Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
OvisOCR3
Modelsimage text to text model by ATH-MaaS · transformers
ATH-MaaS/OvisOCR3 -
Safety-Prompts
PromptsChinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts,用于评估和提升大模型的安全性。
git clone https://github.com/thu-coai/Safety-Prompts.git -
vega-08b-public-intents
Modelstext classification model by nandakishorm · vega
nandakishorm/vega-08b-public-intents -
awesome-harness-engineering
Agents & frameworksAwesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
git clone https://github.com/ai-boost/awesome-harness-engineering.git -
apex-agents
Datasets & benchmarksHugging Face dataset by mercor
mercor/apex-agents -
agents-cli
AI repositoriesThe CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
git clone https://github.com/google/agents-cli.git -
hello-agent-system
Docs & tutorials👋 Hello Agent System — learn enterprise AI agent system design by building every production layer from scratch. 17 bilingual lessons (EN/中文) with tested exercises: tools, architectures, reliability, security, evals, distributed execution, cost, RAG, release ops. 企业级 Agent 系统设计训练营
git clone https://github.com/heaven999b/hello-agent-system.git -
Awesome-Scientific-LLM-Benchmarks
Datasets & benchmarksA curated, accuracy-first list of benchmarks for evaluating LLMs on scientific reasoning and discovery — math, physics, chemistry, materials, biology, and agentic science.
git clone https://github.com/subinium/Awesome-Scientific-LLM-Benchmarks.git -
image text to text model by nvidia · transformers
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 -
dokimi
SkillsDokimi (Greek δοκιμή, "test, proof") measures whether a skill, MCP doc source, agent profile or repository guidance actually helps a coding agent: paired on/off arm comparisons, novel-vs-known content analysis, and repository scans with graded agent runs.
git clone https://github.com/intel/dokimi.git -
text classification model by mrm8488 · transformers
mrm8488/embeddinggemma-2-ft-typed-decision -
joey-1
Modelstext classification model by baselabs · transformers
baselabs/joey-1 -
surya-ocr-2.5
Modelsimage text to text model by datalab-to · transformers
datalab-to/surya-ocr-2.5 -
suede-creator-skills
SkillsOpen-source skills for Claude Code and Codex, with an MCP server, a PyPI package and Suede Awesome Everything, a directory that scores AI agent skills 0 to 99. Created by Jason Colapietro, founder and CEO of Suede AI.
git clone https://github.com/JasonColapietro/suede-creator-skills.git -
Multi-User-LLM-Agent
Datasets & benchmarksOfficial code for the paper: "Multi-User Large Language Model Agents"
git clone https://github.com/Kordi-AI/Multi-User-LLM-Agent.git -
LightOnOCR-3-0.8B
Modelsimage text to text model by lightonai · transformers
lightonai/LightOnOCR-3-0.8B -
Introduction-to-Quantitative-Finance
AI repositoriesAI+金融(量化):1.多因子股票量化框架开源教程 2.学界和业界的经典资料收录 3.AI + 金融的相关工作,包括LLM, Agent, benchmark(evaluation), etc.
git clone https://github.com/Barca0412/Introduction-to-Quantitative-Finance.git -
tuui
MCP serversA desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
git clone https://github.com/AI-QL/tuui.git -
opencode-skill-creator
SkillsCreate, test, and optimize OpenCode skills. Supports OpenCode V2 and V1 ≥ 1.18.29. Adapted from Anthropic's skill-creator.
git clone https://github.com/antongulin/opencode-skill-creator.git -
openbench
Datasets & benchmarksSame model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost
git clone https://github.com/minghinmatthewlam/openbench.git -
vidore-benchmark
AI repositoriesVision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.
git clone https://github.com/illuin-tech/vidore-benchmark.git -
PawBench
Datasets & benchmarksA benchmark for evaluating LLM × harness performance.
git clone https://github.com/agentscope-ai/PawBench.git -
AICGSecEval
Datasets & benchmarksA.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.
git clone https://github.com/Tencent/AICGSecEval.git -
ai-rulez
SkillsAuthor, generate, validate and govern AI agent rules, skills, plugins and MCP configuration across 52 coding assistants. Review with verified model evidence, evaluate skills, lock and sign dependencies, and publish bundles. CLI, MCP server and Go API.
git clone https://github.com/Goldziher/ai-rulez.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.