Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
technocore-chat
Agents & frameworksHTTP-native chat and notes for agents whose sandbox only allows webfetch — every write is a plain GET. Runs technocore.chat.
git clone https://github.com/flop-labs/technocore-chat.git -
second-brain
Tools & appsSecond Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.
git clone https://github.com/henrydaum/second-brain.git -
fieldcraft
Agents & frameworksOne open-source modeler for structures, heat and fluids, built from scratch in pure Rust: parametric part in, verified results out. Automatic all-hex and tet meshing, our own nonlinear implicit and explicit FEA, heat transfer and lattice Boltzmann CFD — every result checked against theory. For engineers and AI agents alike. Free, forever.
git clone https://github.com/tangency-labs/fieldcraft.git -
ai-agent-automation
Tools & appsModular AI agent workflow automation platform with schedulers, tools, and observability. https://vmdeshpande.github.io/ai-automation-platform-website/
git clone https://github.com/vmDeshpande/ai-agent-automation.git -
awesome-claude-video-skills
SkillsOpen-source skills and toolkits that let Claude Code, Codex and other coding agents make video. 180 repos by type, each security-graded. English / 中文.
git clone https://github.com/zhuyansen/awesome-claude-video-skills.git -
agentic-loop-engineering-course
Docs & tutorialsAn 18 notebook course that isolates and measures each component of agentic loop engineering on real, industry standard software datasets.
git clone https://github.com/FareedKhan-dev/agentic-loop-engineering-course.git -
MedXpertQA
Datasets & benchmarks[ICML 2025] MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
git clone https://github.com/TsinghuaC3I/MedXpertQA.git -
LongCite
Datasets & benchmarksLongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
git clone https://github.com/THUDM/LongCite.git -
SuperLocalMemory
MCP serversLocal-first memory for AI agents: recall with sources, answer checks, documents, mesh, governance.
superlocalmemory@4.2.19 -
langchain4j
AI repositoriesLangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.
git clone https://github.com/langchain4j/langchain4j.git -
assay
Agents & frameworksAn agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.
git clone https://github.com/awss1i/assay.git -
free-ai-tools
Docs & tutorialsCurated list of free and low cost AI tools, LLM APIs, IDEs, agents, and infrastructure for building real AI apps
git clone https://github.com/ShaikhWarsi/free-ai-tools.git -
mail
MCP serversA thoughtful home for your email marketing. Open-source campaigns, automations, and APIs. Self-host with Docker Swarm.
git clone https://github.com/mailxem/mail.git -
FRC Events
Public APIsOverview FIRST /FMS FRC Events API is a service to return relevant information about the FIRST Robotics Competition (FRC). Information is made available from events operating around the world. For FRC, information is made available by the Field Management System (FMS) server operating at each event site. The FMS will attempt to sync all data from the event to "the cloud" as long as internet is…
-
Hatchdoor
MCP serversSelf-host your Obsidian vaults: a web UI for you, MCP for your AI agents. No Obsidian, no plugins required.
git clone https://github.com/BatterWorks/Hatchdoor.git -
Webhound
MCP serversBudgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness.
webhound-mcp@0.5.2 -
site
MCP serversCapital Gains Tax HQ: the site's own MCP server — dataset, enquiry (enquiry = a human handoff,...
-
site
MCP serversEntitySearch HQ: the site's own MCP server — dataset, enquiry (enquiry = a human handoff, not a...
-
site
MCP serversEOR Compass: the site's own MCP server — dataset, enquiry (enquiry = a human handoff, not a...
-
site
MCP serversFindAgency HQ: the site's own MCP server — dataset, enquiry (enquiry = a human handoff, not a...
-
site
MCP serversGPA Grade Compare: the site's own MCP server — dataset, enquiry (enquiry = a human handoff, not...
-
site
MCP serversHomeCover HQ: the site's own MCP server — dataset, enquiry (enquiry = a human handoff, not a...
-
site
MCP serversMed Spa Cost Checker: the site's own MCP server — dataset, enquiry (enquiry = a human handoff,...
-
site
MCP serversRechner HQ: the site's own MCP server — dataset, enquiry (enquiry = a human handoff, not a...
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.