Data / Repositories / Vector database
Vector database repositories on GitHub: 14 ranked by stars
14 public repositories tagged Vector database are on GitHub, with 147,610 stars between them; 10 had a push in the last 30 days. Most are written in Python (4), TypeScript (4), Rust (3). The most starred: Mintplex-Labs/anything-llm (66,831), topoteretes/cognee (32,287), StarTrail-org/LEANN (13,027).
SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.
Every repository, most starred first
| Repository | What it is | Language | Stars | Forks | License | Last push | Read |
|---|---|---|---|---|---|---|---|
| Mintplex-Labs/anything-llm | Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience | JavaScript | 66,831 | 7,458 | MIT | Oct 8 | Oct 8 |
| topoteretes/cognee | Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free | Python | 32,287 | 3,363 | Apache-2.0 | Oct 14 | Oct 14 |
| StarTrail-org/LEANN | [MLsys2026 Best Paper]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device. | Python | 13,027 | 1,184 | MIT | Oct 14 | Oct 14 |
| zilliztech/claude-context | Code search MCP for Claude Code. Make entire codebase the context for any coding agent. | TypeScript | 12,616 | 943 | MIT | Jul 14 | Oct 14 |
| volcengine/MineContext | MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse） | Python | 5,535 | 415 | Apache-2.0 | May 7 | Oct 14 |
| CaviraOSS/LongMemory | Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. | TypeScript | 4,535 | 507 | Apache-2.0 | Sep 20 | Oct 14 |
| giancarloerra/SocratiCode | Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level… | TypeScript | 3,335 | 430 | AGPL-3.0 | Oct 10 | Oct 14 |
| tensorchord/pgvecto.rs | Scalable, Low-latency and Hybrid-enabled Vector Search in Postgres. Revolutionize Vector Search, not Database. | Rust | 2,190 | 86 | Apache-2.0 | Feb 26, 2025 | Oct 11 |
| doobidoo/mcp-memory-service | Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation. | Python | 2,014 | 347 | Apache-2.0 | Oct 14 | Oct 14 |
| SeekStorm/SeekStorm | SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust. | Rust | 1,918 | 71 | Apache-2.0 | Oct 10 | Oct 11 |
| NGT-labs/NGT | Nearest Neighbor Search with Neighborhood Graph and Tree for High-dimensional Data | C++ | 1,374 | 131 | Apache-2.0 | Oct 8 | Oct 11 |
| ArcadeData/arcadedb | ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB and Redis. ArcadeDB is a conceptual fork of OrientDB, the first Multi-Model DBMS.… | Java | 1,202 | 154 | Apache-2.0 | Oct 14 | Oct 14 |
| elastic/mcp-server-elasticsearch | Rust | 718 | 159 | Apache-2.0 | Oct 12 | Oct 14 | |
| tayyabimam1/awesome-ai-agent-stack | Curated 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. | TypeScript | 28 | 6 | CC-BY-4.0 | Oct 14 | Oct 14 |
By language
- Python 4
- TypeScript 4
- Rust 3
Related topics
- RAG 7
- AI agents 5
- LLM 5
- Vector search 5
- MCP 5
- AI 4
- Semantic search 4
- Agentic AI 3
- Claude Code 3
- OpenAI 3
- Memory 3
- Agent memory 2
Read from GitHub by SpecStream between October 8, 2026 and October 14, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.