Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
belebele
Datasets & benchmarksHugging Face dataset by facebook
facebook/belebele -
tweet_eval
Datasets & benchmarksHugging Face dataset by cardiffnlp
cardiffnlp/tweet_eval -
sharegpt_gpt4
Datasets & benchmarksHugging Face dataset by shibing624
shibing624/sharegpt_gpt4 -
super_glue
Datasets & benchmarksHugging Face dataset by aps
aps/super_glue -
llm-wiki-v2
AI repositoriesTurn your documents into a Markdown wiki you can read, that answers with citations. Works with any LLM provider, Ollama included. CROW: 99.5% right note read vs 79%, 1.6× faster ingest, 63% fewer LLM tokens, no scaling limit.
git clone https://github.com/crow-hq/llm-wiki-v2.git -
open-science-skills
SkillsAgentic skills for Claude Code and Codex, built from published social-science methods sources. Covers experimental design, computational text analysis, manuscript QA, and transparent reporting.
git clone https://github.com/scdenney/open-science-skills.git -
MathVista
Datasets & benchmarksHugging Face dataset by AI4Math
AI4Math/MathVista -
skills
SkillsProgramAsWeights agent skill - compile natural-language specs into tiny, locally-running neural functions for fuzzy text tasks (classify, extract, repair, fuzzy-match, triage, route). npx skills add programasweights/skills
git clone https://github.com/programasweights/skills.git -
sloptotal
Datasets & benchmarksOpen-source AI text detector and ChatGPT detector: 23 engines, one calibrated score, every number measured on a public benchmark. Self-hosted, runs on CPU.
git clone https://github.com/pablocaeg/sloptotal.git -
ScienceQA
Datasets & benchmarksHugging Face dataset by derek-thomas
derek-thomas/ScienceQA -
jev-cli
MCP serversCommand-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.
git clone https://github.com/shaharia-lab/jev-cli.git -
pii-masking-200k
Datasets & benchmarksHugging Face dataset by ai4privacy
ai4privacy/pii-masking-200k -
FilingFirehose
MCP serversSEC EDGAR filings parsed: 8-K body-text classification, 13D activist tagging, S-3 ATM detection.
-
Tuatara Decide
MCP serversTrain a text classifier from your labelled examples in a minute; label texts with probabilities.
-
Anti-Autoresearch
SkillsDon't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.
git clone https://github.com/wanshuiyin/Anti-Autoresearch.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.