Live-updating landscape of vector database projects, integrations, and benchmarks — refreshed every 15 minutes
⭐ Star this repo to bookmark — fresh data every 15 minutes
Automatically tracks and compares the vector database ecosystem by pulling live data from GitHub, package registries, and release feeds. Generates a structured, always-current comparison table covering maturity, integrations, language support, and recent activity for projects like pgvector, Qdrant, Chroma, Weaviate, and Milvus.
This list is auto-updated every 15 minutes by a GitHub Actions cron. Each commit reflects a real change in the upstream data source — new items added, expired items removed — so you can rely on what you see being current.
⏰ Last updated: 2026-07-16 02:15 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | EonsofStupid/rrf | 0 | Rust | 2026-07-16 | Reason Ready Flow — not just RAG. An embedded, tokio-native retrieval-and-reasoning engine that judges whether what it f |
| 2 | linny006/rag-radar | 2 | Python | 2026-07-16 | Live tracker of new RAG implementations, tools, and patterns — updated every 15 minutes |
| 3 | linny006/vector-db-live | 2 | Python | 2026-07-16 | Live-updating landscape of vector database projects, integrations, and benchmarks — refreshed every |
| 4 | MariaDB/server | 7856 | C++ | 2026-07-16 | MariaDB server is a community developed fork of MySQL server. Started by core members of the original MySQL team, MariaD |
| 5 | 0xLazAI/alith | 44 | Rust | 2026-07-16 | Simple, Composable, High-Performance, Safe and Web3 Friendly AI Agents and LazAI Gateway for Everyone |
| 6 | schmitech/orbit | 307 | Python | 2026-07-16 | Self-hosted, OpenAI-compatible AI gateway for private RAG, natural-language data access, and tool-calling agents. |
| 7 | treygrainger/ai-powered-search | 399 | Jupyter Notebook | 2026-07-16 | The codebase for the book "AI-Powered Search" (Manning Publications, 2025) and associated "AI-Powered Search: Modern Ret |
| 8 | cyberlife-coder/VelesDB | 75 | Rust | 2026-07-16 | The local-first memory engine for AI agents. One offline Rust binary fuses vector + graph + columnar under SQL — remembe |
| 9 | integrallis/vectors | 0 | Java | 2026-07-16 | The Ultimate Vectors Library for Java |
| 10 | codecoradev/uteke | 112 | Rust | 2026-07-16 | 🧠 The Brain for Your AI — Local-first memory engine for AI agents. Store, recall, and search memories with semantic embe |
| 11 | doriapt53/spring-manifold-next-gen | 0 | TypeScript | 2026-07-16 | Orchestrate enterprise data ingestion from diverse repository connectors into vector search infrastructure using Java 25 |
| 12 | impressionable-pyrrhotite668/adaptive-multistage-rag-system | 0 | Jupyter Notebook | 2026-07-16 | Optimize long-document question answering with a multi-stage RAG pipeline featuring query-aware routing, cross-encoder r |
| 13 | jushayden/claude-code-memory-cache | 2 | Python | 2026-07-16 | Persistent, token-efficient memory for Claude Code — 5 memory layers (vector store, file facts, Obsidian vault, code gra |
| 14 | Accessible-sloughing768/docustra | 0 | Python | 2026-07-16 | Compare RAG architectures, chunking strategies, and reliability features using this production-grade document intelligen |
| 15 | jourdaninorder609/mind-query | 0 | TypeScript | 2026-07-16 | Convert natural language into SQL and MQL queries for PostgreSQL, MySQL, SQL Server, and MongoDB using an MCP-enabled ag |
| 16 | Surging-scotandlot818/product-dev-blueprint | 0 | TypeScript | 2026-07-16 | Transform software concepts into structured build plans with this schema-first product planning tool for engineering tea |
| 17 | surrealdb/docs.surrealdb.com | 119 | MDX | 2026-07-16 | The documentation for SurrealDB, powered by Astro |
