Chat with your own documents: AnythingLLM, from Mintplex Labs, wraps retrieval-augmented generation (RAG) in an open-source application anyone can run. You organize content into workspaces, each an isolated namespace with its own documents, vector embeddings, chat history, and settings, so one instance can hold several separate knowledge bases. Upload PDFs, DOCX, TXT, and other formats, or scrape web pages; the built-in collector parses and chunks them into a vector database (LanceDB by default, with Pinecone, Chroma, Qdrant, and others supported). Answers cite their source documents. It works with both cloud LLMs (OpenAI, Anthropic, Gemini) and local ones via Ollama or LM Studio, and the embedding model is separately configurable. Beyond RAG chat, it includes AI agents that can browse the web and run tools, an embeddable chat widget for your website, a developer API, and multi-user mode with admin, manager, and default roles plus per-workspace access control. Context assembly is smarter than naive RAG: pinned documents, attached files, vector search hits, and recent chat history are combined under a token budget so the model's context window is filled efficiently, and each workspace supports multiple independent conversation threads against the same knowledge base. Because the embedding model, vector store, and chat LLM are all independently swappable, you can move between providers without re-ingesting a single document. The stack is Node.js with a React frontend, MIT-licensed.

Formerly known as Danswer and now backed by over 31,000 GitHub stars with 253 releases, Onyx delivers a production-ready AI platform that turns any LLM into a context-aware enterprise assistant connected to your organization's actual knowledge. The agentic RAG pipeline combines BM-25 keyword search with prefix-aware embedding models in a hybrid index, then deploys AI agents to retrieve, verify, and synthesize answers with source citations from over 40 connected workplace tools including Google Drive, Confluence, Slack, Notion, Jira, SharePoint, GitHub, and Linear. Custom AI assistants with configurable prompts, backing knowledge sets, and document-level access control enable specialized agents for engineering, sales, support, and research workflows. The platform supports every major LLM provider — Anthropic Claude, OpenAI, Google Gemini, plus self-hosted options via Ollama, LiteLLM, and vLLM for fully air-gapped deployments. Beyond chat, Onyx provides web search with Serper, Google PSE, Brave, and SearXNG integration, an in-house web crawler, code execution, file creation, and multi-step deep research with report generation. Enterprise features include SSO via Google OAuth, OIDC, or SAML with SCIM provisioning, role-based access control, usage analytics by team and agent, query history auditing, PII removal through custom code hooks, and full whitelabeling. Deploy via Docker Compose on any infrastructure. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed (Community Edition).

Hister is a private search engine for everything you have read or saved, indexing the full text of visited pages, local files, and imported browser history so one query finds the page you only half remember. Firefox and Chrome extensions capture each page as you browse, while a crawler and importers for browser history and bookmarks backfill earlier reading. Watched directories add local files to the same collection. Queries accept field filters, quoted phrases, wildcards, negation, date ranges, and aliases, with a readable stored preview beside each result. Opt-in semantic search matches documents by meaning through an Ollama, llama.cpp, or OpenAI-compatible embeddings endpoint. The same index answers in the browser, a terminal interface, the command line, an HTTP API, and an MCP server for AI assistants. Multi-user mode gives each person separate documents, rules, and access tokens, with password or OAuth sign-in, and public mode lets anonymous visitors search a curated index. Rebuild a research trail, recover a half-remembered article, or share one searchable knowledge base, with no telemetry. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Perplexity's answer-engine experience, self-hostable and open-source: Morphic searches the web and writes cited answers. Instead of returning a list of links, it searches the web, reads the sources, and generates a complete answer with inline numbered citations. The generative UI streams rich components, source cards with thumbnails, image grids, syntax-highlighted code, and LaTeX math, rather than plain markdown. Quick mode answers fast; Adaptive mode runs deeper multi-step research. Search backends are pluggable: the Docker Compose bundle ships with a private SearXNG instance so no search API key is required, and Tavily, Brave, and Exa are supported alternatives. LLM providers include OpenAI, Anthropic, Google, Ollama, and any OpenAI-compatible endpoint, with per-mode model mapping - fast, cheap models for quick searches, stronger models for adaptive research, tuning the cost-quality trade-off per query type. An inspector panel exposes tool execution during multi-step research, and AI-suggested follow-up questions keep an investigation moving. Chat history persists in PostgreSQL, results are shareable by URL, file uploads feed context into queries, and optional Supabase authentication adds multi-user or guest access. Because the default search path is your private SearXNG instance, research topics never hit a commercial search API - and with local Ollama models the marginal cost of a query approaches zero. Built with Next.js, TypeScript, and the Vercel AI SDK under Apache 2.0.

