txtai: review, pricing, security and alternatives

What txtai does

txtai belongs to the data and rag family: agents that query databases and company documents to answer questions or produce analyses. On our grid it ranks #5 of the 15 projects of this family listed in the directory.

Unlike a ready-made agent, a framework provides the parts to build one: tool calling, step sequencing, memory, coordination of several agents. It is aimed at teams that want a custom agent.

You use it from: developer SDK and API. Usable models: local models (Ollama, llama.cpp, vLLM…) and any OpenAI-compatible model. It can run on your own machine or server.

Who is txtai for?

It is for teams that want an AI to answer from their own documents or databases. Typical tasks people give it:

• query internal documentation in plain language
• ask a database questions without SQL
• index and summarise large file collections

It is a good candidate if your data must stay on your machines and you want the option of a local model, with no API fees.

Access and human control

A framework has no access of its own: the tools you plug in define what the agent can do. Start with read-only tools.

We could not establish whether it asks for human approval before sensitive actions: test it first on an unimportant account or folder.

txtai pricing

The code is free, under the Apache-2.0 licence.

Getting started with txtai

1. Install it: the project ships as a Python package (install with pip or uv). The exact command is in the repository README.
2. Pick the model: an API key from a provider, or a local model if your machine has enough graphics memory (the VRAM calculator tells you).
3. Start with the minimal example from the docs, then add one tool at a time and check what the agent does with it.
4. Give it a short, checkable task, review the result and its action log, then raise the difficulty step by step.

Security: risk level

Give it read-only access and check generated queries before any data change.

Three habits: least privilege (minimal rights, dedicated keys), human approval for irreversible actions, a sandbox for code execution. The AI agent security check reviews your setup in a few minutes.

Project activity and releases

Created on August 9, 2020, the neuml/txtai repository has 13,032 stars, 951 forks and 10 open issues, with 2,269 commits in total. It received changes this month.

Over the last 52 weeks: 497 commits, an average of 9.6 per week.

68 releases in total; 15 in the last twelve months. Latest release: v9.14.0, on October 6, 2026.

txtai vs other data and rag

GitHub stars of the best-rated open-source projects in the data and rag family. Stars measure attention, not quality: a heavily promoted project collects them fast, a specialised tool will have few.

txtai and other data and rag at a glance

The 7 best-ranked agents in the same family, 7 of them open source. The score out of 100 only applies to open-source projects; for proprietary services we show the published entry price. A dash marks information the documentation does not state.

How we rated it

Score: 78/100, computed only from public, verifiable data, with no subjective testing or partnership:

• Adoption 25/40: 13,032 stars on a log scale (40 points from about 200,000).
• Activity 28/30: last commit less than a month ago, 7 releases in six months, 497 commits in a year.
• Framework 25/30: licence, default human approval, self-hosting, model choice and documentation site.

The score does not say whether the agent will succeed at your tasks: it measures how solid the project is. The full grid is on the method page.