Alternatives
Self-hosted alternatives to Chroma
Projects in the registry that can run on your own hardware and serve at least one of the same use cases as Chroma.
- Source
- Registry relations over fetched repository records — the evidence sits on each repository page
- Verified
- Evidence not verified
- Confidence
- High
01How this list was built
- Compared against
- Chroma
- Delivery
- Hybrid — hosted or self-hosted
- Shared use cases
- Document Q&A, Internal company search
- Selection rule
- open source, or self-hostable, and shares a use case
- Candidates found
- 23
02Alternatives
AnythingLLM
Hybrid — hosted or self-hosted
Desktop and server application that turns a document set into a chat workspace, with per-workspace embeddings, multiple model back ends and a built-in vector store.
- Repository
- Mintplex-Labs/anything-llm
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Document qa · Internal knowledge search
authentik
Hybrid — hosted or self-hosted
Identity provider with OpenID Connect, SAML and proxy-based authentication, application-level policies and a forward-auth outpost for services that have no login of their own.
- Repository
- goauthentik/authentik
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Internal knowledge search
Dify
Hybrid — hosted or self-hosted
Platform for building LLM applications: visual workflow editor, retrieval pipelines, agent tools, prompt management and an API layer. Available self-hosted or as a managed cloud service.
- Repository
- langgenius/dify
- Stars
- 153,448
- Licence
- Other
- In stacks
- 1
Shares: Internal knowledge search · Document qa
Docling
Libraries
Document conversion toolkit that parses PDF, Office and image files into structured Markdown or JSON, preserving reading order, tables and figures for downstream retrieval.
- Repository
- docling-project/docling
- Stars
- 65,519
- Licence
- MIT
- In stacks
- 4
Shares: Document qa · Internal knowledge search
Flowise
Hybrid — hosted or self-hosted
Visual builder for LLM chains and agents, with retrieval nodes, tool calling and an API or embeddable chat widget for the finished flow.
- Repository
- FlowiseAI/Flowise
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Document qa · Internal knowledge search
Keycloak
Self-hosted projects
Identity and access management server providing OpenID Connect and SAML single sign-on, user federation, groups and roles for self-hosted applications.
- Repository
- keycloak/keycloak
- Stars
- —
- Licence
- unknown
- In stacks
- 3
Shares: Internal knowledge search
Kotaemon
Self-hosted projects
Document question-answering application with a configurable retrieval pipeline, inline citations that highlight the source passage, and support for local or hosted models.
- Repository
- Cinnamon/kotaemon
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Document qa · Internal knowledge search
LangChain
Frameworks
Library for composing model calls, retrieval and tools into applications, with adapters for most providers and vector stores. A building block, not a deployable product.
- Repository
- langchain-ai/langchain
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Document qa · Internal knowledge search
Langflow
Hybrid — hosted or self-hosted
Visual environment for composing LLM pipelines and agents from components, with export to a Python application or an API endpoint.
- Repository
- langflow-ai/langflow
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Document qa · Internal knowledge search
Langfuse
Hybrid — hosted or self-hosted
Tracing, evaluation and prompt management for LLM applications, self-hostable so prompts and responses can stay inside the network being audited.
- Repository
- langfuse/langfuse
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Internal knowledge search
LibreChat
Self-hosted projects
Self-hosted multi-model chat application with authentication, per-conversation model switching, plugins, file upload and an admin configuration file. Familiar interface for staff moving off consumer tools.
- Repository
- danny-avila/LibreChat
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Document qa
LlamaIndex
Frameworks
Data framework for retrieval applications: loaders for many document types, indexing and query pipelines, and evaluation helpers for retrieval quality.
- Repository
- run-llama/llama_index
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Document qa · Internal knowledge search
LM Studio
Hybrid — hosted or self-hosted
Desktop application for downloading and running open-weight models locally, with a chat interface and a local OpenAI-compatible server. Windows, macOS and Linux.
- Repository
- none linked
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Document qa
Milvus
Hybrid — hosted or self-hosted
Distributed vector database designed for large collections, with several index types, GPU indexing options and a separated storage and compute architecture.
- Repository
- milvus-io/milvus
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Internal knowledge search · Document qa
Onyx
Hybrid — hosted or self-hosted
Open-source enterprise search and chat over company systems, with connectors to common SaaS tools, permission-aware indexing and a self-hosted deployment path.
- Repository
- onyx-dot-app/onyx
- Stars
- 31,754
- Licence
- Other
- In stacks
- 0
Shares: Internal knowledge search · Document qa
Open WebUI
Self-hosted projects
Self-hosted chat interface for local and hosted models, with user accounts, groups, document upload and built-in retrieval. Runs in Docker against Ollama, vLLM or any OpenAI-compatible endpoint.