With 26,600 GitHub stars, 50 contributing companies including AWS, Google Cloud, Oracle, and Ericsson, and governance under the Linux Foundation ensuring the BSD 3-Clause license can never be revoked by a single entity, Valkey delivers a truly open-source Redis-compatible key-value datastore that reached 1.19 million requests per second in version 8.0 through redesigned asynchronous I/O threading across CPU cores while maintaining single-threaded data structure operations for predictability. Native data structures include strings, hashes, lists, sets, sorted sets, bitmaps, HyperLogLogs, streams, and geo-spatial indices with JSON support through modules. Valkey 9.0 shipped full-text search and aggregation via Valkey Search, enabling tag queries, numeric filtering, and text matching directly within the datastore without external search engines. Cluster mode provides horizontal scaling with automatic sharding, replication for high availability, and per-slot metrics for granular monitoring. Lua scripting enables complex atomic operations, while the module plugin system extends the server with custom commands and data types including probabilistic Bloom filters. Client libraries for Python, Java, Go, Node.js, and PHP maintain full Redis OSS protocol compatibility — existing Redis applications work without code changes. Deploy as a standalone daemon or in clustered mode with Docker, supporting persistent and ephemeral workloads on any Linux host. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD 3-Clause licensed.

With over 45,000 GitHub stars and 100 million Docker pulls, Milvus is the most widely adopted open-source vector database, powering production AI systems at NVIDIA, Salesforce, eBay, Airbnb, and DoorDash. The distributed architecture separates compute and storage with stateless microservices on Kubernetes, horizontally scaling query nodes for read-heavy workloads and data nodes for write-heavy ingestion independently. Milvus 3.0 introduces lake-native retrieval that builds and serves indexes directly over vector data in object storage and open formats including Parquet, Lance, Iceberg, and Vortex without maintaining separate copies. Native hybrid search unifies lexical BM25 full-text retrieval and semantic vector search in a single engine with metadata filtering, eliminating the need for separate search infrastructure. Hardware-accelerated ANN indexing supports IVF, HNSW, DiskANN, and GPU-based indexes with BitQ 1-bit quantization cutting memory usage by 72 percent. SDKs for Python, Go, Node.js, and Java provide programmatic access, while Milvus Lite offers lightweight embedding for local development via pip install. Server-side aggregation, sorting, faceted search, StructArray for nested document structures, and ColBERT multi-vector scoring move ranking and result processing into the engine. The Path Index enables 100x faster JSON filtering with support for 100,000+ collections per cluster for multi-tenant deployments. Self-hosting deploys via Docker Standalone or Kubernetes with Helm charts using S3-compatible, GCS, or Azure Blob storage backends. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

A self-hosted "second brain": Khoj indexes your own files and answers questions from them, parsing Markdown (whole Obsidian vaults included), org-mode, PDF, Word, plain text, Notion pages, GitHub repositories, and images described by a vision model, then embedding everything with sentence-transformers into a vector index for semantic search and RAG with cited sources. Any LLM backend works: local models like Llama, Qwen, or Mistral via Ollama, or cloud models like GPT, Claude, and Gemini. You can build custom agents, each with its own persona, scoped knowledge base, chat model, and tools such as web search and code execution. Scheduled automations run recurring research and deliver newsletters or notifications to your inbox, and research mode performs multi-hop web searches with inline citations. Access it from a browser, the Obsidian plugin, Emacs, desktop, or WhatsApp - all clients connect to the same self-hosted instance, making Khoj one of the few AI assistants Emacs users can point at decades of org files. Semantic search means recall works without exact keywords: "that paper about forecasting with transformers" surfaces the right PDF even when you cannot remember its title. Switching LLM backends never requires re-indexing your documents, and with a local model via Ollama, even inference stays on hardware you control - journals, research, and private notes are never sent anywhere. Python/FastAPI stack, AGPL-licensed, with PostgreSQL storage.

