# neuml/txtai

> Python framework for semantic search, LLM orchestration and language model workflows. Combines vector indexes, graphs and relational databases into an embeddings database for RAG, agents and multimodal search.

- Magnitude: 4.7 out of 10 — Breakout
- Stars: 13,172 total · +8 stars measured 2026-11-09, 00:03–02:09 UTC, ≈ 63 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2020-08-09 · Last push: 2026-11-06
- GitHub: https://github.com/neuml/txtai · Homepage: https://neuml.github.io/txtai · Page: https://gitnova.dev/en/r/neuml/txtai

## Useful for

- Build semantic search over text, images and audio with an embeddings database
- Set up a RAG pipeline to answer questions over your own documentation
- Run an autonomous smolagents-based agent that uses search to solve tasks

## Why it’s here

- Star-counter measurements on 2026-11-09 (UTC), 00:03–02:09: 13164 → 13172 stars (+8). This is the change over that interval.
- Estimated end-of-day forecast: about +63 stars, using observed gains and the previous day.
- Before this, the repository barely got any stars — about 2 per day.
- Elevated gains were measured on the last 2 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Python today: #7, +56 stars.
- About 9 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 982
- Issues and pull requests: 1,515
- Watchers: 113
- Average over the last week: 25 per day
- Usual pace: 3 per day
- Stars in the last hour (measured): 4
- Latest release: v9.14.0 (2026-10-06)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-11 … 2026-11-09: 3, 7, 1, 6, 3, 4, 2, 3, 3, 1, 0, 2, 5, 3, 1, 5, 1, 2, 3, 1, 4, 7, 2, 1, 1, 1, 1, 47, 59, 8

## Magnitude by day, last 2 days

11-08 4.2, 11-09 4.7

## Spotted in now

- GitHub Trending Python today: #7, +56 stars

## Similar by description

1. **AIMIZING/mcp_docs_reader** — 0.0 · Quiet · AI agents · Python · Not enough measurements today
   A lightweight Python MCP server that loads PDFs from a local docs/ folder, chunks their text, builds a FAISS semantic index, and passes relevant passages to Claude Desktop for document-based question answering.
   Full card: https://gitnova.dev/en/r/AIMIZING/mcp_docs_reader.md
2. **milvus-io/milvus** — 1.3 · Steady · Data & analytics · Go · +2 stars measured 2026-11-09, 00:11–02:16 UTC, ≈ 7 by evening
   Milvus is a cloud-native vector database written in Go and C++ for scalable approximate nearest neighbor (ANN) search over embeddings. It is aimed at AI developers who need to store and search unstructured data such as text, images, and…
   Full card: https://gitnova.dev/en/r/milvus-io/milvus.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-09 02:18 UTC, updated every 30 minutes.