| 18 | Roseapplemutualopposition5427/rag-llamaindex-qdrant-docker | 0 | Dockerfile | 2026-07-16 | Build a multi-collection RAG system using LlamaIndex and Qdrant in a Docker environment. |
| 19 | constancywoodsy286/agentic-rag-for-practice | 1 | Python | 2026-07-16 | Build an agentic RAG document QA system with multi-user support, hybrid retrieval, reranking, and LangGraph workflows fo |
| 20 | jefffergunson118-beep/smara | 1 | — | 2026-07-16 | Sync persistent memory across your AI tools and agents using a unified MCP server. |
| 21 | Tobiaszn8972/turboquant-gpu | 2 | Python | 2026-07-16 | Compress KV cache for LLM inference with 5.02x efficiency on NVIDIA GPUs using cuTile kernels. |
| 22 | sarcosomebankcheck694/coordinode | 0 | Rust | 2026-07-16 | Unify graph, vector, and full-text search in one Rust engine for GraphRAG and AI retrieval with OpenCypher and MVCC |
| 23 | Rippledirham767/LongParser | 1 | Python | 2026-07-16 | Parse PDFs, DOCX, PPTX, XLSX, and CSV into validated, AI-ready chunks for privacy-first RAG pipelines with HITL review |
| 24 | viviannenitrogenous100/mentedb | 0 | — | 2026-07-16 | Build an AI memory database for agents with a Rust storage engine designed for LLM data and fast retrieval |
| 25 | cornelablastular720/dbdb-index | 1 | Go | 2026-07-16 | Browse and index 1,071 database systems from DBDB.io for fast discovery, comparison, and research |
| 26 | nguyenquoaca-hash/agentic-mesh | 1 | HTML | 2026-07-16 | Multi-Agent AI Orchestrator 2026 🚀 | YAML, 6+ LLM Providers, ReAct & Swarm |
| 27 | Twentyeight-lawnchair711/AlayaRenderer | 0 | — | 2026-07-16 | Build an AI-native renderer for games and virtual worlds, with data and tools for world creation and editing |
| 28 | raymondmdzz123/agent-memory | 1 | TypeScript | 2026-07-16 | Store persistent AI agent memory with conversation history, vector search, knowledge base, and fact extraction in TypeSc |
| 29 | Ac3v3d0/semafold | 3 | Python | 2026-07-16 | Compress embeddings, retrieval vectors, and KV-cache with TurboQuant codecs for 10x smaller storage and NumPy-first AI w |
| 30 | Synchronic-leafbud824/skill-vault | 1 | — | 2026-07-16 | Organize, secure, and find Claude Code skills in one vault for easy reuse |
| 31 | Genusophiophagussqueezeplay359/ragpipe | 0 | Python | 2026-07-16 | Build RAG pipelines in 3 functions for vector databases with zero config and support for Ollama, OpenAI, Qdrant, Pinecon |
| 32 | aziz5971/TalentLens | 2 | Python | 2026-07-16 | Analyze candidates with a multi-agent AI screening pipeline that matches skills, verifies background, and prepares inter |
| 33 | Deafened-vascularstructure846/pageindex-rag | 1 | Python | 2026-07-16 | Build vectorless RAG for reasoning-based retrieval and answer generation with no embeddings or vector store |
| 34 | roberthalfway204/Document-Intelligent-Assistant | 1 | Python | 2026-07-16 | Transform scanned documents into searchable, structured data with OCR, AI extraction, and Python automation |
| 35 | lannyfervent952/fastapi-agent-blueprint | 1 | Python | 2026-07-16 | Build FastAPI AI agents with a clear blueprint for reliable, maintainable app architecture |
| 36 | Bielrezende/WMB-100K | 0 | — | 2026-07-16 | Benchmark AI memory systems for situational retrieval with 4.3M tokens and 2,708 questions in real-world scenarios |
| 37 | milvus-io/milvus | 45238 | Go | 2026-07-16 | Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search |
| 38 | okeidontlike/Awareness-Local | 2 | JavaScript | 2026-07-16 | Add local persistent memory to AI coding agents with Markdown storage, hybrid search, and MCP support, all offline. |
| 39 | ahmahmahm/pdf-rag-assistant | 0 | — | 2026-07-16 | Build PDF Q&A with RAG, OpenAI, and ChromaDB for fast, local answers from policies, contracts, and resumes |
| 40 | Uncomfortable-filagree112/OpenViking | 0 | — | 2026-07-16 | Provide a scalable context database designed to improve memory and data handling for AI agents in complex tasks. |