Memory that survives the session: Hindsight extracts facts, entities, and timestamps from everything an AI agent retains, then lets the agent search or reason over it later. Adding it to an existing LLM client takes a two-line wrapper, and more than 60 integrations cover Claude Code, Cursor, LangGraph, CrewAI, and n8n. Every bank also exposes its own MCP endpoint. Retain sends text, images, or files through an LLM that extracts facts, timestamps, entities, and relationships. Recall runs semantic, keyword, graph, and temporal searches in parallel, merges them with reciprocal rank fusion, reranks with a cross-encoder, and trims to a token budget. Reflect reasons across memories for questions that need synthesis, shaped by per-bank skepticism, literalism, and empathy traits. In the background, related facts consolidate into observations that keep exact quotes and proof counts and are refined, never silently overwritten. Mental models and wiki-style knowledge pages hold standing answers that rewrite themselves as the bank learns. Each user, agent, or project gets an isolated bank with no cross-bank leakage, and Memory Defense redacts or blocks secrets and PII against 45 patterns. The Control Plane adds a Recall Analyzer with traces, a memory constellation graph, and a knowledge page editor. Extraction and reasoning can run on 25+ LLM providers, including local Ollama and llama.cpp. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With over 70,000 GitHub stars and billions of documents indexed across enterprises like Uber, Netflix, and Wikipedia, Elasticsearch is the world's most deployed search engine, powering everything from application search to security analytics and AI-driven retrieval. Built on Apache Lucene, its inverted index architecture delivers sub-second full-text search across terabytes of data with BM25 relevance scoring, configurable analyzers for 30+ languages, and fuzzy matching for typo tolerance. The kNN vector search API uses the HNSW algorithm for approximate nearest neighbor queries on dense and sparse embeddings up to 4,096 dimensions, while reciprocal rank fusion enables hybrid search that combines lexical and semantic signals in a single query. Elasticsearch's aggregation framework supports metric, bucket, and pipeline aggregations for real-time analytics directly on indexed data without separate OLAP infrastructure. The cluster distributes data across shards with automatic rebalancing, replica allocation, and cross-cluster search for multi-datacenter deployments. Kibana provides the visualization layer with dashboards, Lens visual editor, Canvas for pixel-perfect reports, and Discover for ad-hoc log exploration. Ingest pipelines with processors like grok, dissect, GeoIP enrichment, and inference handle data transformation at index time, and ES|QL brings pipe-based query syntax with joins and columnar processing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL v3 licensed.

Used by over 46,800 companies including Forbes, Toyota, and Cisco, MongoDB stores data as flexible JSON-like BSON documents that eliminate rigid table schemas and support rapid application iteration. Its aggregation pipeline processes complex data transformations through composable stages including $match, $group, $lookup for joins, $unwind, and $project, operating directly within the database engine. Horizontal scaling is built in through automatic sharding, which distributes data across nodes using range-based, hashed, or zone-based shard keys, while replica sets provide automatic failover with configurable read preferences and write concerns. Multi-document ACID transactions span multiple collections and shards since version 4.0, enabling relational-style consistency guarantees within a document model. Starting with Community Edition 8.2, native full-text search and vector search are available directly in the database through $search and $vectorSearch aggregation stages, supporting RAG patterns, semantic retrieval, and hybrid search without external dependencies. Change streams provide real-time event-driven data access by tailing the oplog through the aggregation framework, enabling reactive architectures without polling. Time series collections offer optimized columnar storage for IoT sensor data and metrics with automatic bucketing and compression. Official drivers exist for Python, Node.js, Java, Go, C#, C++, Rust, Swift, and PHP, with MongoDB Compass providing a GUI for visual schema exploration and query building. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. SSPL v1 licensed.

