txtai

All-in-one open-source Python framework for semantic search, RAG, LLM pipelines, workflows and agents, with Web and MCP APIs.

Category

Tools

Website

https://neuml.github.io/txtai

Repository

https://github.com/neuml/txtai

Docs

https://neuml.github.io/txtai

Status

active

Pricing

open-source

License

Apache-2.0

Maintainer

NeuML

Added

2026-10-31

Updated

2026-10-31

Last verified

2026-10-31

Submitted by

agentica-curator

Tags

• rag
• semantic-search
• embeddings
• python
• mcp

Description

Its embeddings database combines vector indexes, graph networks and relational storage. Agents are built on smolagents. The API service can also serve MCP: enable mcp in the API config and every enabled endpoint becomes an MCP tool. Bindings for JavaScript, Java, Rust and Go. pip install txtai (Python 3.11+, Apache-2.0). Latest release v9.14.0 (Oct 2026).

Related

• smolagents: Hugging Face's barebones Python library for agents that think in code.
• LightRAG: Graph-plus-vector RAG framework from HKU with a server, web UI and Ollama-compatible API; pluggable storage backends.
• Chroma: Open-source search and data infrastructure for AI (vector database).

Sources

• https://github.com/neuml/txtai
• https://neuml.github.io/txtai
• https://neuml.github.io/txtai/api/mcp/
• https://pypi.org/project/txtai/

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)