Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
PaperOrchestra
SkillsAn automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.
git clone https://github.com/Ar9av/PaperOrchestra.git -
bisheng
AI repositoriesBISHENG is an open-source enterprise Agent platform for building, deploying, and managing AI applications. It combines AI agents, workflows, RAG and knowledge management, desktop agent integration, and vibecoding app hosting with unified model management, evaluation, observability, access control, and enterprise administration.
git clone https://github.com/dataelement/bisheng.git -
Open-Workflow-Library
Tools & appsOpen workflow intelligence for discovering, validating, repairing, and generating automation workflows across frameworks — starting with n8n.
git clone https://github.com/oxbshw/Open-Workflow-Library.git -
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 -
Sponsio
SkillsDeterministic safety solutions for probabilistic AI agents
git clone https://github.com/SponsioLabs/Sponsio.git -
agentset
AI repositoriesThe open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
git clone https://github.com/agentset-ai/agentset.git -
llm-wiki-compiler
SkillsThe knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.
git clone https://github.com/atomicstrata/llm-wiki-compiler.git -
codec
Agents & frameworksOpen-Source Intelligent Command Layer
git clone https://github.com/AVADSA25/codec.git -
sloptrim
SkillsA local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.
git clone https://github.com/seyedehsanhadi/sloptrim.git -
Parser Club
MCP serversTelegram/VK audience scraping, marketplaces, Russian government registers. Free open dataset.
-
munimind-mcp
MCP serversQuery 2,500+ NYC civic datasets (zoning, deeds, permits, violations, meetings) via Claude.
munimind-mcp@0.3.2 -
Roboflow (Official)
MCP serversRoboflow computer vision for AI agents: datasets, annotation, versioning, workflows, inference.
-
mcp
MCP serversPay for x402 paywalls, datasets, and store checkouts on Solana, behind hard spending caps.
@solinkify/mcp@0.3.3 -
fiftyone-mcp-server
MCP serversControl FiftyOne computer vision datasets through AI assistants using 80+ operators.
fiftyone-mcp-server@0.1.2 -
Kaggle-mcp
MCP serversMCP server for the Kaggle API: competitions, datasets, kernels, and models.
mcp-server-kaggle@0.1.1 -
Braintrust
MCP serversAI evaluation and observability platform — query experiments, logs, datasets, and prompts.
-
gbif-mcp-server
MCP serversSearch GBIF species taxonomy, occurrence records, datasets, and publishers.
@cyanheads/gbif-mcp-server@0.1.7 -
Fda Devices
MCP serversFDA medical-device regulatory intelligence from keyless openFDA datasets.
@pipeworx/mcp-fda-devices@0.2.1 -
mirelia-patent-market
MCP serversAI-optimized patent data marketplace providing structured JSON datasets.
-
openFDA MCP by usefulapi
MCP serversSearch openFDA drug, device, food and adverse-event datasets.
-
GreyNoise
Public APIsQuery IPs in the GreyNoise dataset and retrieve a subset of the full IP context data
-
obis-mcp
MCP serversOBIS marine biodiversity: taxon records, accepted names, children, occurrence records and datasets.
@mrfentmen/obis-mcp@1.0.1 -
Harashsuq
MCP serversMarketplace where AI agents buy prompt packs, workflows, personas, datasets and playbooks.
-
NHTSA Edge VIN Decoder
Public APIsDecode US VINs offline from the NHTSA vPIC dataset, served from edge locations
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.