Product catalogs, help centers, and document archives all fail the same way: visitors type a few words, get the wrong results, and leave. Apache Solr is the search platform behind fast, relevant answers, returning ranked matches with faceted filters, highlighted snippets, spell suggestions, and geospatial distance in a single query. Index documents through HTTP updates or data import handlers, shape fields in the schema, and watch changes appear through near-real-time indexing without rebuilding the corpus. SolrCloud turns one index into a distributed collection: shards split large corpora across nodes, replicas copy each shard for failover and query load, and ZooKeeper coordinates configuration so every node serves the same schema. Dense vector fields store embeddings beside your text, and the KNN parser retrieves nearest neighbors through HNSW graphs, so semantic search runs in the same engine as keyword search instead of a second system. A combined query handler merges keyword and vector rankings with reciprocal rank fusion, and an enrichment processor can call language models at index time to tag or summarize documents as they arrive. Streaming expressions add analytics over results, from rollups and percentiles to joins across collections, while JWT authentication and authorization rules protect the admin console and APIs. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Your documents change every day, and your RAG answers should change with them: Serviette keeps a chat and REST API continuously in sync with the files you point it at, no re-indexing jobs to remember. Point it at a local folder, Google Drive, S3 or MinIO bucket, SharePoint library, or even an FTP or WebDAV share, and edits, additions, and deletions flow into the index in real time. One YAML file, or the interactive wizard, chooses among eight vector databases, from embedded DuckDB with zero setup to pgvector, Qdrant, Milvus, Chroma, Weaviate, Pinecone, or MongoDB Atlas. Text, Office files, PDFs with tables, and scanned images are parsed and answerable by default, with audio and video joining when you add the keys. Embeddings can run fully locally with no credentials, and keyless answers simply quote the retrieved passages with their sources. The indexer and the stateless server scale independently, the server shards across workers with one config line, and both a ChatGPT-style web chat and a versioned /api/v1 retrieval API answer on the same port. A free license key from Pathway activates the engine, and benchmarks cover corpora up to 50 GB of text. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

CRW gives your apps and AI agents a private web data API that scrapes pages, crawls sites, maps links, and searches the web without sending every request to a hosted scraping service. Post a URL to the scrape endpoint and receive clean Markdown, HTML, screenshots, links, or structured JSON shaped by a schema you supply. Start a crawl when a whole section matters, then poll for progress while CRW walks pages asynchronously and returns the collected content in one job. Use map first to discover the URLs on a site before spending effort extracting pages you do not need. Connect agent tools through the MCP endpoint so assistants can search, scrape, and crawl from the same self-hosted service your applications call. Add browser rendering when JavaScript-heavy pages hide content from a plain HTTP fetch, and keep simpler pages on the fast lightweight path. Protect a public deployment with Bearer token authentication, your own reverse proxy, logging, and rate limits, or keep the service inside a private network for internal tools. Run one Docker container for the core API, or use the Compose stack when you want bundled search and rendering sidecars beside it. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Unify fragmented corporate knowledge across chat channels, documents, and cloud drives with PipesHub, an open-source workplace context platform providing permission-aware search and verifiable answers for teams and autonomous agents. Employees can query enterprise knowledge bases through a conversational interface that retrieves relevant information across Google Workspace, Microsoft 365, Slack, Confluence, Jira, and GitHub while strictly respecting individual user access permissions. Knowledge workers can verify every answer through clickable citation blocks that trace claims directly back to source documents, spreadsheet rows, or chat messages. Teams can assemble custom AI agents visually using a drag-and-drop builder, combining retrieval collections with interactive toolsets to automate multi-step operations like drafting customer responses or creating issue tickets. Autonomous agents connect via Model Context Protocol to inspect shared company knowledge and perform external actions across connected SaaS tools. Organizations can index scanned PDFs, slide decks, markdown pages, and spreadsheets with OCR and document parsing, maintaining synchronized records through automated schedules. Administrators can inspect synchronized records, monitor query history, and manage connector credentials across all integrated business applications. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache License 2.0 licensed.

With nearly 12,000 GitHub stars and a lineage tracing back to Sphinx Search, Manticore Search is the C++ search database that delivers the full-text, vector, and hybrid search capabilities of Elasticsearch at a fraction of the resource cost — starting in under a second and consuming just 40MB RAM for an empty instance. The SQL-first interface speaks the MySQL wire protocol, meaning mysql client, MySQL Workbench, and any MySQL-compatible driver connects natively without adapters, while the HTTP JSON API provides RESTful access for modern applications. Over 20 full-text operators handle proximity search, quorum matching, field-start and field-end constraints, MAYBE operators, and regex patterns, backed by stemming, lemmatization, stopwords, synonyms, wordforms, and advanced morphology in 70+ languages. Vector search with HNSW indexing enables semantic similarity queries, and hybrid mode combines keyword relevance with vector distance in a single ranked result set using a cost-based query optimizer. Real-time indexing delivers sub-second document availability after insert, sharded tables distribute data across nodes, and Galera-based synchronous replication ensures high availability. Conversational search via CREATE CHAT MODEL and CALL CHAT integrates LLM-backed responses with KNN retrieval and conversation history directly inside the database. Client libraries ship for PHP, Python, JavaScript, TypeScript, Java, Go, Rust, and Elixir. Columnar storage via the Manticore Columnar Library handles analytical workloads on large datasets. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPLv3 licensed.

