Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
ai4s-skills
SkillsOpen-source agent skills for AI for Science: topic exploration, literature survey, experiments, paper writing, and integrity audit — driven by any coding agent.
git clone https://github.com/ai4s-research/ai4s-skills.git -
AgentLab
Datasets & benchmarksAgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
git clone https://github.com/ServiceNow/AgentLab.git -
OpenEMMA
AI repositoriesOpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.
git clone https://github.com/taco-group/OpenEMMA.git -
axiomize
SkillsReproducible 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.
git clone https://github.com/Furox-Art/axiomize.git -
ai-playground
AI repositoriesI put all my exploration around AI in reproducible notebooks in this repository
git clone https://github.com/tuhinsharma121/ai-playground.git -
agentic-swmm-workflow
SkillsAgentic 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
git clone https://github.com/Zhonghao1995/agentic-swmm-workflow.git -
remote-gpu-trainer
SkillsAn Agent Skill for Claude Code, Codex and other coding agents: train on rented GPUs without losing checkpoints or paying for idle machines.
git clone https://github.com/Hanyuyuan6/remote-gpu-trainer.git -
memor
PromptsReproducible Structured Memory for LLMs
git clone https://github.com/openscilab/memor.git -
repertoire-ai
SkillsThe lockfile for agent skills. A package manager with named catalogs, a digest per target, and a manifest you commit. 30+ agents, no telemetry.
git clone https://github.com/phillarmonic/repertoire-ai.git -
FPF
Agents & frameworksFPF (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.
git clone https://github.com/ailev/FPF.git -
DreamLayer-Eval
AI repositoriesDreamLayer 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).
git clone https://github.com/TheDesignFounder/DreamLayer-Eval.git -
ieee-acm-paper-writing
SkillsEvidence-bounded skill for drafting, rewriting, humanizing, and auditing IEEE/ACM engineering manuscripts.
git clone https://github.com/huguryildiz/ieee-acm-paper-writing.git -
saluteface-public
Agents & frameworksOpen-source AI research agent for protein watermarking, autonomous research workflows, reproducible datasets, and Hugging Face publishing.
git clone https://github.com/IAmAaronYang/saluteface-public.git -
ScientificFigureLibrary
MCP serversLocal-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.
git clone https://github.com/xuzhougeng/ScientificFigureLibrary.git -
mantis
PromptsA modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
git clone https://github.com/google/mantis.git -
statewave
AI repositoriesOpen-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.
git clone https://github.com/smaramwbc/statewave.git -
memtrust
MCP serversIndependent, reproducible benchmark harness for agent-memory backends.
memtrust-cli@0.3.6 -
asb-skill-collections
SkillsEvidence-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.
git clone https://github.com/HolobiomicsLab/asb-skill-collections.git -
benchmarks
Agents & frameworksReproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.
git clone https://github.com/coval-ai/benchmarks.git -
witnessed
MCP serversSigned, reproducible market facts for agents, verifiable without trust.
witnessed-sdk@0.2.0 -
TwinFix
Datasets & benchmarksTwinFix — 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。
git clone https://github.com/spacesky-cell/TwinFix.git -
BambooAI
Agents & frameworksAI-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.
git clone https://github.com/pgalko/BambooAI.git -
PyHealth
Datasets & benchmarksA deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
git clone https://github.com/sunlabuiuc/PyHealth.git -
BenchMARL
Agents & frameworksBenchMARL 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.
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.