Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Ix
Tools & appsUnderstand any codebase instantly. System intelligence for codebases, built for humans and AI.
git clone https://github.com/ix-infrastructure/Ix.git -
EKOS
MCP serversEKOS is an AI-native platform that continuously reconstructs, compiles, stores and serves enterprise knowledge.
git clone https://github.com/alexeyban/EKOS.git -
reposwarm
Tools & appsOpen-source multi-repo architecture discovery for AI coding agents. Analyze repositories, generate standardized .arch.md files, and keep them in a central results hub for agent context, onboarding and architecture reviews. GitHub, GitLab, CodeCommit, Azure DevOps and Bitbucket. Apache-2.0.
git clone https://github.com/reposwarm/reposwarm.git -
gemini-mcp-tool
MCP serversMCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding
git clone https://github.com/jamubc/gemini-mcp-tool.git -
Sense
MCP serversCodebase understanding for AI coding agents — symbol graph, blast radius, semantic search.
https://github.com/luuuc/sense/releases/download/v0.84.3/sense_0.84.3_darwin_arm64.mcpb -
Meeba Brain
MCP serversRepository knowledge graph MCP server for codebase understanding and debugging.
-
rune
MCP serversEvidence-backed codebase understanding with file:line citations, for AI clients over MCP.
https://github.com/thecolourfoundation/rune/releases/download/v0.5.1/rune-mcp-linux-x64.mcpb -
grand-tour-rpocket
SkillsAgent skill that conducts an interactive architectural walkthrough and verification quiz over a codebase.
git clone https://github.com/YorEthereallab4497-alt/grand-tour-rpocket.git -
Span
MCP serversCodebase understanding with exact evidence, qualified on every read and re-aligned on change.
span-mcp@0.10.4 -
Meta: Muse Spark Open
ModelsMuse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...
meta/muse-spark-open
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.