Processing billions of operations per second across companies like Twitter, GitHub, Snapchat, and Stack Overflow, Redis is the world's fastest and most widely deployed in-memory data store. Redis 8 unifies previously separate modules into a single distribution: RediSearch for full-text indexing with BM25 scoring and vector similarity search via HNSW and FLAT algorithms, RedisJSON for native JSON document storage with JSONPath queries, RedisTimeSeries for timestamped data with configurable downsampling compaction rules, and RedisBloom for probabilistic data structures including Bloom filters, cuckoo filters, count-min sketches, top-k, and t-digest. The core engine provides strings, lists, sets, sorted sets, hashes, streams, HyperLogLog, bitmaps, bitfields, geospatial indexes, and the new array data structure introduced in Redis 8.8. Pub/Sub delivers lightweight real-time messaging between publishers and subscribers, while Streams provide an append-only log with consumer groups for event sourcing and complex consumption patterns. Redis Cluster distributes data across nodes with automatic sharding using 16,384 hash slots, and Sentinel provides high availability with automatic failover monitoring. Lua scripting and Redis Functions enable server-side computation, and ACL-based security provides granular per-command, per-key access control. Official clients exist for Python, Node.js, Java, Go, .NET, Rust, and PHP. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPLv3 licensed.

OpenSearch is a search and analytics platforms, powering full-text search, log analytics, observability, and AI-powered vector retrieval at petabyte scale. The distributed engine provides BM25 full-text search alongside k-NN vector search using NMSLIB, Faiss, and Lucene libraries, enabling semantic search, hybrid search combining keyword and vector scoring through normalization processors, neural sparse search, and retrieval-augmented generation workflows with built-in ML Commons for model hosting. OpenSearch Dashboards delivers interactive visualization with Discover for log exploration, custom dashboards, alerting, anomaly detection using Random Cut Forest algorithms, and Security Analytics with detection rules mapped to MITRE ATT&CK. Native Prometheus integration with full PromQL support unifies metrics alongside logs and traces in a single observability interface, while Data Prepper handles telemetry ingestion from OpenTelemetry collectors, Fluent Bit, and Logstash-compatible pipelines. SQL and Piped Processing Language queries with a visual PPL builder enable analysts to query data without learning the native DSL. Index State Management automates index lifecycle with rollover, shrink, and delete policies, while cross-cluster replication and searchable snapshots on S3-compatible storage provide disaster recovery. Scoped API keys, field-level security, document-level security, and audit logging deliver enterprise-grade access control. Docker Compose deploys multi-node clusters alongside the Kubernetes operator for orchestrated production environments. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

With over 29,000 GitHub stars and deep integrations into LangChain, LlamaIndex, and CrewAI, Chroma has become the default vector database for developers building retrieval-augmented generation pipelines and AI agent memory systems. Its core API consists of just four functions — create, add, query, and delete — making it the fastest path from zero to semantic search, while the underlying Rust engine handles tokenization, embedding, HNSW indexing, and similarity scoring automatically. Chroma supports dense vector search via HNSW with configurable distance metrics including L2, cosine similarity, and inner product, sparse vector search using SPLADE, full-text BM25 keyword search, and regex matching, all combinable in hybrid queries through a single unified interface. Metadata filtering at query time uses MongoDB-style operators including $eq, $ne, $gt, $lt, $in, and logical combinators $and and $or, enabling precise result scoping without post-processing. The multimodal pipeline powered by OpenCLIP embeds text and images into a shared vector space, allowing cross-modal retrieval where text queries return relevant images and vice versa. Deployment options range from embedded mode via PersistentClient for notebooks and prototypes, to client-server mode with Docker for production, to Chroma Cloud for serverless scalability. Official Python and JavaScript SDKs provide identical APIs, and embedding function integrations support OpenAI, Cohere, Hugging Face, Google, Ollama, and custom models. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.