Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
eval-genius
SkillsTeach 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.
git clone https://github.com/alexgreensh/eval-genius.git -
deepsearchqa
Datasets & benchmarksHugging Face dataset by google
google/deepsearchqa -
Hill-Climb
SkillsMake your coding agent prove "done". Each change is kept only if a locked test or benchmark scores it better. Claude Code and Codex skill.
git clone https://github.com/Bil0000/Hill-Climb.git -
SkillEvaluator
SkillsMulti-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.
git clone https://github.com/NVIDIA/SkillEvaluator.git -
autoharness
SkillsAutoharness — 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.
git clone https://github.com/tigerless-labs/autoharness.git -
sacp
Datasets & benchmarksState-Aware Collaboration Protocol: auditable work receipts for AI agents.
git clone https://github.com/aDragon0707/sacp.git -
BenchLM Data
MCP serversCurrent AI model rankings, API prices, benchmark results and history from BenchLM.
-
Agents_Failure_Attribution
Agents & frameworksBenchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)
git clone https://github.com/ag2ai/Agents_Failure_Attribution.git -
ds4-on-spark
Datasets & benchmarksEntrpi/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
git clone https://github.com/Entrpi/ds4-on-spark.git -
Awesome-AI-Scientist
Datasets & benchmarks🧪 Awesome list of AI Scientist papers, systems, benchmarks, datasets and open-source platforms.
git clone https://github.com/Omni-Scientist/Awesome-AI-Scientist.git -
llm-value-rankings
Datasets & benchmarksDaily LLM value rankings - compare 300+ models by intelligence, speed and price. OpenRouter + Artificial Analysis. 大模型性价比排行榜
git clone https://github.com/yyh-001/llm-value-rankings.git -
fleurs
Datasets & benchmarksHugging Face dataset by google
google/fleurs -
ResearchClawBench
Datasets & benchmarks🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
git clone https://github.com/InternScience/ResearchClawBench.git -
code-review-graph
AI repositoriesLocal-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.
git clone https://github.com/tirth8205/code-review-graph.git -
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
git clone https://github.com/Purewhiter/mobilegym.git -
Multi-User-LLM-Agent
Datasets & benchmarksOfficial code for the paper: "Multi-User Large Language Model Agents"
git clone https://github.com/Kordi-AI/Multi-User-LLM-Agent.git -
Free to compete: testnet faucet funds everything. Classify a product blurb: category + sentiment
-
aya_dataset
Datasets & benchmarksHugging Face dataset by CohereLabs
CohereLabs/aya_dataset -
BenchLeader
MCP serversDaily LLM leaderboard from independent benchmarks: ranks, scores, prices, speed and comparisons.
-
opencode-skill-creator
SkillsCreate, test, and optimize OpenCode skills. Supports OpenCode V2 and V1 ≥ 1.18.29. Adapted from Anthropic's skill-creator.
git clone https://github.com/antongulin/opencode-skill-creator.git -
Introduction-to-Quantitative-Finance
AI repositoriesAI+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.
git clone https://github.com/Barca0412/Introduction-to-Quantitative-Finance.git -
Bulgaria Beneficial Owners
MCP serversbulgaria-beneficial-owners -- a Bulgarian legal entity's beneficial owners (действителни…
@pipeworx/mcp-bulgaria-beneficial-owners@0.2.1 -
bend-mcp
MCP serversBend MCP: 20 real tools to read, check, lint, scaffold, build and run Bend code.
@mrfentmen/bend-mcp@1.0.0 -
BenAwf
MCP serversBenAwf remote MCP for Strategy Lab. Streamable HTTP. Paper GA; live venue beta.
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.