Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
arxiv-summarization
Datasets & benchmarksHugging Face dataset by ccdv
ccdv/arxiv-summarization -
code_search_net
Datasets & benchmarksHugging Face dataset by code-search-net
code-search-net/code_search_net -
spider
Datasets & benchmarksHugging Face dataset by xlangai
xlangai/spider -
action100m-preview
Datasets & benchmarksHugging Face dataset by facebook
facebook/action100m-preview -
qwen3.8-max-glm5.2-kimi-k3-distillation
Datasets & benchmarksHugging Face dataset by r0b0tlab
r0b0tlab/qwen3.8-max-glm5.2-kimi-k3-distillation -
Llama-Nemotron-VLM-Dataset-v1
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/Llama-Nemotron-VLM-Dataset-v1 -
ai-powershell-standards
SkillsEnterprise-grade PowerShell development standards, shipped as GitHub Copilot instructions and Claude Code rules, for consistent, secure, and high-quality PowerShell code across teams and projects.
git clone https://github.com/fadwen/ai-powershell-standards.git -
MINT-1T-HTML
Datasets & benchmarksHugging Face dataset by mlfoundations
mlfoundations/MINT-1T-HTML -
backenly
MCP serversAutonomous backend platform. Your coding agent builds it over MCP, Backenly keeps it running: Postgres, REST APIs, auth, storage, realtime, and functions, with every change governed, verified, and reversible.
git clone https://github.com/backenly/backenly.git -
gigaspeech
Datasets & benchmarksHugging Face dataset by speechcolab
speechcolab/gigaspeech -
RLAIF-V-Dataset
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/RLAIF-V-Dataset -
lumi-4b
Modelstext generation model by ceia-br
ceia-br/lumi-4b -
openpost
MCP serversCreate, adapt, schedule, and track social posts. Open-source, hosted or self-hosted.
git clone https://github.com/getopenpost/openpost.git -
windiff
SkillsTool that allows comparing symbol, type and syscall information of Microsoft Windows binaries across different versions of the OS, using a Web UI and/or LLMs.
git clone https://github.com/ergrelet/windiff.git -
dialogsum
Datasets & benchmarksHugging Face dataset by knkarthick
knkarthick/dialogsum -
ClaudeSkills
Skills13 curated Agent Skills for research, product decisions, decks, publishing, audits, and more — portable across skills-compatible agents.
git clone https://github.com/staruhub/ClaudeSkills.git -
sst2
Datasets & benchmarksHugging Face dataset by stanfordnlp
stanfordnlp/sst2 -
image text to text model by huihui-ai · transformers
huihui-ai/Huihui-Qwen3.8-Flash-Next-abliterated-GGUF -
chubbyskills
Skills把中文全渠道内容(抖音 / B站 / 小红书 / 公众号 / X / 播客)采集进个人知识库的 14 个 AI Skill:图文存图、视频转文字稿、字幕优先免 GPU、RSS/YouTube 订阅调度与每日情报简报,附带知识库 MCP server。| Ingest Chinese content into your personal knowledge base — image/video routing, subtitle-first transcription, feed subscriptions with daily digests, and a KB MCP server.
git clone https://github.com/chubbyguan/chubbyskills.git -
SWE-ZERO-12M-trajectories
Datasets & benchmarksHugging Face dataset by AlienKevin
AlienKevin/SWE-ZERO-12M-trajectories -
bgts-context-engine
AI repositoriesDeterministic code-graph context engine for AI coding agents - PostgreSQL + Apache AGE + pgvector, MCP & REST, no LLM in the loop.
git clone https://github.com/bgts-ai-org/bgts-context-engine.git -
mira
Agents & frameworksa best-effort approximation of a synthetic entity complete with all of the primatives required for long-horizon persistance. batteries included.
git clone https://github.com/taylorsatula/mira.git -
Oracle3 prediction-market agent tools
MCP serversKalshi and Polymarket data, venue fees, no-arbitrage checks and paper execution for AI agents.
oracle3@1.3.0 -
gtm-cofounder
Tools & apps#1 Product of The Day @ Product Hunt. The GTM co-founder you don't have. Open-source GTM Agent Skills for developer tools and AI products, for founders, GTM hires, and founding AEs: positioning, first users, launch, pricing. Sharpened by Frankl & Czakon. MIT.
git clone https://github.com/AIDevGTM/gtm-cofounder.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.