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: 2026-10-06 02:00 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | kylebrodeur/modal-embedding-server | 0 | Python | 2026-10-06 | A high-performance, generic GPU embedding stack on Modal with synthetic query generation, retrieval evaluation, and a mo |
| 2 | KeiaiLab/qdrant-operator | 0 | Go | 2026-10-06 | Kubernetes Operator for Qdrant — declarative QdrantCluster/QdrantCollection management, distributed (Raft) clusters, aut |
| 3 | 4nur4gmishr4/4nur4gmishr4 | 2 | JavaScript | 2026-10-06 | Backend-focused fullstack & applied ai dev. Building cool stuff with LLMs & agents. Obsessed with clean architecture & s |
| 4 | liliang-cn/cortexdb | 268 | Go | 2026-10-06 | AI memory and a knowledge graph in one SQLite file. Pure Go: vectors, RAG, agent memory, RDF/SPARQL, Cypher, 80+ MCP too |
| 5 | ArcadeData/arcadedb | 1180 | Java | 2026-10-06 | ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB and Redis. ArcadeDB is a |
| 6 | MrPeppersDev/agent-infrastructure-landscape | 5 | HTML | 2026-10-06 | AI agent memory & infrastructure landscape — comparative catalog of 912 systems × 68 columns covering memory layers, age |
| 7 | topoteretes/cognee | 31414 | Python | 2026-10-06 | Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small mode |
| 8 | gay00ung/vecnook | 2 | Rust | 2026-10-06 | Embedded vector database for Rust: from-scratch HNSW, atomic batches, durable storage, and no external crates. |
| 9 | linny006/vector-db-live | 3 | Python | 2026-10-06 | Live-updating landscape of vector database projects, integrations, and benchmarks — refreshed every |
| 10 | linny006/rag-radar | 3 | Python | 2026-10-06 | Live tracker of new RAG implementations, tools, and patterns — updated every 15 minutes |
| 11 | wickra-lib/wickra-genome | 1 | Rust | 2026-10-06 | A vector database of the whole market: every asset as a live vector over the 497 O(1) streaming indicators the registry |
| 12 | pwolfey09-sketch/embedflow | 0 | Python | 2026-10-06 | Migrate embedding models progressively over existing vector indexes without full re-embedding, enabling seamless upgrade |
| 13 | Constraintworthy6058/ai-github-repository-assistant | 0 | TypeScript | 2026-10-06 | Explore GitHub repositories privately with local AI assistance for code, architecture, PRs, issues, and commits—no cloud |
| 14 | threefigure-achromia682/ai-memory | 1 | — | 2026-10-06 | |
| 15 | alegameplays14-del/leica-infinity-2026 | 0 | — | 2026-10-06 | Setup Leica Infinity on Windows 10/11 64-bit with admin installer, license key, and essential workflow tools. |
| 16 | xerj-org/xerj | 2668 | Rust | 2026-10-06 | XERJ is the new way for AI to search data. Its autoindex capability activates agents to know your data without the token |
| 17 | Divine-vision-visiondivine21/less-tokens | 0 | — | 2026-10-06 | Reduce LLM token usage and API costs using this local, privacy-first optimization tool for ChatGPT, Claude, and Gemini. |
| 18 | Wry-letters233/notes-quiz-agent | 0 | JavaScript | 2026-10-06 | Convert PDF notes into cited answers, adaptive quizzes, and flashcards using local LLMs for private study. |
| 19 | retrograde-prosceniumwall239/ai-search-engine | 2 | Python | 2026-10-06 | Build a production-ready semantic search engine with FastAPI, vector databases, and LLM-powered citations for your docum |
| 20 | impressionable-pyrrhotite668/adaptive-multistage-rag-system | 0 | Jupyter Notebook | 2026-10-06 | Optimize long-document question answering with a multi-stage RAG pipeline featuring query-aware routing, cross-encoder r |
| 21 | eminsk/nanovector | 6 | C | 2026-10-06 | The SQLite of Vector Search & Episodic Memory for AI Agents in ~120KB. Pure C99, AVX2+FMA, ARM NEON, FASM x64, zero depe |
| 22 | constancywoodsy286/agentic-rag-for-practice | 1 | Python | 2026-10-06 | Build an agentic RAG document QA system with multi-user support, hybrid retrieval, reranking, and LangGraph workflows fo |
| 23 | sarcosomebankcheck694/coordinode | 0 | Rust | 2026-10-06 | Unify graph, vector, and full-text search in one Rust engine for GraphRAG and AI retrieval with OpenCypher and MVCC |
| 24 | Rippledirham767/LongParser | 1 | Python | 2026-10-06 | Parse PDFs, DOCX, PPTX, XLSX, and CSV into validated, AI-ready chunks for privacy-first RAG pipelines with HITL review |
| 25 | cornelablastular720/dbdb-index | 1 | Go | 2026-10-06 | Browse and index 1,071 database systems from DBDB.io for fast discovery, comparison, and research |