- Repository
- open-webui/open-webui
- Stars
- 149,870
- Licence
- Other
- In stacks
- 4
Shares: Internal knowledge search · Document qa
pgvector
Libraries
PostgreSQL extension adding vector types and HNSW or IVFFlat indexes, so embeddings live in the same database and the same backup as the rest of the application data.
- Repository
- pgvector/pgvector
- Stars
- 22,735
- Licence
- Other
- In stacks
- 5
Shares: Internal knowledge search · Document qa
PostgreSQL
Self-hosted projects
Relational database used here as the system of record for documents, metadata and job queues, and — with pgvector — for embeddings as well.
- Repository
- none linked
- Stars
- —
- Licence
- unknown
- In stacks
- 3
Shares: Internal knowledge search · Document qa
Qdrant
Hybrid — hosted or self-hosted
Vector search engine written in Rust with payload filtering, hybrid search, quantisation and snapshots. Runs as a single container or a cluster, or as a managed cloud service.
- Repository
- qdrant/qdrant
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Internal knowledge search · Document qa
RAGFlow
Self-hosted projects
Retrieval engine built around deep document parsing: layout-aware chunking of PDFs, tables and scans, citation-backed answers, and a visual pipeline for building knowledge bases.
- Repository
- infiniflow/ragflow
- Stars
- —
- Licence
- unknown
- In stacks
- 1
Shares: Internal knowledge search · Document qa
Unstructured
Hybrid — hosted or self-hosted
Library and hosted API that partition documents of many formats into typed elements for indexing, with connectors to common storage systems and vector databases.
- Repository
- Unstructured-IO/unstructured
- Stars
- —
- Licence
- unknown
- In stacks
- 1
Shares: Internal knowledge search · Document qa
vLLM
Model servers
High-throughput GPU inference server using paged attention and continuous batching, with an OpenAI-compatible API. Built for many concurrent users rather than single-session use.
- Repository
- vllm-project/vllm
- Stars
- 89,956
- Licence
- Apache-2.0
- In stacks
- 7
Shares: Internal knowledge search
Weaviate
Hybrid — hosted or self-hosted
Vector database with a schema model, hybrid keyword and vector search, and optional built-in vectorisation modules. Self-hosted or managed, single-tenant or multi-tenant collections.
- Repository
- weaviate/weaviate
- Stars
- —
- Licence
- unknown
- In stacks
- 0
Shares: Internal knowledge search · Document qa
03Repository facts
| Repository | Stars | Health |
|---|---|---|
| Mintplex-Labs/anything-llm | — | Health not measuredunknown |
| goauthentik/authentik | — | Health not measuredunknown |
| langgenius/difyBuild Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack. | 153k | Maintenance 100%, Releases 80%, Contributors 50%, Issues 94%, Community 100%88 |
| docling-project/doclingGet your documents ready for gen AI | 66k | Maintenance 100%, Releases 100%, Contributors 50%, Issues 85%, Community 96%90 |
| FlowiseAI/Flowise | — | Health not measuredunknown |
| keycloak/keycloak | — | Health not measuredunknown |
| Cinnamon/kotaemon | — | Health not measuredunknown |
| langchain-ai/langchain | — | Health not measuredunknown |
| langflow-ai/langflow | — | Health not measuredunknown |
| langfuse/langfuse | — | Health not measuredunknown |
| danny-avila/LibreChat | — | Health not measuredunknown |
| run-llama/llama_index | — | Health not measuredunknown |
| milvus-io/milvus | — | Health not measuredunknown |
| onyx-dot-app/onyxOpen Source AI Platform - AI Chat with advanced features that works with every LLM | 32k | Maintenance 100%, Releases 100%, Contributors 50%, Issues 87%, Community 90%89 |
| open-webui/open-webuiUser-friendly AI Interface (Supports Ollama, OpenAI API, ...) | 150k | Maintenance 100%, Releases 80%, Contributors 50%, Issues 99%, Community 100%88 |
| pgvector/pgvectorOpen-source vector similarity search for Postgres | 23k | Maintenance 100%, Releases 30%, Contributors 50%, Issues 99%, Community 87%75 |
| qdrant/qdrant | — | Health not measuredunknown |
| infiniflow/ragflow | — | Health not measuredunknown |
| Unstructured-IO/unstructured | — | Health not measuredunknown |
| vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs | 90k | Maintenance 100%, Releases 80%, Contributors 50%, Issues 22%, Community 99%81 |
| weaviate/weaviate | — | Health not measuredunknown |
04Ask about your own case
Which alternative is right depends on how many people will use it, what the data is and what you can operate. Ask and the answer is researched for your organisation.