

    Stale GitHub, THU-BPM 115 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/THU-BPM/Omni-SafetyBench.git
  2. Language AI Engineering Lab, a place where you can deeply understand and build modern Language AI systems, from fundamentals to production.

    Stale GitHub, gil-son 129 ★GPL-3.0Updated 15 days ago

    git clone https://github.com/gil-son/language-ai-engineering-lab.git
  3. 50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.

    Stale GitHub, ContextJet-ai 46 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/ContextJet-ai/awesome-llm-observability.git
  4. ms-cookbook

    AI repositories

    魔搭紫皮书|ModelScope Cookbook:面向开发者的开源模型应用实战指南,覆盖模型选型、推理、微调、评测、RAG、Agent 与 AIGC,从跑通第一个模型到构建实际应用。

    Stale GitHub, modelscope 518 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/modelscope/ms-cookbook.git
  5. text generation model by nvidia · transformers

    Stale Hugging Face Hub, nvidia 457 ♥otherUpdated 2 months ago

    nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
  6. image text to text model by openbmb · minicpm-ocr

    Stale Hugging Face Hub, openbmb 452 ♥apache-2.0Updated 12 days ago

    openbmb/MiniCPM-OCR-1.0
  7. text generation model by inclusionAI

    Stale Hugging Face Hub, inclusionAI 95 ♥mitUpdated 12 days ago

    inclusionAI/Ling-3.1-flash-1019
  8. OpenART

    Skills

    OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.

    Stale GitHub, AI45Lab 263 ★AGPL-3.0Updated 15 days ago

    git clone https://github.com/AI45Lab/OpenART.git
  9. AgentLab

    Datasets & benchmarks

    AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

    Stale GitHub, ServiceNow 653 ★Custom licence (see repository)Updated 41 days ago

    git clone https://github.com/ServiceNow/AgentLab.git
  10. langfuse-docs

    Skills

    🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

    Stale GitHub, langfuse 253 ★MITUpdated 4 days ago

    git clone https://github.com/langfuse/langfuse-docs.git
  11. xVerify

    Datasets & benchmarks

    xVerify: Efficient Answer Verifier for Reasoning Model Evaluations

    Stale GitHub, IAAR-Shanghai 150 ★Custom licence (see repository)Updated 19 days ago

    git clone https://github.com/IAAR-Shanghai/xVerify.git
  12. ai-agents-tutorial

    Agents & frameworks

    Learn AI Agents step by step, from scratch - from function calling to agent loops to multi-agent systems, orchestration, and evaluation.

    Indexed GitHub, amitshekhariitbhu 212 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/amitshekhariitbhu/ai-agents-tutorial.git
  13. WritingBench

    Datasets & benchmarks

    WritingBench: A Comprehensive Benchmark for Generative Writing

    Stale GitHub, X-PLUG 202 ★Apache-2.0Updated 11 months ago

    git clone https://github.com/X-PLUG/WritingBench.git
  14. SWE-bench_Pro

    Datasets & benchmarks

    Hugging Face dataset by ScaleAI

    Stale Hugging Face Hub, ScaleAI 197 ♥Updated 55 days ago

    ScaleAI/SWE-bench_Pro
  15. GTA

    Agents & frameworks

    [NeurIPS 2024 D&B] GTA: A Benchmark for General Tool Agents & [arXiv 2026] GTA-2

    Indexed GitHub, open-compass 153 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/open-compass/GTA.git
  16. text classification model by perplexity-ai · pytorch

    Stale Hugging Face Hub, perplexity-ai 161 ♥apache-2.0Updated 35 days ago

    perplexity-ai/pplx-decider-v1.1-27b
  17. folkbench

    AI repositories

    帮你的 AI 编程工具找到不降智、不断连、高性价比的好线路 · Live LLM relay rankings, model integrity probes & Tauri/Rust switcher for Claude Code, Codex & Gemini CLI

    Indexed GitHub, Folkbench 3,883 ★Custom licence (see repository)Updated today

    git clone https://github.com/Folkbench/folkbench.git
  18. text generation model by nvidia · transformers

    Stale Hugging Face Hub, nvidia 437 ♥otherUpdated 2 months ago

    nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
  19. skillcheck

    Prompts

    Blind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.

    Stale GitHub, sx4im 30 ★MITUpdated 13 days ago

    git clone https://github.com/sx4im/skillcheck.git
  20. instructor-xl

    Models

    sentence similarity model by hkunlp · sentence-transformers

    Stale Hugging Face Hub, hkunlp 587 ♥apache-2.0Updated 3 years ago

    hkunlp/instructor-xl
  21. raglite

    AI repositories

    🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

    Stale GitHub, superlinear-ai 1,209 ★MPL-2.0Updated 31 days ago

    git clone https://github.com/superlinear-ai/raglite.git
  22. SWE-bench_Verified

    Datasets & benchmarks

    Hugging Face dataset by SWE-bench

    Stale Hugging Face Hub, SWE-bench 188 ♥Updated 3 months ago

    SWE-bench/SWE-bench_Verified
  23. audio text to text model by OpenMOSS-Team · transformers

    Stale Hugging Face Hub, OpenMOSS-Team 500 ♥apache-2.0Updated 2 months ago

    OpenMOSS-Team/MOSS-Transcribe-Diarize
  24. NuExtract3

    Models

    image to text model by numind · transformers

    Stale Hugging Face Hub, numind 377 ♥apache-2.0Updated 2 months ago

    numind/NuExtract3

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.