InnerVault

Library

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

Results

  1. bg3-agent-harness

    MCP servers

    An AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark and a playthrough app.

    Stale GitHub, Bogzx 33 ★MITUpdated 7 days ago

    git clone https://github.com/Bogzx/bg3-agent-harness.git
  2. AssetOpsBench

    MCP servers

    AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scenarios, 5 specialist agents (IoT, FMSR, TSFM, Work Order,...), and multi-agent orchestration blueprints (MetaAgent, AgentHive) over MCP.

    Indexed GitHub, IBM 2,424 ★Apache-2.0Updated today

    git clone https://github.com/IBM/AssetOpsBench.git
  3. promptdesk

    Prompts

    Promptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and large language models (LLMs).

    Stale GitHub, promptdesk 99 ★AGPL-3.0Updated 14 months ago

    git clone https://github.com/promptdesk/promptdesk.git
  4. MathJS

    Public APIs

    Evaluate math expressions via GET or POST as JSON

    Indexed public-apis (GitHub list)

  5. Open-source skills for Claude Code and Codex, with an MCP server, a PyPI package and Suede Awesome Everything, a directory that scores AI agent skills 0 to 99. Created by Jason Colapietro, founder and CEO of Suede AI.

    Indexed GitHub, JasonColapietro 124 ★MITUpdated yesterday

    git clone https://github.com/JasonColapietro/suede-creator-skills.git
  6. jev-judge-mcp

    MCP servers

    Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.

    Stale GitHub, PyModel 48 ★MITUpdated 32 days ago

    git clone https://github.com/PyModel/jev-judge-mcp.git
  7. VibeSearchBench

    Datasets & benchmarks

    🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.

    Stale GitHub, VibeBench 112 ★MITUpdated 5 months ago

    git clone https://github.com/VibeBench/VibeSearchBench.git
  8. ReForm-Eval

    Datasets & benchmarks

    An benchmark for evaluating the capabilities of large vision-language models (LVLMs)

    Stale GitHub, FudanDISC 145 ★Apache-2.0Updated 3 years ago

    git clone https://github.com/FudanDISC/ReForm-Eval.git
  9. Based on Anthropic's skill-creator — with bug fixes, working Cowork support, and official best practices baked in. Claude skill for creating, testing, and improving other Claude skills.

    Stale GitHub, yaniv-golan 7 ★MITUpdated 4 days ago

    git clone https://github.com/yaniv-golan/skill-creator-plus.git
  10. posthog

    MCP servers

    Capture analytics events, evaluate feature flags, and manage projects

    Stale Official MCP Registry, com.mcparmory Updated 6 months ago 1 note

    mcparmory-posthog@1.0.5
  11. Okareo

    MCP servers

    Simulation, evaluation and monitoring for voice agents.

    Stale Official MCP Registry, com.okareo Updated 4 days ago 1 note

  12. JamAIBase

    AI repositories

    The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

    Stale GitHub, EmbeddedLLM 1,103 ★Apache-2.0Updated 25 days ago

    git clone https://github.com/EmbeddedLLM/JamAIBase.git
  13. PAKGOV-RAG-project

    AI repositories

    Research project on bilingual Urdu-English retrieval-augmented generation for Pakistani government and legal documents, with OCR, hybrid retrieval, citation grounding, and evaluation.

    Stale GitHub, salikhussain71-code 130 ★MITUpdated 14 days ago

    git clone https://github.com/salikhussain71-code/PAKGOV-RAG-project.git
  14. aiml-companion

    Agents & frameworks

    AI-ML Companion: an interactive platform to learn AI & ML by watching it work - 28 tracks, 400+ modules, live visualizations - plus 20+ end-to-end real world projects from classical ML, DL, Computer Vision to production LLM & multi-agent systems.

    Indexed GitHub, genieincodebottle 74 ★Updated 2 days ago

    git clone https://github.com/genieincodebottle/aiml-companion.git
  15. hermeneutic

    Skills

    Turn corrections from AI agent logs into guidance for similar tasks. Local memory with semantic retrieval, prompt-context hooks, and response checks.

    Stale GitHub, hermes-labs-ai 9 ★Apache-2.0Updated 27 days ago

    git clone https://github.com/hermes-labs-ai/hermeneutic.git
  16. calcport

    MCP servers

    Safe arithmetic: evaluate expressions and add, subtract, multiply, divide.

    Stale Official MCP Registry, io.github.CloudCorpRecords Updated 20 days ago 1 note

    @reneturcios/calcport@0.1.0
  17. agent-starter-pack

    AI repositories

    Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.

    IndexedArchived GitHub, GoogleCloudPlatform 6,574 ★Apache-2.0Updated yesterday 1 note

    git clone https://github.com/GoogleCloudPlatform/agent-starter-pack.git
  18. web-eval-agent

    MCP servers

    An MCP server that autonomously evaluates web applications.

    Stale Archived GitHub, refreshdotdev 1,235 ★Apache-2.0Updated 9 months ago 1 note

    git clone https://github.com/refreshdotdev/web-eval-agent.git
  19. mcp

    MCP servers

    MCP server providing OpenFeature SDK installation guides and OFREP flag evaluation

    Stale Official MCP Registry, dev.openfeature Updated 6 months ago 1 note

    @openfeature/mcp@0.0.22
  20. Data Observability

    MCP servers

    SQL data health analyzer and pipeline observability evaluator.

    Stale Official MCP Registry, io.github.Evozim Updated 5 months ago 1 note

  21. calculator-mcp-server

    MCP servers

    Evaluate, simplify, and differentiate mathematical expressions.

    Stale Official MCP Registry, io.github.cyanheads Updated 4 days ago 2 notes

    @cyanheads/calculator-mcp-server@0.6.0
  22. Evaluate mathematical expressions and propagate measurement uncertainty.

    Stale Official MCP Registry, io.github.quentintruong Updated 39 days ago 1 note

  23. RecourseOS

    MCP servers

    Consequence evaluation for AI agents. Check recoverability before destructive actions.

    Stale Official MCP Registry, io.github.recourseOS Updated 6 months ago 1 note

    recourse-cli@0.1.12
  24. ADHDEvaluations

    MCP servers

    9,846 ADHD evaluation providers from the CMS NPI Registry.

    Stale Official MCP Registry, fyi.adhdevaluations Updated 37 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.