| 41 | Daubingweirdie414/multimodal-rag | 3 | Python | 2026-07-16 | Enable unified search and AI answers across text, images, audio, and video using multimodal retrieval-augmented generati |
| 42 | Ekaterinaacid284/memory-lancedb-pro-skill | 0 | — | 2026-07-16 | Provide Claude Code with expert guidance to install, configure, and optimize memory-lancedb-pro for long-term AI memory |
| 43 | cornellebivalved856/example-multimodal-rag | 0 | Python | 2026-07-16 | Search and retrieve information from text, images, and video using unified Gemini Embedding 2 vectors with Supabase and |
| 44 | decided-indication109/AI-Engineer-in-90-Days | 2 | Mermaid | 2026-07-16 | Build practical AI systems and agents in 90 days with a clear, project-based roadmap for developers seeking hands-on AI |
| 45 | BMC-INC/Iron-mem | 5 | Rust | 2026-07-16 | Agent-native memory infrastructure for AI coding assistants. Governed session capture, LLM compression, hybrid retrieval |
| 46 | Boney-massiveness357/ragscope | 0 | Python | 2026-07-16 | Build a Q&A API that indexes PDFs and text using RAG, logging queries with MLflow for offline document search and evalua |
| 47 | eastythenob8-svg/graph-memory | 1 | TypeScript | 2026-07-16 | Manage and compress long conversation histories into structured knowledge graphs to improve context retention across ses |
| 48 | conceited-watergillyflower311/meilisearch-desktop | 1 | TypeScript | 2026-07-16 | Manage Meilisearch instances across platforms with a desktop app built using Tauri 2 and React for efficient, cross-plat |
| 49 | Arthrocentesisgenusphylloxera328/rag-forge | 1 | Python | 2026-07-16 | Benchmark RAG pipeline configurations by testing chunking, embedding, and retrieval methods to identify the best setup f |
| 50 | MrPeppersDev/agent-infrastructure-landscape | 1 | HTML | 2026-07-16 | AI agent memory & infrastructure landscape — comparative catalog of 912 systems × 68 columns covering memory layers, age |
Every 15 minutes, a GitHub Action runs tracker.py. That script:
- Fetches the latest state from
GitHub Search API. - Diffs against
data/items.json(the previous snapshot). - Rewrites the table above between the
<!-- TRACKER_TABLE_* -->markers. - Commits
feat: +N added, -M removed (timestamp)if anything changed.
No external services. No paid APIs. Just a public data source and a free GitHub Action.
See CONTRIBUTING.md — usually you don't need to: the tracker keeps itself current.
If you spot a data-source bug or want to suggest a new column for the table, open
an issue.
If you find this useful, you might also like these other auto-updated trackers from the same maintainer — same mechanism, different upstream:
- trending-claude-skills — What's shipping in Claude Skills this week (
topic:claude-skills) - mcp-servers-live — Live index of newest MCP servers (
topic:mcp-server) - cursor-rules-live — Newest Cursor rules and .cursorrules patterns (
topic:cursor-rules) - claude-code-plugin-tracker — Claude Code plugins and hook configs (
topic:claude-code) - llm-agents-radar — Newest LLM agent frameworks (
topic:llm-agent) - rag-radar — Newest RAG implementations and tools (
topic:rag) - llm-eval-tracker — Newest LLM evaluation tools and benchmarks (
topic:llm-eval) - agent-framework-radar — Newest agent frameworks shipping on GitHub (
topic:agent-framework) - llmops-radar — Newest LLMOps tooling (observability, deployment) (
topic:llmops) - prompt-tools-live — Newest prompt-engineering tools and prompt repos (
topic:prompt-engineering) - agent-eval-harness — Live benchmark of AI coding agents (
topic:llm-eval) - skills-tracker — Tracking new GitHub 'skills' repos (
topic:agent-skills) - awesome-agent-skills — Curated auto-updated awesome-list of AI agent skills (
topic:agent-skills)
MIT — see LICENSE.