InnerVault

Library

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

Results

  1. eval-genius

    Skills

    Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it tells you. Deterministic-first, tool-agnostic.

    Stale GitHub, alexgreensh 24 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/alexgreensh/eval-genius.git
  2. deepsearchqa

    Datasets & benchmarks

    Hugging Face dataset by google

    Stale Hugging Face Hub, google 133 ♥apache-2.0Updated 11 months ago

    google/deepsearchqa
  3. Hill-Climb

    Skills

    Make your coding agent prove "done". Each change is kept only if a locked test or benchmark scores it better. Claude Code and Codex skill.

    Indexed GitHub, Bil0000 111 ★MITUpdated 4 days ago

    git clone https://github.com/Bil0000/Hill-Climb.git
  4. Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

    Indexed GitHub, NVIDIA 1,963 ★Apache-2.0Updated today

    git clone https://github.com/NVIDIA/SkillEvaluator.git
  5. autoharness

    Skills

    Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.

    Stale GitHub, tigerless-labs 11.1k ★MITUpdated 33 days ago

    git clone https://github.com/tigerless-labs/autoharness.git
  6. sacp

    Datasets & benchmarks

    State-Aware Collaboration Protocol: auditable work receipts for AI agents.

    Stale GitHub, aDragon0707 107 ★MITUpdated 32 days ago

    git clone https://github.com/aDragon0707/sacp.git
  7. BenchLM Data

    MCP servers

    Current AI model rankings, API prices, benchmark results and history from BenchLM.

    Stale Official MCP Registry, ai.benchlm Updated 5 days ago 1 note

  8. Agents_Failure_Attribution

    Agents & frameworks

    Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)

    Stale GitHub, ag2ai 397 ★MITUpdated 17 days ago

    git clone https://github.com/ag2ai/Agents_Failure_Attribution.git
  9. ds4-on-spark

    Datasets & benchmarks

    Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support

    Stale GitHub, Entrpi 409 ★MITUpdated 2 months ago

    git clone https://github.com/Entrpi/ds4-on-spark.git
  10. Awesome-AI-Scientist

    Datasets & benchmarks

    🧪 Awesome list of AI Scientist papers, systems, benchmarks, datasets and open-source platforms.

    Indexed GitHub, Omni-Scientist 105 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/Omni-Scientist/Awesome-AI-Scientist.git
  11. llm-value-rankings

    Datasets & benchmarks

    Daily LLM value rankings - compare 300+ models by intelligence, speed and price. OpenRouter + Artificial Analysis. 大模型性价比排行榜

    Indexed GitHub, yyh-001 30 ★MITUpdated yesterday

    git clone https://github.com/yyh-001/llm-value-rankings.git
  12. fleurs

    Datasets & benchmarks

    Hugging Face dataset by google

    Indexed Hugging Face Hub, google 513 ♥cc-by-4.0Updated 6 months ago

    google/fleurs
  13. ResearchClawBench

    Datasets & benchmarks

    🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

    Stale GitHub, InternScience 275 ★MITUpdated 19 days ago

    git clone https://github.com/InternScience/ResearchClawBench.git
  14. code-review-graph

    AI repositories

    Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

    Stale GitHub, tirth8205 32.2k ★MITUpdated 41 days ago

    git clone https://github.com/tirth8205/code-review-graph.git
  15. mobilegym

    Datasets & benchmarks

    [EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training

    Indexed GitHub, Purewhiter 866 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/Purewhiter/mobilegym.git
  16. Multi-User-LLM-Agent

    Datasets & benchmarks

    Official code for the paper: "Multi-User Large Language Model Agents"

    Stale GitHub, Kordi-AI 39 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/Kordi-AI/Multi-User-LLM-Agent.git
  17. Free to compete: testnet faucet funds everything. Classify a product blurb: category + sentiment

    Stale Official MCP Registry, com.a2awire Updated 8 days ago 1 note

  18. aya_dataset

    Datasets & benchmarks

    Hugging Face dataset by CohereLabs

    Indexed Hugging Face Hub, CohereLabs 382 ♥apache-2.0Updated 19 months ago

    CohereLabs/aya_dataset
  19. BenchLeader

    MCP servers

    Daily LLM leaderboard from independent benchmarks: ranks, scores, prices, speed and comparisons.

    Stale Official MCP Registry, com.benchleader Updated 16 days ago 1 note

  20. Create, test, and optimize OpenCode skills. Supports OpenCode V2 and V1 ≥ 1.18.29. Adapted from Anthropic's skill-creator.

    Stale GitHub, antongulin 174 ★Apache-2.0Updated 29 days ago

    git clone https://github.com/antongulin/opencode-skill-creator.git
  21. AI+金融(量化):1.多因子股票量化框架开源教程 2.学界和业界的经典资料收录 3.AI + 金融的相关工作,包括LLM, Agent, benchmark(evaluation), etc.

    Indexed GitHub, Barca0412 1,883 ★MITUpdated yesterday

    git clone https://github.com/Barca0412/Introduction-to-Quantitative-Finance.git
  22. bulgaria-beneficial-owners -- a Bulgarian legal entity's beneficial owners (действителни…

    Stale Official MCP Registry, io.github.pipeworx-io Updated 16 days ago 3 notes

    @pipeworx/mcp-bulgaria-beneficial-owners@0.2.1
  23. bend-mcp

    MCP servers

    Bend MCP: 20 real tools to read, check, lint, scaffold, build and run Bend code.

    Stale Official MCP Registry, io.github.mrfentmen Updated 8 days ago 1 note

    @mrfentmen/bend-mcp@1.0.0
  24. BenAwf

    MCP servers

    BenAwf remote MCP for Strategy Lab. Streamable HTTP. Paper GA; live venue beta.

    Stale Official MCP Registry, com.benawf Updated 56 days ago 1 note

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.