Open source vector databases, installed and queried

Vector databases you can run yourself. The list is ordered by whether each project came up when Argusic installed it fresh, with the recording of that attempt one click away.

Tested between and . Each row shows its own test date; a project can change after that day.

81 of 84 tested projects run. 7 more waiting for a test.

In short: 55 of the 84 tested projects started as-is on a fresh machine: anything-llm, xerj, langchain4j, genkit, pinot, riot, LongMemory, and crate, and 47 more. 26 more started once a stand-in replaced a service they expect, such as a database: claude-context, ava-whatsapp-agent-course, chatWeb, mcp-server-elasticsearch, embedJs, aisearch-openai-rag-audio, shopkeeper-agent, and wikipedia-semantic-search, and 18 more. 3 could not be verified: autoflow, unbody, and orbit; the log shows where each one stopped.

Measured by Argusic on a fresh machine every time. Every number links to its evidence.

#projectverdictArgusic Scorelanguagestarstested on
1anything-llmRuns100 / 100JavaScript68,514

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

What the test found: The AnythingLLM monorepo installs and builds cleanly; the server boots on port 3001 responding to API calls; the collector boots on port 8888; all 1,119 unit tests across server (725) and collector (394) pass without errors. 20 minutes.

2xerjRuns100 / 100Rust19,394

AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search...

What the test found: XERJ v1.0.0-rc.77 built from source in 2m06s (quick profile), serving ES-compat API on :9200 with autoindex and MCP server working; test suites pass except 2 IPv6 bind failures specific to this container. 36 minutes.

3langchain4jRuns100 / 100Java13,433

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: LangChain4j project compiles and 1724 unit tests pass with Java 17 (Adoptium Temurin-17.0.21+9) and Maven wrapper 3.9.16. 32 minutes.

4genkitRuns100 / 100TypeScript6,612

Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google

What the test found: Genkit Python SDK (5692 tests pass), JS core/genkit SDK (builds, 385/389 tests pass), and genkit CLI tools (437 tests pass) are all functional. The Python SDK was verified end-to-end using a mock echo model producing correct output. Only pre-existing limitations: Node 18 crypto compatibility affects the JS ai package... 65 minutes.

5pinotRuns100 / 100Java6,178

Apache Pinot: a real-time analytics database for low-latency SQL and vector search, serving user-facing and agent-facing applications

What the test found: Built pinot-tools and dependencies (BUILD SUCCESS), ran Apache Pinot 1.7.0-SNAPSHOT batch quickstart end-to-end with controller :9000 /health OK and broker :8000 serving SQL, and ran passing unit tests (FSTBuilderTest 3/3, RangeIndexTest 1/1) under JDK 25; verified repository working tree unchanged and cluster stopped... 62 minutes.

6riotRuns100 / 100Go6,068

Go Open Source, Distributed, Simple and fastest efficient text/vector Search Engine

What the test found: Go 1.26.10 toolchain installed under /tmp/go-toolchain, riot builds and its entire test suite passes with -race (984/984), CLI installs and runs, and the README index/query and CJK demos produce the documented 'match: example' and hit results. 12 minutes.

7LongMemoryRuns100 / 100TypeScript4,584

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

What the test found: LongMemory CLI, HTTP server (port 7331), and programmatic library all function: init, status, ingest, recall, and health endpoints work with SQLite persistence. 4 minutes.

8crateRuns100 / 100Java4,456

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.

9mcp-memory-serviceRuns100 / 100Python2,140

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 v11.13.0 installed in a venv at /work/repo/.venv; 3196 of 3199 tests pass; the HTTP REST API server starts, serves /api/health (200), /api/memories (stores and lists memories), /api/search (semantic search with hash embeddings), and the dashboard at / (200). 13 minutes.

10matrixoneRuns100 / 100Go2,069

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 v1.3.0 (MySQL-compatible, Go-based HTAP database) builds from source and runs as a three-service cluster (LOG/TN/CN) accepting MySQL-protocol connections on port 6001, executing DDL and DML statements. 20 minutes.

11LLPhantRuns100 / 100PHP1,719

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

What the test found: LLPhant installed with composer, 223 unit tests pass using static PHP 8.2.23 binary. 5 minutes.

12pymilvusRuns100 / 100Python1,427

Python SDK for Milvus Vector Database

What the test found: PyMilvus SDK installed with uv, unit test suite (5255 tests) and integration-lite suite (4 tests with real Milvus Lite server) all pass. 6 minutes.

