InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. belebele

    Datasets & benchmarks

    Hugging Face dataset by facebook

    Stale Hugging Face Hub, facebook 139 ♥cc-by-sa-4.0Updated 2 years ago

    facebook/belebele
  2. tweet_eval

    Datasets & benchmarks

    Hugging Face dataset by cardiffnlp

    Stale Hugging Face Hub, cardiffnlp 158 ♥unknownUpdated 2 years ago

    cardiffnlp/tweet_eval
  3. sharegpt_gpt4

    Datasets & benchmarks

    Hugging Face dataset by shibing624

    Stale Hugging Face Hub, shibing624 139 ♥cc-by-4.0Updated 2 years ago

    shibing624/sharegpt_gpt4
  4. super_glue

    Datasets & benchmarks

    Hugging Face dataset by aps

    Stale Hugging Face Hub, aps 214 ♥otherUpdated 18 months ago

    aps/super_glue
  5. llm-wiki-v2

    AI repositories

    Turn 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.

    Indexed GitHub, crow-hq 284 ★AGPL-3.0Updated 2 days ago

    git clone https://github.com/crow-hq/llm-wiki-v2.git
  6. Agentic skills for Claude Code and Codex, built from published social-science methods sources. Covers experimental design, computational text analysis, manuscript QA, and transparent reporting.

    Indexed GitHub, scdenney 70 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/scdenney/open-science-skills.git
  7. MathVista

    Datasets & benchmarks

    Hugging Face dataset by AI4Math

    Stale Hugging Face Hub, AI4Math 235 ♥cc-by-sa-4.0Updated 2 years ago

    AI4Math/MathVista
  8. skills

    Skills

    ProgramAsWeights 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

    Stale GitHub, programasweights 9 ★MITUpdated 9 days ago

    git clone https://github.com/programasweights/skills.git
  9. sloptotal

    Datasets & benchmarks

    Open-source AI text detector and ChatGPT detector: 23 engines, one calibrated score, every number measured on a public benchmark. Self-hosted, runs on CPU.

    Stale GitHub, pablocaeg 98 ★MITUpdated 13 days ago

    git clone https://github.com/pablocaeg/sloptotal.git
  10. ScienceQA

    Datasets & benchmarks

    Hugging Face dataset by derek-thomas

    Indexed Hugging Face Hub, derek-thomas 244 ♥cc-by-sa-4.0Updated 3 years ago

    derek-thomas/ScienceQA
  11. jev-cli

    MCP servers

    Command-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.

    Indexed GitHub, shaharia-lab 46 ★Apache-2.0Updated today

    git clone https://github.com/shaharia-lab/jev-cli.git
  12. pii-masking-200k

    Datasets & benchmarks

    Hugging Face dataset by ai4privacy

    Stale Hugging Face Hub, ai4privacy 129 ♥Updated 5 months ago

    ai4privacy/pii-masking-200k
  13. FilingFirehose

    MCP servers

    SEC EDGAR filings parsed: 8-K body-text classification, 13D activist tagging, S-3 ATM detection.

    Stale Official MCP Registry, com.filingfirehose Updated 6 months ago 1 note

  14. Tuatara Decide

    MCP servers

    Train a text classifier from your labelled examples in a minute; label texts with probabilities.

    Stale Official MCP Registry, com.cymetica Updated 14 days ago 1 note

  15. Don'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.

    Stale GitHub, wanshuiyin 180 ★MITUpdated 10 days ago

    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.