Library
87,734 resources from 11 public sources. 46 checked by hand. The rest are indexed automatically and not reviewed.
Results
-
Arena rates 399 text models from 52 labs, up from 10 models in May 2023. Yet only 5 labs hold.
-
cfgaudit
MCP serversStatic security auditor for AI-agent configuration: Claude Code, MCP servers, Cursor, Codex, Copilot, Gemini CLI and more. SARIF output, OWASP LLM Top 10 mapping.
Source for cfgaudit (opens github.com) git clone https://github.com/cfgaudit/cfgaudit.git -
deepmark
Datasets & benchmarksDeepmark AI enables a unique testing environment for language models (LLM) assessment on task-specific metrics and on your own data so your GenAI-powered solution has predictable and reliable performance.
Source for deepmark (opens github.com) git clone https://github.com/IngestAI/deepmark.git -
deltallm
MCP serversSelf-hosted LLM gateway with SSO, audit logs, client access controls, routing, and usage tracking. OpenAI-compatible and MIT licensed.
Source for deltallm (opens github.com) git clone https://github.com/deltawi/deltallm.git -
game-asset-aesthetic-test
Skills8 个游戏美术 Agent Skills:像素精灵、Spine 骨骼动画、方块角色(Blockbench)与讲解配音。附可复用代码、资源来源、验证记录和效果示例。
Source for game-asset-aesthetic-test (opens github.com) git clone https://github.com/zeroa234/game-asset-aesthetic-test.git -
DishwasherBench
Datasets & benchmarksA dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The game inside is called Spotless.
Source for DishwasherBench (opens github.com) git clone https://github.com/composo-ai/DishwasherBench.git -
Learning Model Context Protocol
MCP serversBasic arithmetic tools with natural-language expression parsing and evaluation.
Source for Learning Model Context Protocol (opens github.com) mcp-learning@0.3.0 -
humanjs
MCP serversHumanize browser automation for AI agents, QA tests, and demos. Playwright-first — record sessions to video or runnable tests, and drive it over MCP from your favorite AI.
Source for humanjs (opens github.com) git clone https://github.com/totigm/humanjs.git -
seekstone
MCP serversThe Obsidian MCP server that needs no plugin, no running Obsidian app — and doesn't blow your context window. Filesystem-direct: single-digit-ms keyword search, ~26 ms local semantic search, ~2 KB payloads, 25 tools.
Source for seekstone (opens github.com) git clone https://github.com/shaqmughal/seekstone.git -
model-card-lint-gpai
MCP serversLints a Hugging Face model card against the Hub metadata spec and the EU AI Act general-purpose AI d
Source for model-card-lint-gpai (opens github.com) @readystack/model-card-lint-gpai@1.0.3 -
Find open biology and chemistry AI models, bioinformatics tools and databases, and run them online.
-
Find GitHub tools and Hugging Face models: source links, licenses, setup notes and review dates.
-
The best open model trails the best closed model by 42 Arena points. In a blind vote it would.
-
run402
MCP serversFull-stack backend infrastructure for AI agents: Postgres, auth, storage, serverless functions and atomic deploys. TypeScript SDK, CLI and MCP server. Paid with x402/MPP. Open source.
Source for run402 (opens github.com) git clone https://github.com/kychee-com/run402.git -
ai model card
PromptsAsk me for AI model name(s) in next message * You are an AI model research expert. You must research and provide actual and accurate data, never make up any data. * research and list the specification of the AI model…
-
pain001
MCP serversGenerate and validate ISO 20022 payment files (pain.001 v03-v12, pain.008) from CSV, SQLite, JSON, or Parquet. XSD and SEPA scheme validation, pain.002 and camt.053 parsers and builders, plus a CLI, REST API, MCP server, and LSP server for editor diagnostics. 🐍
Source for pain001 (opens github.com) git clone https://github.com/sebastienrousseau/pain001.git -
model.tools — Zero-Auth Agent Utilities
MCP serversZero-auth email OTP extractor, KV checkpoints, webhook bins, wake timers, and markdown reader.
-
modelranch
MCP serversA free deals network for AI agents: post what your person has and needs, find agents who can help.
-
CoalTipple
SkillsSafe, quality-gated model+effort router for Claude Code - delegates cheap work down to save tokens, escalates hard/sensitive work up through a verify staircase, never-down gate, and fail-safe Lock, up to a consent-gated fable top rung. Not the cheapest router; the safest one inside Claude.
Source for CoalTipple (opens github.com) git clone https://github.com/TheColliery/CoalTipple.git -
Automatically filters and aggregates AI news, extracts article data, and produces actionable commercial intelligence.
Source for openclaw-genpark-signal-aggregator (opens github.com) git clone https://github.com/alphaparkinc/openclaw-genpark-signal-aggregator.git -
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.
Source for multi-agents (opens github.com) git clone https://github.com/BichengWang/multi-agents.git -
agentic-resource-discovery
MCP serversNeuronto Agentic Resource Discovery (ARD) Index. Federated search across every public ARD registry, plus a verified tool index read from each MCP server's own tools/list, hybrid lexical and semantic retrieval, and ARD-Bench.
Source for agentic-resource-discovery (opens github.com) git clone https://github.com/neuronto/agentic-resource-discovery.git -
bagidea-office
Agents & frameworksA living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, delegate, learn & hold meetings. Per-agent swappable models (Claude/GLM/DeepSeek/Qwen/Kimi/OpenAI/Gemini/Groq/Ollama…), workflows, plugins, voice & Telegram/Discord/LINE. Open source.
Source for bagidea-office (opens github.com) git clone https://github.com/bagidea/bagidea-office.git -
Act as a Vacuum Arc Modeling Expert. You are a professor-level specialist in vacuum arc theory and Fluent-based modeling, with expertise in writing UDFs and UDSs. Your task is to model vacuum arcs under transverse…
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.