13NGTRuns100 / 100C++1,376

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

What the test found: NGT 2.8.1 builds, installs, and runs: the ngt CLI creates indices from TSV data and performs ANN searches; C++ samples for cosine, L2, and Hamming distances produce correct nearest-neighbor results; Python ctypes bindings create, insert, search, and retrieve objects successfully. 3 minutes.

14infinispanRuns100 / 100Java1,362

Infinispan is an open source data grid platform and highly scalable NoSQL cloud data store.

What the test found: Infinispan server 16.3.0-SNAPSHOT starts on 127.0.0.1:11222, responds to REST API requests for server info and cache operations, and the core module's SimpleCacheTest passes all 115 test cases. 21 minutes.

15chromem-goRuns100 / 100Go1,076

Embeddable vector database for Go with Chroma-like interface and zero third-party dependencies. In-memory with optional persistence.

What the test found: The chromem-go package builds with `go build ./...`, all 46 tests pass, and the benchmark suite completes successfully on a functional in-memory vector database with optional persistence. 3 minutes.

16FlashRankRuns100 / 100Python1,015

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more...

What the test found: FlashRank 0.2.9 installed in a Python 3.12 virtualenv; default ms-marco-TinyBERT-L-2-v2 model downloaded from HuggingFace and reranks passages with valid float scores. 1 minute.

17OpenSwarmRuns100 / 100TypeScript869

OpenSwarm, Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.

What the test found: OpenSwarm 0.24.2 builds, CLI binary runs (version, help, doctor, validate), and test suite passes ~4600+ tests across subdirectories with 41 bubblewrap-gated failures and 3 env-specific unrelated failures. 27 minutes.

18vector-db-from-scratchRuns100 / 100Rust815

Learn vector search with Rust and DataFusion; the C++/BusTub track is deprecated.

What the test found: The solution crates compile, all 61 tests pass, and the DataFusion CLI example executes real SQL queries. The starter crates contain the expected 'not yet implemented' stubs for the six-day course. 24 minutes.

19RAGLightRuns100 / 100Python672

RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now...

What the test found: RAGLight 3.4.7 is fully installed in a venv at /tmp/venv with all extras (chroma, qdrant, langfuse). The CLI, FastAPI REST API server, and all 75 unit tests (embeddings, LLM, vector store, API, document processing, scrapper, config) all pass and function correctly. The package is importable from Python under the venv. 6 minutes.

20next-plaidRuns100 / 100Rust624

NextPlaid, ColGREP: Multi-vector search, from database to coding agents.

What the test found: The Rust workspace compiles, all 1062 unit tests pass, both binaries respond to help/version, NextPlaid API serves CRUD endpoints (index create/add documents/search returning real scores), and ColGREP builds indexes and performs semantic code search with ONNX model inference. 14 minutes.

21cortexdbRuns100 / 100Go530

Local-first AI agent memory with a knowledge graph, ontology constraints, and traceable reasoning, all in one SQLite file.

What the test found: CortexDB v2.113.0 builds from source, all 25 test packages pass, and the gRPC+REST server starts on lexical mode (no API keys) serving health, info, knowledge, memory, graph, and query endpoints with no errors. 15 minutes.

22qdrant-jsRuns100 / 100TypeScript474

JavaScript/Typescript SDK for Qdrant Vector Database

What the test found: All 112 tests pass across all 4 packages (js-client-rest unit: 28, js-client-rest integration: 25, js-client-grpc unit: 42, js-client-grpc integration: 17) against Qdrant 1.19.2 running locally on port 6333. 5 minutes.

23CompartmentRuns100 / 100Python472

Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.

What the test found: Compartment v4.10.1 installs and runs in Python 3.12.3 venv; vault creates with 6664 seeded starter memories; MCP stdio server responds to initialize/tools/list/store/search/forget; test suite passes 975+ tests with 32 platform skips and 1 deselected real_launchctl test. 76 minutes.

24vectorliteRuns100 / 100Rust360

Fast, SQL powered, in-process vector search for any language with an SQLite driver

What the test found: vectorlite.so builds and loads as a SQLite extension; all 35 C++ unit tests and all 112 Python integration tests pass on Ubuntu 24.04 x86_64 with vcpkg-managed dependencies. 8 minutes.

