Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
d3-lite
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-lite -
fintech-skills
Skills13 fintech engineering skills for coding agents, with test vectors and published with/without eval results
git clone https://github.com/felipealvarenga/fintech-skills.git -
dynobox
SkillsCross-harness testing framework for agent skills and workflows
git clone https://github.com/dynobox/dynobox.git -
Phocinae-Largha-150M-v1
Modelstext classification model by Phocinae
Phocinae/Phocinae-Largha-150M-v1 -
paperthin
SkillsThe skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.
git clone https://github.com/LilMGenius/paperthin.git -
opentai.github.io
SkillsThe official website of the Open Trustworthy AI Community (OpenTAI).
git clone https://github.com/OpenTAI/opentai.github.io.git -
agent-eval
MCP serversStatistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
agent-regress-cli@0.1.8 -
GenPark Safe Eval Expression AST Sandbox
MCP serversZero-dependency AST safe mathematical and boolean expression evaluator and validator
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 -
hwatu
MCP serversVerification browser for coding agents: headless WebKit, DOM eval, screenshots, pixel-diff.
https://github.com/hongnoul/hwatu/releases/download/v0.6.0/hwatu-mcp-linux-x86_64.tar.gz@0.6.0 -
Chipp Analytics and evals
MCP serversChipp: conversations, messages, usage and engagement analytics, end users and their memories, and.
-
agent-control-standard
Agents & frameworksThe open standard for runtime agent control — declarative hooks, policy enforcement, and observability across AI agent frameworks.
git clone https://github.com/GenAI-Security-Project/agent-control-standard.git -
Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models
git clone https://github.com/jxzhangjhu/Awesome-LLM-Uncertainty-Reliability-Robustness.git -
elimination_game
Datasets & benchmarksA 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
git clone https://github.com/lechmazur/elimination_game.git -
Long-Horizon-Terminal-Bench
Datasets & benchmarksHugging Face dataset by IntelligenceLab
IntelligenceLab/Long-Horizon-Terminal-Bench -
sacp
Datasets & benchmarksState-Aware Collaboration Protocol: auditable work receipts for AI agents.
git clone https://github.com/aDragon0707/sacp.git -
jailbreak-archives
PromptsA structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-teaming, and defensive hardening.
git clone https://github.com/e2sy/jailbreak-archives.git -
LLM Eval Harness
MCP serversRun a golden set and gate LLM model swaps on accuracy, with latency and cost per request.
ghcr.io/razilzul/llm-eval-harness:1.0.0 -
langwatch
PromptsOpen-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.
git clone https://github.com/langwatch/langwatch.git -
Japanese Order Eval
MCP serversRegression checks for Japanese order automations: six free cases, strict JSON scoring and CI gates.
-
Eval Engine API
MCP serversPay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
-
Web Search API Eval
MCP serversWeb search API benchmark for AI agents: You.com, Tavily, Exa, Parallel. Results and charts.
websearch-api-eval-mcp@1.1.0 -
National safety week
PromptsOn the occasion of national safety week 2026 write a safety script which engage the employee and peoples create awareness on safety by following safety guidelines in steel industry
-
QAE Safety Certification
MCP serversDeterministic pre-execution safety certification for autonomous AI agents.
qae-safety@0.1.2 -
Rights-aware censorship, China-economic status, and tamper-evident AI evaluation tools.
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.