Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
MINT-1T-HTML
Datasets & benchmarksHugging Face dataset by mlfoundations
mlfoundations/MINT-1T-HTML -
WaxalNLP
Datasets & benchmarksHugging Face dataset by google
google/WaxalNLP -
dialogsum
Datasets & benchmarksHugging Face dataset by knkarthick
knkarthick/dialogsum -
sst2
Datasets & benchmarksHugging Face dataset by stanfordnlp
stanfordnlp/sst2 -
claude-code-sub-agent-collective
Agents & frameworks🧠 Context Engineering Research - Not just another agent collection, but using research and context engineering to function as a collective. Hub-and-spoke coordination through Claude Code.
git clone https://github.com/vanzan01/claude-code-sub-agent-collective.git -
proof-pile-2
Datasets & benchmarksHugging Face dataset by EleutherAI
EleutherAI/proof-pile-2 -
the-stack
Datasets & benchmarksHugging Face dataset by bigcode
bigcode/the-stack -
atlas-mcp-server
MCP serversA Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workflows. Now with Deep Research.
git clone https://github.com/cyanheads/atlas-mcp-server.git -
UltraFeedback
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/UltraFeedback -
dolphin
Datasets & benchmarksHugging Face dataset by QuixiAI
QuixiAI/dolphin -
xsum
Datasets & benchmarksHugging Face dataset by EdinburghNLP
EdinburghNLP/xsum -
NuminaMath-CoT
Datasets & benchmarksHugging Face dataset by project-numina
project-numina/NuminaMath-CoT -
glaive-function-calling-v2
Datasets & benchmarksHugging Face dataset by glaiveai
glaiveai/glaive-function-calling-v2 -
NuminaMath-CoT
Datasets & benchmarksHugging Face dataset by AI-MO
AI-MO/NuminaMath-CoT -
Ultra-FineWeb
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/Ultra-FineWeb -
finephrase
Datasets & benchmarksHugging Face dataset by HuggingFaceFW
HuggingFaceFW/finephrase -
jupyter-agent-dataset
Datasets & benchmarksHugging Face dataset by jupyter-agent
jupyter-agent/jupyter-agent-dataset -
commonsense_qa
Datasets & benchmarksHugging Face dataset by tau
tau/commonsense_qa -
omnilingual-asr-corpus
Datasets & benchmarksHugging Face dataset by facebook
facebook/omnilingual-asr-corpus -
sciq
Datasets & benchmarksHugging Face dataset by allenai
allenai/sciq -
distilabel-capybara-dpo-7k-binarized
Datasets & benchmarksHugging Face dataset by argilla
argilla/distilabel-capybara-dpo-7k-binarized -
unlazy
PromptsAnti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
git clone https://github.com/Leonxlnx/unlazy.git -
unilm
AI repositoriesLarge-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
git clone https://github.com/microsoft/unilm.git -
yelp_review_full
Datasets & benchmarksHugging Face dataset by Yelp
Yelp/yelp_review_full
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.