| 26 | Ac3v3d0/semafold | 4 | Python | 2026-10-06 | Compress embeddings, retrieval vectors, and KV-cache with TurboQuant codecs for 10x smaller storage and NumPy-first AI w |
| 27 | aziz5971/TalentLens | 2 | Python | 2026-10-06 | Analyze candidates with a multi-agent AI screening pipeline that matches skills, verifies background, and prepares inter |
| 28 | lannyfervent952/fastapi-agent-blueprint | 1 | Python | 2026-10-06 | Build FastAPI AI agents with a clear blueprint for reliable, maintainable app architecture |
| 29 | Bielrezende/WMB-100K | 0 | — | 2026-10-06 | Benchmark AI memory systems for situational retrieval with 4.3M tokens and 2,708 questions in real-world scenarios |
| 30 | okeidontlike/Awareness-Local | 2 | JavaScript | 2026-10-06 | Add local persistent memory to AI coding agents with Markdown storage, hybrid search, and MCP support, all offline. |
| 31 | ahmahmahm/pdf-rag-assistant | 0 | — | 2026-10-06 | Build PDF Q&A with RAG, OpenAI, and ChromaDB for fast, local answers from policies, contracts, and resumes |
| 32 | Ekaterinaacid284/memory-lancedb-pro-skill | 0 | — | 2026-10-06 | Provide Claude Code with expert guidance to install, configure, and optimize memory-lancedb-pro for long-term AI memory |
| 33 | decided-indication109/AI-Engineer-in-90-Days | 3 | Mermaid | 2026-10-06 | Build practical AI systems and agents in 90 days with a clear, project-based roadmap for developers seeking hands-on AI |
| 34 | eastythenob8-svg/graph-memory | 1 | TypeScript | 2026-10-06 | Manage and compress long conversation histories into structured knowledge graphs to improve context retention across ses |
| 35 | iqiipo-dev/PS-HK19_MindForge_MindForge | 2 | JavaScript | 2026-10-06 | Provide context-based, accurate answers to syllabus questions using AI powered by Retrieval-Augmented Generation for eff |
| 36 | Tribrix23/CleaveDB | 0 | Python | 2026-10-06 | Beyond NoSQL. A hyper-fast graph and vector database you query in plain English. Built on a unique Python, Rust, and C++ |
| 37 | a258huit58/claude-memory | 1 | JavaScript | 2026-10-06 | Enable persistent memory for Claude that works across crashes and restarts in both Claude Code and Claude Cowork environ |
| 38 | Anonymousforareason111/hybrid-orchestrator | 3 | Python | 2026-10-06 | 🤖 Implement hybrid human-AI orchestration patterns in Python to coordinate agents, manage sessions, and enable smooth AI |
| 39 | ELSAKKK/mnemos-mcp | 5 | Python | 2026-10-06 | 🧠 Transform documentation chaos into a structured memory system with Mnemos, your self-hosted, multi-context knowledge s |
| 40 | BiggerCap/agentops-hub | 2 | TypeScript | 2026-10-06 | 🤖 Orchestrate AI agents with ease using this production-ready platform, featuring real-time streaming and multi-tool exe |
| 41 | hankamarvanova/unified-db | 2 | Swift | 2026-10-06 | 🌟 Accelerate SQLite database operations on Apple Silicon with GPU power for faster analytics and efficient data manageme |
| 42 | lancedb/lancedb | 11605 | Rust | 2026-10-06 | Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less. |
| 43 | kldhsh123/Afterglow | 311 | Python | 2026-10-06 | 使用社交软件聊天记录结合向量数据库让AI更好的扮演对方的角色，在不微调模型的情况下可以达到可观的效果。把曾经的美好，续成往后的陪伴。 |
| 44 | drae1712/Agentic-RAG-Anime-Recommender-System | 2 | Python | 2026-10-06 | 🎬 Discover your next favorite anime with this advanced Retrieval-Augmented Generation system, offering precise recommend |
| 45 | mmnto-ai/totem | 17 | TypeScript | 2026-10-06 | Rules you can enforce, state you can derive, context you can query: plain files in your repo, under whichever coding age |
| 46 | Edublackk/self-correcting-rag-chatbot | 3 | — | 2026-10-06 | 🤖 Enhance chatbot accuracy with a self-correcting RAG system that ingests documents, retrieves data, and evaluates respo |
| 47 | piporyx/doc-qa-agent | 0 | Python | 2026-10-06 | 🤖 Create an interactive chatbot that answers questions from documents using OpenAI and Ollama, with a user-friendly Grad |
| 48 | leitoooatr/PythonVectorDB | 2 | Python | 2026-10-06 | 🗄️ Manage and search large vector datasets efficiently with this pure Python vector database featuring Int8 quantization |
| 49 | Jeroflo88/Self-Corrective-RAG | 0 | Python | 2026-10-06 | 🔍 Enhance your searches with Self-Corrective RAG, a system that optimizes queries and evaluates document relevance using |
| 50 | rao-studios/Sewn | 0 | Swift | 2026-10-06 | The LLM API inference layer for MaryOS built on hummingbird. Can be used for independent clients or other solutions. |
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.