Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
VelesDB
AI repositoriesThe explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.
git clone https://github.com/cyberlife-coder/VelesDB.git -
lasagna
Datasets & benchmarksSwap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.
git clone https://github.com/dolev31/lasagna.git -
console
MCP serversOpen-source, self-hosted AI gateway and control plane: OpenAI-compatible LLM routing, RAG, an MCP hub, guardrails and agent tracing for multi-tenant teams.
git clone https://github.com/Cognipeer/console.git -
knolo-core
AI repositoriesThe open framework AI agents use to share knowledge with one another. Pack knowledge into a portable, verifiable Knowledge Image, pin it by digest, mount it locally over MCP, and prove what was used. Local-first, deterministic, no vector DB required.
git clone https://github.com/HiveForensics-AI/knolo-core.git -
vectorsearch
MCP serversStore and retrieve text in a Qdrant vector database by similarity search.
@reneturcios/vectorsearch@0.1.0 -
Sibyl-Memory
AI repositoriesDurable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseStore. No vector database, no embeddings.
git clone https://github.com/Sibyl-Labs/Sibyl-Memory.git -
vector-store-scanner
MCP serversProbes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
@guardbee/mcp-vector-store-scanner@0.1.1 -
vector-store-scanner
MCP serversProbes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
@guardbee/mcp-vector-store-scanner@0.3.1 -
awesome-ai-agent-stack
MCP serversCurated map of 3,000+ open-source AI agent tools: coding agents, agent frameworks, MCP servers, RAG, memory and local LLMs, sorted by layer and ranked by GitHub stars.
git clone https://github.com/tayyabimam1/awesome-ai-agent-stack.git -
mcp
MCP serversBuild and deploy backends: auth, Postgres/MySQL/vector databases, storage, functions, hosting, CDN
mcp-server-appwrite@2.6.2 -
ChromaDB Remote MCP Server
MCP serversRemote ChromaDB vector database MCP server with streamable HTTP transport
devsaurus/chromadb-remote-mcp:latest -
HelixDB
MCP serversGraph-vector database: run Helix queries, read query insights and health, manage databases
-
Local FAISS MCP Server
MCP serversLocal FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
local-faiss-mcp@0.2.0-rc.3 -
samyama-graph
MCP serversRust graph-vector database: OpenCypher (99.9% of evaluated TCK scenarios pass), vector search, graph algorithms, RESP + HTTP. LDBC SNB Interactive and BI complete; 1B edges on one machine.
git clone https://github.com/samyama-ai/samyama-graph.git -
ai-memory-vault
SkillsGive your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No vector database, just markdown.
git clone https://github.com/jaredrhod/ai-memory-vault.git -
10xGraph
MCP serversProduction-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground
git clone https://github.com/10xGraph/10xGraph.git -
Pinecone API
Public APIsPinecone is a vector database. This is an unofficial, community-managed OpenAPI spec that (should) accurately model the Pinecone API. This project was developed independent of and is unaffiliated with Pinecone Systems. Users should switch to the official API spec, if and when Pinecone releases it.
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.