25vicinityRuns100 / 100Python351

Lightweight Nearest Neighbors with Flexible Backends

What the test found: Package installs and runs in Python 3.12; BASIC, FAISS, PYNNDESCENT, USEARCH, and VOYAGER backends work correctly; HNSW and ANNOY backends require python3-dev to compile from source. 12 minutes.

26shodh-memoryRuns100 / 100Rust322

Local, LLM-free memory for AI agents. A single offline Rust binary, deterministic and auditable, that learns from use, forgets the irrelevant, and strengthens...

What the test found: The Shodh-Memory v0.2.0 pre-built server binary stores and recalls memories via REST API on localhost:3031, the MCP server TypeScript test suite passes 216/216, and the Python client test suite passes 106/106. 21 minutes.

27knowledge-ragRuns100 / 100Python306

Local RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file...

What the test found: knowledge-rag v4.9.0 installed from source in a Python 3.12 venv; all 779 automated tests pass; the MCP server starts and responds to initialize and tools/list MCP protocol messages over stdio. 5 minutes.

28utekeRuns100 / 100Rust291

Long-term memory for AI agents (MCP). One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Works with Claude Code, Cursor, Codex. Self-host free or use...

What the test found: Uteke v0.18.2 builds from source, stores and semantically recalls memories via CLI (remember/recall), serves HTTP API on port 18768 (health/remember/recall all 200 OK with correct JSON), and the MCP server responds to initialize, all 705 workspace tests pass with 0 failures. 14 minutes.

29fast-plaidRuns100 / 100Python286

High-Performance Engine for Multi-Vector Search

What the test found: fast-plaid 1.7.0 builds, installs from a patched wheel, and passes all 83 tests: create, search, update, delete, metadata filtering, freeze/unfreeze, single-copy storage, legacy argument compatibility, and chunk-budget verification on CPU with torch 2.7.0. 31 minutes.

30relevanceaiRuns100 / 100Python286

Home of the AI workforce - Multi-agent system, AI agents & tools

What the test found: The relevanceai SDK version 10.2.1 is installed and all 46 unit tests pass, covering client initialization, agents, tools, tasks, knowledge, and OAuth resource classes via mocked HTTP responses. 1 minute.

31radientRuns100 / 100Python280

Radient turns many data types (not just text) into vectors for similarity search, RAG, regression analysis, and more.

What the test found: Installs under virtualenv. All 5 vectorizer backends produce correct embeddings. GANN C extension compiles and searches. Workflows run. ffmpeg demux produces decodable media. accelerate() broken on modern torch/transformers. 25 minutes.

32pinecone-ts-clientRuns100 / 100TypeScript278

The official TypeScript/Node client for the Pinecone vector database

What the test found: SDK installs, builds, and passes all 1460 unit tests and 48 mocked smoke tests on Node 22.14.0. The dist/ folder contains 30 files with all expected exports (Pinecone, Index, Documents, Assistants, Inference, etc.). No errors remain. 3 minutes.

33nano-vectordbRuns100 / 100Python211

A simple, easy-to-hack Vector Database

What the test found: The nano-vectordb package installs in a local venv, all 7 tests pass, and real upsert/query/get/delete/filter/save-reload and multi-tenant persistence operations all worked in this container. 1 minute.

34chroma-goRuns100 / 100Go210

The Go client for Chroma vector database

What the test found: make build succeeds. 1975 V2 API tests pass, default_ef embedding function produces real 384-dim embeddings via ONNX Runtime, ORT and BM25 embedding function tests all pass. 20 minutes.

35Personal_External_BrainRuns100 / 100Python200

Not another ChatGPT wrapper. This is a local-first tool that turns your notes, web pages, PDFs and audio/video into a personal knowledge graph, running...

What the test found: Backend API serves 30 endpoints with seed graph data, all 131 automated tests pass, and the React frontend builds and starts. 4 minutes.

36vearchRuns96 / 100Python2,334

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.

37opencode-memRuns96 / 100TypeScript1,883

OpenCode plugin that gives coding agents persistent memory using local vector database

What the test found: npm install completes without error, TypeScript typecheck passes, bun test runs all 767 tests with 0 failures: the plugin compiles, the test suite exercises real Turso/libSQL vector search, schema migrations, embedding ONNX dtype resolution, provider configs, memory scoping, web auth/CORS, health checks, and 100+... 9 minutes.

38OpenContractsRuns96 / 100Python1,551

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.

39memory-osRuns96 / 100Python1,398

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.

