Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
OSWorld-V2
Datasets & benchmarksOSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
git clone https://github.com/xlang-ai/OSWorld-V2.git -
Step-3.5-Flash-SFT
Datasets & benchmarksHugging Face dataset by stepfun-ai
stepfun-ai/Step-3.5-Flash-SFT -
hermes-function-calling-v1
Datasets & benchmarksHugging Face dataset by NousResearch
NousResearch/hermes-function-calling-v1 -
ai-village
Datasets & benchmarksHugging Face dataset by aidigestorg
aidigestorg/ai-village -
Fable-5.1-Max-Reasoning-Filtered-10000x
Datasets & benchmarksHugging Face dataset by MoreThought
MoreThought/Fable-5.1-Max-Reasoning-Filtered-10000x -
AICGSecEval
Datasets & benchmarksA.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.
git clone https://github.com/Tencent/AICGSecEval.git -
WebsiteBench
Datasets & benchmarksCan AI agents rebuild websites through browser exploration?
git clone https://github.com/TIGER-AI-Lab/WebsiteBench.git -
polymarket-paper-trader
Datasets & benchmarksPaper trading simulator for Polymarket
git clone https://github.com/agent-next/polymarket-paper-trader.git -
Toucan-1.5M
Datasets & benchmarksHugging Face dataset by Agent-Ark
Agent-Ark/Toucan-1.5M -
BALROG
Datasets & benchmarksBenchmarking Agentic LLM and VLM Reasoning On Games
git clone https://github.com/balrog-ai/BALROG.git -
Simreal-MLBench
Datasets & benchmarks[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.
git clone https://github.com/Simreal-AI/Simreal-MLBench.git -
MiroVerse-v0.1
Datasets & benchmarksHugging Face dataset by miromind-ai
miromind-ai/MiroVerse-v0.1 -
Long-Horizon-Terminal-Bench
Datasets & benchmarksHugging Face dataset by IntelligenceLab
IntelligenceLab/Long-Horizon-Terminal-Bench -
Awesome-AI4AI
Datasets & benchmarksUpdated weekly — until humanity achieves AI4AI. 1148 curated papers across Benchmarks, Harness Design, and Model Design — from long-horizon agents to recursive self-improvement. Citation rankings, GitHub stars, and source-verified weekly news.
git clone https://github.com/KaiWU5/Awesome-AI4AI.git -
TrustLLM
Datasets & benchmarks[ICML 2024] TrustLLM: LLM trustworthiness evaluation across truthfulness, safety, fairness, robustness, privacy and ethics. Python/CLI toolkit for local models, compatible APIs and AI agent orchestration.
git clone https://github.com/HowieHwong/TrustLLM.git -
10Kh-RealOmin-OpenData
Datasets & benchmarksHugging Face dataset by genrobot2025
genrobot2025/10Kh-RealOmin-OpenData -
ResearchClawBench
Datasets & benchmarks🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
git clone https://github.com/InternScience/ResearchClawBench.git -
XYZ-Aquila-SFT
Datasets & benchmarksHugging Face dataset by XYZAILab
XYZAILab/XYZ-Aquila-SFT -
multi-agents
Datasets & benchmarksMulti-agent teams for real work: run teams of coding agents (Claude Code, Codex, any model) in isolated git worktrees, and measure whether the team beats a solo agent on cost and results.
git clone https://github.com/BichengWang/multi-agents.git -
civ6-mcp
Datasets & benchmarksAn MCP server that lets LLM agents play Civilization VI.
git clone https://github.com/lmwilki/civ6-mcp.git -
LLM-Agent-Benchmark-List
Datasets & benchmarksA banchmark list for evaluation of large language models.
git clone https://github.com/zhangxjohn/LLM-Agent-Benchmark-List.git -
MobileWorld
Datasets & benchmarksBenchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments (ACL 2026)
git clone https://github.com/Tongyi-MAI/MobileWorld.git -
VIBE
Datasets & benchmarksHugging Face dataset by MiniMaxAI
MiniMaxAI/VIBE -
DeepScaleR-Preview-Dataset
Datasets & benchmarksHugging Face dataset by agentica-org
agentica-org/DeepScaleR-Preview-Dataset
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.