Open source vector databases, installed and queried

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

What the test found: AnythingLLM installs and runs in development mode on port 3001; the test suite passes all 1119 tests across 62 suites covering server and collector modules. 17 minutes.

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

What the test found: pymilvus 3.0.2 with milvus-lite 3.2.1 runs embedded vector database operations (create, insert 1000 vectors, search, query, delete, drop) in the container. Go toolchain 1.26.6, Rust 1.84, and Conan 2.25.1 are installed. The C++ core cannot build without root for system library packages. 31 minutes.

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

What the test found: PageIndex SDK v0.2.10 installed in a venv, all 796 unit tests pass, the CLI parses correctly, and the package imports without error. 3 minutes.

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free

What the test found: cognee 1.6.1 installs, builds, starts, and runs: the local LLM-free remember/recall pipeline produces search results from ingested text, the CLI demo loads a bundled knowledge graph, the FastAPI server answers HTTP 200 on /health, and 388 unit tests pass across 5 test suites with zero failures. 33 minutes.

A lightweight, lightning-fast, in-process vector database

What the test found: Zvec v0.7.0 prebuilt wheel and from-source build both work: the Python SDK successfully creates vectors collections, inserts documents, and returns ranked similarity search results, and the 1543-test suite passes with zero failures. 58 minutes.

LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and...

What the test found: JDK 17 installed from Adoptium tarball, Maven wrapper mvnw boots correctly, full project compiles without errors, and tests across langchain4j-core (1413), langchain4j (1724), and 10+ provider/integration modules all pass with 0 failures. 36 minutes.

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

What the test found: The LongMemory Hydrograph TypeScript package builds, its CLI (init, ingest, recall, doctor) works, the library API (createMemory, ingest, recall) returns correct results, the HTTP server starts on port 7331 and responds 200 on /health, and the CI benchmark suite passes all 11 smoke-test gates with 100% retrieval... 9 minutes.

CrateDB is a distributed and scalable SQL database for storing and analyzing massive amounts of data in near real-time, even with complex queries. It is...

What the test found: CrateDB 6.5.0 compiles, installs, launches as a single-node cluster, accepts HTTP SQL queries, and returns correct query results. 27 minutes.

XERJ is the new way for AI to search data. Its autoindex capability activates agents to know your data without the token waste of grep and sed. One command...

What the test found: xerj v1.0.0-rc.77 is installed at /home/runner/.local/bin/xerj, started in 690ms on --insecure mode, successfully autoindexed /work/repo/docs (18 datasets, 9681 records, 21s wall time), and serves queries on http://127.0.0.1:9200 with ES 8.13 wire protocol. No build step needed (binary install from GitHub releases)... 3 minutes.

Distributed vector search for AI-native applications

What the test found: Vearch v3.5.9 binary (81MB) and gamma engine (.so) built from source, server starts with master+router+PS on localhost:8817/9001, REST API responds, db/create/list works, cluster health/stats/members endpoints return valid JSON, tests pass basic cluster operations but space creation times out due to PS heartbeat... 59 minutes.

AI-native HTAP database with Git-for-Data and built-in vector search, serving as the data and memory backbone for intelligent agents and applications.

What the test found: MatrixOne server built from source (mo-service, 275MB binary), launched on port 6001, accepting MySQL protocol connections, queries returning correct results including data manipulation operations. 34 minutes.

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.

What the test found: mcp-memory-service 11.13.0 installed from source via pip install -e '.[dev]', the uvicorn server starts on 127.0.0.1:9791 (HTTP) with sqlite_vec backend, health endpoint returns 200, memory CRUD operations work end to end, and the full test suite passes except for one benchmark test that fails due to hash-embedding... 20 minutes.

SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.

What the test found: Workspace builds cleanly with Rust 1.99.0, all 45 seekstorm library integration tests and all 7 seekstorm_client E2E tests pass, and the release seekstorm_server binary serves the live endpoint (HTTP 200) and completes the API key creation, index creation, document indexing, commit, and query flow returning the... 63 minutes.

LLPhant - A comprehensive PHP Generative AI Framework using OpenAI GPT 4. Inspired by Langchain

What the test found: Static PHP 8.2.32 and Composer 2.7.9 installed; all 119 Composer dependencies resolved; 223 unit tests pass in 0.3s; PHPStan static analysis passes with 0 errors; Laravel Pint style check passes on 294 files. 6 minutes.

The open document intelligence platform for builders and hackers - DMS for the agentic world

What the test found: Python dependencies installed in virtual environment, embedded PostgreSQL 18.6 provisioned and running, Django app boots with all migrations applied, and 613+ tests pass verifying admin, agents, annotations, authentication, analysis pipeline, badge system, base services, and artifact service against a real PostgreSQL... 77 minutes.