40rag-apiRuns96 / 100Python928

ID-based RAG FastAPI: Integration with Langchain and PostgreSQL/pgvector

What the test found: Dependencies installed in venv, all 303 non-integration tests pass after adding OPENAI_API_KEY mock to conftest.py; 6 tests skip due to missing pandoc, 35 integration tests require Docker. 4 minutes.

41zvecRuns95 / 100C++16,274

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

What the test found: zvec v0.8.0 installed via pip prebuilt wheel on Python 3.12.3 (x86_64, Linux). Vector ANN query, FTS query, collection stats, and all core operations verified working. C++ static library (libzvec.a, 15MB) built from source. Python wheel build from source fails without python3-dev headers. 30 minutes.

42PageIndexRuns90 / 100Python40,743

📑 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.

43qdrant-clientRuns90 / 100Python1,380

Python client for Qdrant vector search engine

What the test found: Qdrant-client Python library installed; local/in-memory mode works: collection creation, point upsert, search, count, delete, and 112 tests pass. Server-dependent tests skipped due to no Qdrant server in this container. 6 minutes.

44milvusRuns60 / 100Go46,718

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.

45helix-dbRuns60 / 100Rust6,309

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.

46infinityRuns60 / 100C++4,772

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.

47SeaGOATRuns60 / 100Python1,320

local-first semantic code search engine

What the test found: SeaGOAT v1.2.0 installs via poetry, starts a local server, responds to status queries, and returns correct semantic search results for a test repository. 190 of 204 tests pass; 12 snapshot tests fail due to ONNX model processing timeout on this CPU. 30 minutes.

48arcadedbRuns60 / 100Java1,259

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.

49VectorDBBenchRuns60 / 100Python1,201

Benchmark for vector databases.

What the test found: vectordb-bench installed from source in venv, 247 of 256 unit tests pass, CLI and REST API both operable. 22 minutes.

50RaBitQ-LibraryRuns60 / 100C++298

Official library for RaBitQ vector quantization and approximate nearest-neighbor search, in C++ and Python.

What the test found: RaBitQ Library v0.4.0 Python bindings and C++ library built from source; 395/395 Python tests and 187/187 C++ tests pass natively on x86_64 with runtime AVX2/AVX-512 dispatch. 11 minutes.

51neuron-aiRuns58.6 / 100PHP2,182

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.

52cogneeRuns50 / 100Python33,462

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.

53SeekStormRuns50 / 100Rust1,939

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.

54lancedbRuns48 / 100Rust11,968

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.

55txtaiRuns47.4 / 100Python13,713

💡 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.

56claude-contextRuns with mocks92 / 100TypeScript12,716

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.

57ava-whatsapp-agent-courseRuns with mocks92 / 100Python1,682

Meet Ava, the WhatsApp Agent

What the test found: The project installs cleanly, all 17 unit tests pass, the FastAPI webhook endpoints respond correctly (GET docs 200, GET verify 200, POST status update 200, GET wrong token 403), and the Chainlit interface boots and responds on port 8000. 14 minutes.

58chatWebRuns with mocks92 / 100Python916

ChatWeb can crawl web pages, read PDF, DOCX, TXT, and extract the main content, then answer your questions based on the content, or summarize the key points.

What the test found: ChatWeb launches in both API mode (FastAPI/uvicorn on :9531) and WebUI mode (Gradio on :7860). File upload, summary generation, and Q&A endpoints all return HTTP 200 with correct JSON schema against a mock OpenAI API. The three startup modes (console/api/webui) are all functional; console mode was not interactively... 9 minutes.

59mcp-server-elasticsearchRuns with mocks92 / 100Rust735

What the test found: The crate builds, all 5 tests pass, the HTTP server answers 200 on /ping and returns isError:false for all 5 MCP tools against a local schema-correct mock Elasticsearch, and stdio mode completes the MCP initialize handshake. 11 minutes.

60embedJsRuns with mocks92 / 100TypeScript601

A NodeJS RAG framework to easily work with LLMs and embeddings

What the test found: EmbedJs monorepo installs and builds; RAG pipeline (loaders -> embeddings -> HNSWDb -> similarity search) works with mocked embeddings. 11 minutes.

61aisearch-openai-rag-audioRuns with mocks92 / 100Python568

A simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's...

What the test found: Backend server starts on port 8765, serves built frontend (HTML, JS, CSS, favicon all HTTP 200), WebSocket endpoint /realtime accepts client connections and routes to Azure OpenAI, all Python imports compile, Ruff lint passes, frontend TypeScript builds cleanly via Vite. 3 minutes.

