InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. LLM & RAG evals: hallucination, eval contracts, semantic tests, tokens & model info. Free, no key.

    Stale Official MCP Registry, io.github.JcJamet Updated 21 days ago 1 note

  2. LLM-RGB

    Datasets & benchmarks

    LLM Reasoning and Generation Benchmark. Evaluate LLMs in complex scenarios systematically.

    Stale GitHub, babelcloud 165 ★MITUpdated 18 months ago

    git clone https://github.com/babelcloud/LLM-RGB.git
  3. Premium agentic endpoint for clause-risk-score-evaluator-mcp.

    Stale Official MCP Registry, io.github.Evozim Updated 3 months ago 1 note

  4. chess-eval

    MCP servers

    Stockfish chess eval: best move, score, principal variation, multipv. $0.005/call via x402.

    Stale Official MCP Registry, com.x402supply Updated 4 months ago 1 note

  5. evals-mcp-server

    MCP servers

    Author verifiable eval records through a draft→review→revise→submit loop with enforced graders.

    Stale Official MCP Registry, io.github.cyanheads Updated 3 days ago 1 note

    @cyanheads/evals-mcp-server@0.2.0
  6. Zero-dependency AST safe mathematical and boolean expression evaluator and validator

    Stale Official MCP Registry, io.github.alphaparkinc Updated 26 days ago 1 note

    https://github.com/Alpha-Park/genpark-safe-eval-expression-ast-sandbox-skill/releases/download/v1.0.1/genpark-safe-eval-expression-ast-sandbox-skill-v1.0.1.mcpb
  7. In LangChain for LLM Application Development, you will gain essential skills in expanding the use cases and capabilities of language models in application development using the LangChain framework.

    Stale GitHub, Ryota-Kawamura 212 ★Updated 3 years ago

    git clone https://github.com/Ryota-Kawamura/LangChain-for-LLM-Application-Development.git
  8. autoguardrails

    Datasets & benchmarks

    Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

    Stale GitHub, SantanderAI 129 ★Apache-2.0Updated 46 days ago

    git clone https://github.com/SantanderAI/autoguardrails.git
  9. measured-type

    Skills

    Agent skill for web typography: Bringhurst applied to modern CSS, with claims measured in the browser and a baseline eval suite

    Stale GitHub, PetriLahdelma 18 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/PetriLahdelma/measured-type.git
  10. d3-lite

    Models

    zero shot classification model by vllm-sr · transformers

    Stale Hugging Face Hub, vllm-sr 29 ♥apache-2.0Updated 30 days ago

    vllm-sr/d3-lite
  11. hwatu

    MCP servers

    Verification browser for coding agents: headless WebKit, DOM eval, screenshots, pixel-diff.

    Stale Official MCP Registry, io.github.hongnoul 116 ★MITUpdated 30 days ago 1 note

    https://github.com/hongnoul/hwatu/releases/download/v0.6.0/hwatu-mcp-linux-x86_64.tar.gz@0.6.0
  12. elimination_game

    Datasets & benchmarks

    A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private conversations, form alliances, and vote to eliminate each other

    Stale GitHub, lechmazur 298 ★Updated 10 months ago

    git clone https://github.com/lechmazur/elimination_game.git
  13. Long-Horizon-Terminal-Bench

    Datasets & benchmarks

    Hugging Face dataset by IntelligenceLab

    Stale Hugging Face Hub, IntelligenceLab 140 ♥apache-2.0Updated 36 days ago

    IntelligenceLab/Long-Horizon-Terminal-Bench
  14. MIRAI

    Agents & frameworks

    Code and Data for "MIRAI: Evaluating LLM Agents for Event Forecasting"

    Stale GitHub, yecchen 114 ★Updated 2 years ago

    git clone https://github.com/yecchen/MIRAI.git
  15. evalgate

    MCP servers

    Statistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).

    Stale Official MCP Registry, io.github.ipezygj Updated 3 months ago 1 note

    eval-integrity@0.4.1
  16. evalpair

    MCP servers

    Run LLM eval suites on local or hosted models; compare runs with intervals and a noise floor.

    Stale Official MCP Registry, io.github.Srikarmk Updated 11 days ago 2 notes

    evalpair@0.1.1
  17. Sage

    Agents & frameworks

    An RSI Agent Harness for running, evaluating, and evolving agents—with tools, skills, MCP, stateful execution, and multi-agent workflows.

    Indexed GitHub, ZHangZHengEric 1,215 ★MITUpdated yesterday

    git clone https://github.com/ZHangZHengEric/Sage.git
  18. SGI-Bench

    Datasets & benchmarks

    Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

    Stale GitHub, InternScience 172 ★MITUpdated 5 months ago

    git clone https://github.com/InternScience/SGI-Bench.git
  19. Evaluation-only ledger MCP. Temporary storage; not durable audit evidence. Payments disabled.

    Indexed Official MCP Registry, io.github.canoydario847-cloud Updated yesterday 1 note

  20. Agent evaluation scorecard, delivered per API call as an atom service on Conduit Atoms.

    Indexed Official MCP Registry, org.aimlds Updated yesterday 1 note

  21. Claim evaluation review, delivered per API call as an atom service on Conduit Atoms.

    Indexed Official MCP Registry, org.aimlds Updated today 1 note

  22. Vendor evaluation three-way match: declared procurement record checked per call.

    Indexed Official MCP Registry, org.aimlds Updated today 1 note

  23. cs329z-chinese

    Docs & tutorials

    斯坦福 Stanford CS329Z Engineering AI Agents 中文教程:面向 Python 开发者的 AI 智能体课程,19 讲与 4 项实践,涵盖 LLM、RAG、工具调用、记忆、多智能体、评测与安全。完整 Markdown、在线与离线 HTML。Chinese course notes.

    Stale GitHub, wanghao-SunSky 512 ★Updated 10 days ago

    git clone https://github.com/wanghao-SunSky/cs329z-chinese.git
  24. Awesome-CUA

    Agents & frameworks

    Open, source-backed catalog of computer-use agents: reviewed papers, GUI models, datasets, benchmarks, tools, and reusable JSONL/SQLite data.

    Stale GitHub, reacher-z 659 ★Custom licence (see repository)Updated 6 days ago

    git clone https://github.com/reacher-z/Awesome-CUA.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.