Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
finepdfs
Datasets & benchmarksHugging Face dataset by HuggingFaceFW
HuggingFaceFW/finepdfs -
Mixture-of-Thoughts
Datasets & benchmarksHugging Face dataset by open-r1
open-r1/Mixture-of-Thoughts -
reazonspeech
Datasets & benchmarksHugging Face dataset by reazon-research
reazon-research/reazonspeech -
plandex
Agents & frameworksOpen source AI coding agent. Designed for large projects and real world tasks.
git clone https://github.com/plandex-ai/plandex.git -
MathInstruct
Datasets & benchmarksHugging Face dataset by TIGER-Lab
TIGER-Lab/MathInstruct -
medical-opinion-english-audio
Datasets & benchmarksHugging Face dataset by HumynLabs
HumynLabs/medical-opinion-english-audio -
Zhihu-KOL
Datasets & benchmarksHugging Face dataset by wangrui6
wangrui6/Zhihu-KOL -
tiny-codes
Datasets & benchmarksHugging Face dataset by nampdn-ai
nampdn-ai/tiny-codes -
CowAgent
Agents & frameworksOpen-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.
git clone https://github.com/zhayujie/CowAgent.git -
fineweb-2
Datasets & benchmarksHugging Face dataset by HuggingFaceFW
HuggingFaceFW/fineweb-2 -
task-orchestrator
MCP serversServer-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. Works with any MCP-compatible client.
git clone https://github.com/jpicklyk/task-orchestrator.git -
Docmatix
Datasets & benchmarksHugging Face dataset by HuggingFaceM4
HuggingFaceM4/Docmatix -
Zero-To-CAD-1m
Datasets & benchmarksHugging Face dataset by ADSKAILab
ADSKAILab/Zero-To-CAD-1m -
dsh-routing-suite
Agents & frameworksdsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).
git clone https://github.com/yjh051108/dsh-routing-suite.git -
overclick
Agents & frameworksThe open source task board where AI agents do the work. Self-hosted, MCP-native, zero data collection.
git clone https://github.com/ustoppble/overclick.git -
EgoStandard
Datasets & benchmarksHugging Face dataset by LightwheelAI
LightwheelAI/EgoStandard -
Nemotron-Personas-Korea
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/Nemotron-Personas-Korea -
CodeX-2M-Thinking
Datasets & benchmarksHugging Face dataset by Modotte
Modotte/CodeX-2M-Thinking -
medical-symptoms-english-audio
Datasets & benchmarksHugging Face dataset by HumynLabs
HumynLabs/medical-symptoms-english-audio -
e-commerce-customersupport-hinglish-audio
Datasets & benchmarksHugging Face dataset by HumynLabs
HumynLabs/e-commerce-customersupport-hinglish-audio -
Nemotron-Personas-USA
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/Nemotron-Personas-USA -
zenith
MCP serversZenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.
git clone https://github.com/Intelligent-Internet/zenith.git -
pixel-art-atlas-1.4m
Datasets & benchmarksHugging Face dataset by Angais
Angais/pixel-art-atlas-1.4m -
reasoning-v1-20m
Datasets & benchmarksHugging Face dataset by glaiveai
glaiveai/reasoning-v1-20m
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.