62shopkeeper-agentRuns with mocks92 / 100Python550

📊 电商数仓智能问数 AI Agent,最适合用于系统学习 LangGraph 的实战项目:基于 LangGraph、FastAPI、Qdrant、Elasticsearch、MySQL 与 React,完整实现元数据知识库、混合检索、自然语言生成 NL2SQL 生成校验、SQL...

What the test found: With schema-correct mocks for the mandatory external services, the uvicorn-served app answers POST /api/query with a complete SSE pipeline and returns SQL aggregate result sales=10088 for '统计华北地区销售额'; uv sync installs all dependencies and the frontend pnpm build completes. 31 minutes.

63wikipedia-semantic-searchRuns with mocks92 / 100TypeScript471

Semantic Search on Wikipedia with Upstash Vector

What the test found: pnpm install and next build succeed; next start serves / with HTTP 200 and the full chat/search pipeline runs end-to-end against local schema-correct Upstash/OpenAI mocks, with retrieval context and streaming answers verified via the installed SDKs; connecting real Upstash/OpenAI credentials is the only remaining... 30 minutes.

64ai4jRuns with mocks92 / 100Java442

Java 8+ agentic SDK: unified LLM access (OpenAI/Anthropic/DashScope/Doubao/DeepSeek...),unified AI service(image/video/audio...), Tool Calling, MCP, RAG...

What the test found: All 10 modules build, install, and pass their test suites (1624+ total tests, 0 failures, 10 skipped). The CLI JAR starts and responds to --help and extension list. The docs-site Docusaurus build requires Node.js >=20 (has 18.19.1) which is a preexisting constraint. 19 minutes.

65memento-mcpRuns with mocks92 / 100TypeScript427

Memento MCP: A Knowledge Graph Memory System for LLMs

What the test found: npm install and TypeScript build succeed; 287/287 unit tests pass with mocked Neo4j; the MCP server binary starts and accepts MCP initialization but cannot connect to Neo4j (not available in this container). 6 minutes.

66prompt-cacheRuns with mocks92 / 100Go427

Cut LLM costs by up to 80% and unlock sub-millisecond responses with intelligent semantic caching.A drop-in, provider-agnostic LLM proxy written in Go with...

What the test found: PromptCache builds, all 42 tests pass across 7 packages, the server starts on port 8080 with health endpoints responding 200, and semantic caching works end-to-end against a mock OpenAI API (cache miss on first request, cache hit on second identical request). 17 minutes.

67vector-db-benchmarkRuns with mocks92 / 100Python377

Framework for benchmarking vector search engines

What the test found: All 11 parser tests pass, the run.py CLI shows help, and all 118 engine + 58 dataset configs load. The repo is ready to use with running backend servers. 3 minutes.

68vector-graph-ragRuns with mocks92 / 100Python332

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

What the test found: The full test suite (143 tests across 11 files) passes cleanly and the FastAPI server starts and responds correctly on /health. 12 minutes.

69memlayerRuns with mocks92 / 100Python309

Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.

What the test found: memlayer 0.1.8 installs from source in a venv, all 58+ symbols import cleanly, core storage (ChromaDB + NetworkX) and search (SearchService) work end-to-end, entity deduplication merges 'Dr. Watson' into 'Dr. Emma Watson', SalienceGate correctly classifies salient vs. non-salient text in both LOCAL and LIGHTWEIGHT... 16 minutes.

70vectordbzRuns with mocks92 / 100TypeScript275

A modern desktop application for exploring, managing, and analyzing vector databases

What the test found: npm ci completes successfully, Vite builds produce valid bundles, the Electron app launches on Xvfb with a visible VectorDBZ 1400x900 window connected to the Vite renderer dev server. The embedding mock server serves embedding vectors on port 3005. Integration tests require Docker containers not available in this... 30 minutes.

71skillsRuns with mocks92 / 100Python271

Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK...

What the test found: The repository builds its static skills site into public/ and passes all 16 link-rewriting unit tests with zero validation errors, and its skill-eval harness reports 30/30 (100%) when driven by a mocked claude CLI; the only unverified path is real Claude Code eval scoring. 2 minutes.

72vector-storageRuns with mocks92 / 100TypeScript249

Vector Storage is a vector database that enables semantic similarity searches on text documents in the browser's local storage. It uses OpenAI embeddings to...

