InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. rag-from-scratch

    Agents & frameworks

    Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.

    Stale GitHub, pguso 1,643 ★MITUpdated 8 months ago

    git clone https://github.com/pguso/rag-from-scratch.git
  2. anchr-app

    AI repositories

    Self-hostable RAG backend for document knowledge: hybrid search, cited answers, and agentic deep reading. Java · Spring Boot · Spring AI · Elasticsearch.

    Stale GitHub, ryanmeowy 109 ★MITUpdated 32 days ago

    git clone https://github.com/ryanmeowy/anchr-app.git
  3. TrueMemory

    AI repositories

    The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.

    Stale GitHub, buildingjoshbetter 385 ★AGPL-3.0Updated 19 days ago

    git clone https://github.com/buildingjoshbetter/TrueMemory.git
  4. dense-mem

    MCP servers

    Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgvector

    Indexed GitHub, markhuangai 39 ★Apache-2.0Updated yesterday

    git clone https://github.com/markhuangai/dense-mem.git
  5. vector-graph-rag

    AI repositories

    Graph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.

    Indexed GitHub, zilliztech 325 ★MITUpdated 4 days ago

    git clone https://github.com/zilliztech/vector-graph-rag.git
  6. prism-coder

    MCP servers

    Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.

    Indexed GitHub, dcostenco 156 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/dcostenco/prism-coder.git
  7. vectordb-recipes

    AI repositories

    Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs

    Stale GitHub, lancedb 986 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/lancedb/vectordb-recipes.git
  8. A complete collection of RAG interview questions, answers (1619 questions & 52 RAG types), system design scenarios, architecture patterns, and production-ready concepts.

    Stale GitHub, ather-techie 183 ★MITUpdated 14 days ago

    git clone https://github.com/ather-techie/rag-interview-system.git
  9. agenticow

    Agents & frameworks

    Git for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory (83x faster, 3000x smaller snapshots)

    Stale GitHub, ruvnet 56 ★MITUpdated 5 days ago

    git clone https://github.com/ruvnet/agenticow.git
  10. mneme

    AI repositories

    The memory that dreams — long-term memory for AI agents. Readable files on your own machine, consolidated between sessions. Runs as a DeepSeek Harness plugin or over MCP.

    Indexed GitHub, slow-stack 234 ★MITUpdated yesterday

    git clone https://github.com/slow-stack/mneme.git
  11. inite-brain-service

    MCP servers

    Open-source bitemporal knowledge graph — long-term memory for AI agents. Hybrid retrieval, conflict-aware ingest, GDPR forget. REST + native MCP.

    Indexed GitHub, inite-ai 43 ★AGPL-3.0Updated yesterday

    git clone https://github.com/inite-ai/inite-brain-service.git
  12. starling

    AI repositories

    Local AI in .NET, with no Python sidecar and no API key: embeddings, entity extraction, image and video search and chat on ONNX Runtime (CPU/CUDA), through Microsoft.Extensions.AI.

    Indexed GitHub, starlinghq 102 ★Apache-2.0Updated today

    git clone https://github.com/starlinghq/starling.git
  13. codesearch

    MCP servers

    Multi-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor, and any MCP client.

    Stale GitHub, flupkede 92 ★Apache-2.0Updated 29 days ago

    git clone https://github.com/flupkede/codesearch.git
  14. vera

    AI repositories

    Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

    Indexed GitHub, VeraTools 148 ★MITUpdated 4 days ago

    git clone https://github.com/VeraTools/vera.git
  15. RustFox

    Skills

    Your own local AI assistant on Telegram — Rust, sandbox, schedule, MCP, persistent memory. Provider-agnostic (OpenRouter, OpenCode, xAI…).

    Indexed GitHub, chinkan 12 ★MITUpdated 3 days ago

    git clone https://github.com/chinkan/RustFox.git
  16. basemind

    AI repositories

    Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

    Indexed GitHub, Goldziher 121 ★MITUpdated today

    git clone https://github.com/Goldziher/basemind.git
  17. NornicDB

    MCP servers

    Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.

    Indexed GitHub, orneryd 931 ★MITUpdated yesterday

    git clone https://github.com/orneryd/NornicDB.git
  18. docling-Studio

    AI repositories

    Chunkless RAG for AI agents, powered by Docling. Parse your PDFs, inspect every title, table and box on the page, then let any MCP client (Claude, Cursor…) read only the sections it needs under a token budget and cite exact, server-verified passages. No chunks, no embeddings, no vector store.

    Indexed GitHub, scub-france 277 ★MITUpdated yesterday

    git clone https://github.com/scub-france/docling-Studio.git
  19. resonant-mind

    MCP servers

    Persistent cognitive infrastructure for AI systems. 28 MCP tools — semantic memory, emotional processing, identity continuity, and a subconscious daemon. Built on Cloudflare Workers.

    Indexed GitHub, nekyialabs 34 ★Custom licence (see repository)Updated today

    git clone https://github.com/nekyialabs/resonant-mind.git
  20. mind-mem

    MCP servers

    Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure.

    Indexed GitHub, star-ga 22 ★Apache-2.0Updated today

    git clone https://github.com/star-ga/mind-mem.git
  21. vector-admin

    Agents & frameworks

    The universal tool suite for vector database management. Manage Pinecone, Chroma, Qdrant, Weaviate and more vector databases with ease.

    Stale Archived GitHub, Mintplex-Labs 2,243 ★MITUpdated 19 months ago 1 note

    git clone https://github.com/Mintplex-Labs/vector-admin.git
  22. Citadel

    MCP servers

    Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools

    Stale Official MCP Registry, dev.citadeldb Updated 49 days ago 2 notes

    citadeldb-mcp@2.7.0
  23. fortemi

    MCP servers

    Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.

    Indexed GitHub, Fortemi 30 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/Fortemi/fortemi.git
  24. OmniMem

    MCP servers

    Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills compiled from what worked, plus knowledge from the RSS feeds you read. One Rust binary on SQLite: a tray app for macOS, Windows and Linux, or a server.

    Indexed GitHub, richarvey 95 ★MITUpdated 4 days ago

    git clone https://github.com/richarvey/OmniMem.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.