Python SDK for Milvus Vector Database

What the test found: PyMilvus SDK installed via uv sync, imports successfully, get_commit returns '290d76f', and the full unit test suite passes 5255/5255 with 3 skipped. 36 minutes.

Nearest Neighbor Search with Neighborhood Graph and Tree for High-dimensional Data

What the test found: NGT v2.8.1 C++ library, command-line tool, and four sample programs build and run successfully; the CLI creates indexes, appends data, searches with L2/cosine/hamming distance, and reports index statistics; the Python ctypes binding (ngt.base) inserts 5000 128-d vectors and returns correct nearest-neighbor results. 11 minutes.

Python client for Qdrant vector search engine

What the test found: The qdrant-client Python library installed without errors. All local-mode tests pass. When a Qdrant server v1.19.1 runs in the same session, all REST and gRPC integration tests pass. The in-memory client creates collections, upserts points, and searches vectors successfully. 32 minutes.

A 7-layer memory operating system for Hermes Agent, persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context...

What the test found: Python dependencies install cleanly in a venv, all 7 icarus module imports succeed, all 3 standalone test suites pass with 0 failures, SQLite databases are initialized with correct FTS5 schema, Icarus plugin tools produce valid output, and the Docker-compose file, worker services, and cron scripts are syntactically... 8 minutes.

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

What the test found: txtai 9.14.0 installed in venv, all core embeddings/graph/workflow/agent/cloud/vector/scoring tests pass, API responds to search/index/count endpoints with real model inference, ~470 automated tests pass across 30 test suites. 83 minutes.

HelixDB is an OLTP graph database with native vector and full-text search built in Rust on Object Storage.

What the test found: The HelixDB workspace builds and all crate test suites pass. The server binary starts and responds to HTTP POST /v2/query with HTTP 200. The CLI binary prints version 3.3.0 and help output. 51 minutes.

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

What the test found: Infinity v0.7.3 nightly (x86_64-v2) standalone server starts and accepts Thrift connections on port 23817 and HTTP on port 23820; Python SDK can create tables, insert vectors, run dense vector search queries, and return results via Polars DataFrames. 12 minutes.

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...

What the test found: ArcadeDB 26.10.1-SNAPSHOT is fully built and functional: the server starts in development mode listening on port 2480, serving the Studio web UI (HTTP 200), and the engine test suite passes ~14624 tests with 0 errors and 1 pre-existing flaky timeout test that fails under heap contention during concurrent runs. 85 minutes.

The Agentic Framework of the PHP ecosystem to build production-ready AI driven applications. Connect components (LLMs, Tools, vector DBs, memory) to agents...

What the test found: Composer install with all 145 dependencies succeeded; vendor/bin/phpunit reports 1373 tests, 5460 assertions passed, 0 failures, 0 errors, 78 skipped (external services); vendor/bin/phpstan analyse reports OK, 0 errors; bin/neuron CLI reports help with 7 commands. 33 minutes.

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

What the test found: Rust core crate lancedb compiles and passes all 73 integration tests; Python bindings install, import, and pass 1368 tests; the local (in-process) embedding store works end-to-end with vector search queries returning correct results. 84 minutes.

Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

What the test found: Install, build, typecheck, lint config, and all 35 tests pass across the monorepo. The core indexing pipeline runs end-to-end with mock providers. The MCP server starts but requires real OpenAI API key and Milvus credentials for production use. 15 minutes.

MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）

What the test found: MineContext server starts successfully, serves all 12 HTTP routes (GET and POST), initializes ChromaDB vector store and SQLite document store, and the CLI help command prints usage information. 18 minutes.

Meet Ava, the WhatsApp Agent

What the test found: uv sync installs all dependencies, 30 Python source files compile, LangGraph workflow graph compiles with 9 nodes, FastAPI WhatsApp webhook answers GET verification with HTTP 200, Chainlit chat interface starts on port 8000 and serves HTTP 200, mock API keys produce 401 when POSTing messages as expected since real... 19 minutes.

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100%...

What the test found: LEANN Python packages installed, HNSW backend with custom-built Faiss SWIG module works, CI tests pass, README HNSW examples pass with mock embeddings, DiskANN backend blocked by missing libaio system dependency. 87 minutes.

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

What the test found: DeepSearcher package installs with uv sync and pip install -e . and all 422 unit tests pass after fixing 2 test files with stale default model values. 5 minutes.

pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai

What the test found: could not be verified; the log shows where it stopped. 29 minutes.

Self-hosted AI gateway for private RAG, natural-language data access, and tool-calling agents.

What the test found: could not be verified; the log shows where it stopped. 28 minutes.