Cognita is a self-hosted RAG framework for developers building applications that answer questions using their own documents. The project is archived and no longer maintained. It combines a browser interface for document Q&A with reusable components built on LangChain and LlamaIndex, under the Apache 2.0 open-source license.
The full application can run locally through Docker Compose, including its databases and web interface. Ollama handles local LLMs, while Infinity provides local embeddings and reranking. You can also use OpenAI or TrueFoundry's model gateway, which sends model requests to those services. TrueFoundry is optional, and Cognita supports Qdrant and SingleStore for vector storage.
Its main appeal is control over how documents become answers. Developers can replace parsers, models and retrieval components, then expose the application through an API. The interface lets non-technical users upload documents and ask questions using the components their team provides. It also supports comparing retrieval settings and models, and one application can host multiple RAG systems.
Data sources include local files, web pages, GitHub URLs and S3. Incremental indexing skips unchanged documents, so updates don't require processing the entire collection again. Retrieval options include similarity search, query decomposition and document reranking. Answers include references and relevant document excerpts. Audio and video parsers extend ingestion beyond text documents.
Claim this page and we'll verify you by hand. Cognita gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Cognita?Promote it
Something wrong or outdated on this page?
18.3KUpdated 24 hours agoMIT
macOS · Windows · Linux · Docker · Web#Human approval#Hybrid search#llama.cpp backend
DocsGPT is an MIT-licensed, open-source platform for teams that want AI search, assistants and agents over their own documents. It can run on your servers with local models, including fully air-gapped deployments where documents and questions stay inside your network. Answers include the source title and page number so readers can check the evidence.
29.8KUpdated 1 day ago
Docker · Web#LLM tracing#MCP#Multi-user access
FastGPT is a self-hosted AI agent builder for teams that want assistants to answer questions using company documents and carry out business workflows. Its visual editor connects model calls, knowledge retrieval and tools into applications for customer support, internal knowledge search and document review. You can run the platform on your own server through Docker or use the vendor's hosted service.
25.8KUpdated 4 months agoApache-2.0
macOS · Windows · Linux · Docker · Web#Hybrid search#llama.cpp backend#Multi-user access
39.9KUpdated 4 days agoMIT
macOS · Windows · Linux · Docker · Web#Knowledge graphs#LLM tracing#Multimodal input
22.9KUpdated 3 days agoGPL-3.0
Docker · Web#MCP#Multimodal input#RAG
3.7KUpdated 5 days ago
Docker · Web#MCP#Multi-user access#Multimodal input
Morphik Core is a self-hosted multimodal retrieval engine for developers building AI applications around visually rich documents. It searches diagrams, schematics, charts, and datasheets alongside text, so applications can retrieve information that text extraction alone can miss. You can run it on your own server, including through Docker, or use Morphik's hosted service.
kotaemon is a self-hosted document chat app for people who want to ask questions across their files and check where the answers came from. It runs in a browser on Windows, macOS or Linux, with Docker also supported. The project uses the Apache 2.0 license.
LightRAG combines knowledge graphs with vector search to answer questions across a document collection. It's a self-hosted Python framework for developers building document assistants, particularly where answers depend on relationships between facts in different files, such as legal or financial material.
MaxKB is a self-hosted AI agent platform for organizations building customer support bots, internal knowledge assistants and business automation. It combines answers grounded in company documents with workflows that can call functions and MCP tools. You can run it on your own server through Docker and use it through a browser.