InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. ai4s-skills

    Skills

    Open-source agent skills for AI for Science: topic exploration, literature survey, experiments, paper writing, and integrity audit — driven by any coding agent.

    Stale GitHub, ai4s-research 237 ★MITUpdated 3 months ago

    git clone https://github.com/ai4s-research/ai4s-skills.git
  2. AgentLab

    Datasets & benchmarks

    AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

    Stale GitHub, ServiceNow 653 ★Custom licence (see repository)Updated 41 days ago

    git clone https://github.com/ServiceNow/AgentLab.git
  3. OpenEMMA

    AI repositories

    OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.

    Stale GitHub, taco-group 959 ★Apache-2.0Updated 18 months ago

    git clone https://github.com/taco-group/OpenEMMA.git
  4. axiomize

    Skills

    Reproducible scientific modeling engine and agent skill pack: versioned Model IR with mandatory units, dimensional and numerical validation, calibration, uncertainty analysis, and portable export (SBML, CellML, Modelica) via CLI, REST and MCP. Install: pip install axiomize.

    Stale GitHub, Furox-Art 9 ★MITUpdated 16 days ago

    git clone https://github.com/Furox-Art/axiomize.git
  5. ai-playground

    AI repositories

    I put all my exploration around AI in reproducible notebooks in this repository

    Indexed GitHub, tuhinsharma121 113 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/tuhinsharma121/ai-playground.git
  6. Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex, Hermes, Claude code as well as OpenClaw compatibility

    Stale GitHub, Zhonghao1995 31 ★MITUpdated 19 days ago

    git clone https://github.com/Zhonghao1995/agentic-swmm-workflow.git
  7. An Agent Skill for Claude Code, Codex and other coding agents: train on rented GPUs without losing checkpoints or paying for idle machines.

    Stale GitHub, Hanyuyuan6 42 ★MITUpdated 25 days ago

    git clone https://github.com/Hanyuyuan6/remote-gpu-trainer.git
  8. memor

    Prompts

    Reproducible Structured Memory for LLMs

    Stale GitHub, openscilab 69 ★MITUpdated 11 days ago

    git clone https://github.com/openscilab/memor.git
  9. repertoire-ai

    Skills

    The lockfile for agent skills. A package manager with named catalogs, a digest per target, and a manifest you commit. 30+ agents, no telemetry.

    Indexed GitHub, phillarmonic 10 ★MITUpdated 3 days ago

    git clone https://github.com/phillarmonic/repertoire-ai.git
  10. FPF

    Agents & frameworks

    FPF (First Principles Framework) Library: methods and pattern languages for open-ended development and a shared culture of thinking and acting among people and AI agents. Use individual methods or combine them to solve difficult problems and expand capabilities.

    Indexed GitHub, ailev 542 ★CC-BY-4.0Updated today

    git clone https://github.com/ailev/FPF.git
  11. DreamLayer-Eval

    AI repositories

    DreamLayer Eval: open-source benchmarking for image and video diffusion models. Automate prompts, seeds, and metrics for reproducible results. A research project from DreamLayer AI (dreamlayer.io).

    Stale GitHub, TheDesignFounder 412 ★GPL-3.0Updated 17 days ago

    git clone https://github.com/TheDesignFounder/DreamLayer-Eval.git
  12. Evidence-bounded skill for drafting, rewriting, humanizing, and auditing IEEE/ACM engineering manuscripts.

    Indexed GitHub, huguryildiz 14 ★MITUpdated today

    git clone https://github.com/huguryildiz/ieee-acm-paper-writing.git
  13. saluteface-public

    Agents & frameworks

    Open-source AI research agent for protein watermarking, autonomous research workflows, reproducible datasets, and Hugging Face publishing.

    Stale GitHub, IAmAaronYang 138 ★MITUpdated 32 days ago

    git clone https://github.com/IAmAaronYang/saluteface-public.git
  14. Local-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.

    Stale GitHub, xuzhougeng 140 ★MITUpdated 4 days ago

    git clone https://github.com/xuzhougeng/ScientificFigureLibrary.git
  15. mantis

    Prompts

    A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.

    Indexed GitHub, google 2,787 ★Apache-2.0Updated yesterday

    git clone https://github.com/google/mantis.git
  16. statewave

    AI repositories

    Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.

    Indexed GitHub, smaramwbc 267 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/smaramwbc/statewave.git
  17. memtrust

    MCP servers

    Independent, reproducible benchmark harness for agent-memory backends.

    Stale Official MCP Registry, io.github.RudrenduPaul Updated 3 months ago 1 note

    memtrust-cli@0.3.6
  18. Evidence-grounded skills and software-tool records for scientific AI agents, distilled from method papers by the AgenticScienceBuilder pipeline. Metabolomics: 5,859 skills, 909 tools, 21 workflows.

    Stale GitHub, HolobiomicsLab 16 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/HolobiomicsLab/asb-skill-collections.git
  19. benchmarks

    Agents & frameworks

    Reproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.

    Stale GitHub, coval-ai 104 ★Custom licence (see repository)Updated 24 days ago

    git clone https://github.com/coval-ai/benchmarks.git
  20. witnessed

    MCP servers

    Signed, reproducible market facts for agents, verifiable without trust.

    Stale Official MCP Registry, io.github.BARRYPMARSHALL Updated 27 days ago 1 note

    witnessed-sdk@0.2.0
  21. TwinFix

    Datasets & benchmarks

    TwinFix — AI agent that diagnoses, reproduces and fixes bugs in a disposable twin environment. 在一次性孪生环境中自动诊断、复现并修复故障的 AI Agent。

    Indexed GitHub, spacesky-cell 117 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/spacesky-cell/TwinFix.git
  22. BambooAI

    Agents & frameworks

    AI-powered data analysis workbench built for transparency, reproducibility and user control. Inspect the code and evidence behind results, verify calculations through replay, and choose from a wide range of models, including local open-weight models.

    Stale GitHub, pgalko 840 ★MITUpdated 8 days ago

    git clone https://github.com/pgalko/BambooAI.git
  23. PyHealth

    Datasets & benchmarks

    A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.

    Indexed GitHub, sunlabuiuc 1,699 ★MITUpdated today

    git clone https://github.com/sunlabuiuc/PyHealth.git
  24. BenchMARL

    Agents & frameworks

    BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

    Stale GitHub, facebookresearch 672 ★MITUpdated 9 months ago

    git clone https://github.com/facebookresearch/BenchMARL.git

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.