What the test found: npm install completes, npx tsc and npm run lint pass, and node verify.mjs exits 0 with ALL CHECKS PASSED covering add/search/filter/hits/persistence/LRU and the OpenAI embedding fetch path against a local mock server. 10 minutes.

73k8ssandra-operatorRuns with mocks92 / 100Go244

The Kubernetes operator for K8ssandra

What the test found: Go 1.26.10 installed, project builds, 25 pkg packages pass tests, all API validation tests pass, secrets-webhook unit tests pass, yq tests pass. Multi-cluster controller tests (k8ssandra, control, replication) fail intermittently due to envtest resource contention in container environment, they require 3-4 concurrent... 38 minutes.

74RelaMindRuns with mocks92 / 100Java213

基于 AI 的个人成长轨迹分析系统,通过记录生活、回顾历史、分析模式帮助用户更好地理解自己,实现持续成长。包含智能路由、RAG 检索、自主任务智能体等功能。

What the test found: Spring Boot backend compiles and passes 17/18 tests; Vue.js frontend builds; 1 test skipped for PostgreSQL/pgvector dependency. 35 minutes.

75MineContextRuns with mocks86 / 100Python5,552

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.

76servietteRuns with mocks61 / 100Python58,685

A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway.

What the test found: All 394 non-integration tests pass under the mock license patch, including DuckDB-backed end-to-end indexer tests with persistence, the combined serviette up server+indexer, and the FastAPI server. 86 minutes.

77deep-searcherRuns with mocks56 / 100Python8,405

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.

78automemRuns with mocks56 / 100Python832

Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.

What the test found: In this container: make install succeeds, python app.py boots and serves /health, the unit suite passes 664 tests, and authenticated store/recall/query/delete flows work over HTTP against the schema-compatible in-memory mock. 15 minutes.

79python-sdkRuns with mocks56 / 100Python456

Official Python SDK for the Pinecone vector database

What the test found: The Pinecone Python SDK builds and imports (v10.0.0), its full unit suite passes (9623 passed, 13 skipped), and the sync and async quickstart document flows plus the gRPC upsert/query path all return correct results against schema-correct local mocks. 36 minutes.

80redis-vl-pythonRuns with mocks54 / 100Python436

Redis Vector Library. The AI-native Python client for Redis.

What the test found: redisvl 0.27.2 installed in a venv with all unit tests passing (1619/27skipped), CLI responding correctly, and optional dependencies for MCP, HF, GoogleGenAI, and AzureOpenAI vectorizers resolved. 19 minutes.

81LEANNRuns with mocks44.8 / 100Python13,808

[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.

82autoflowCould not verify25 / 100TypeScript2,984

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.

83unbodyCould not verify20 / 100TypeScript525

The Supabase of AI era. A modular, open-source backend for building AI-native software, designed for knowledge, not static data.

What the test found: could not be verified; the log shows where it stopped. 1 minute.

84orbitCould not verify10 / 100Python366

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.

-databendNot yet tested-Rust9,504-
-dingoNot yet tested-Java1,706-
-iai-personal-memory-engineNot yet tested-Python925-
-chromadb-adminNot yet tested-TypeScript282-
-ahnlichNot yet tested-Rust249-
-satoriDBNot yet tested-Rust245-
-corpusosNot yet tested-Python207-

runs installed and started with its real dependencies. runs with mocks started after stand-ins replaced external services such as a database or a third-party API. could not verify neither the standard agent nor the stronger one got it running within the time limit; the log shows where it stopped.

How we tested

On this list as of the latest test: 55 projects ran as-is, 26 with mocks, 3 could not be verified, 7 still waiting. Languages tested: C++, Go, Java, JavaScript, PHP, Python, Rust, TypeScript. Every attempt used a clean single-use machine, the subject at a pinned version, and a 90-minute limit for standard projects; the complete procedure is on the methodology page.

Frequently asked questions (FAQs)

How is this list ranked?

By measurement, not opinion: projects Argusic installed and launched on a fresh machine come first, then those that ran with mocks in place of external services, then those it could not verify. Ties go to the Argusic Score, then how popular it is on its own source.

Why are some projects unranked?

7 projects are still waiting for a test or for a finished attempt. They are listed without a rank until Argusic has measured them.

Where is the evidence?

Every row links to the project's Argusic page, where each run has a full log and a terminal recording stored with a sha256 fingerprint. The same pages exist for every one of the tested projects, on this list or not.

More lists in this category

All lists: Best. All tested projects: subjects.