Skip to content
repository radar
RAG & Memory

⚙️llmware

ACTIVE STEADY

llmware-ai/llmware · homepage ↗

Unified framework for building enterprise RAG pipelines with small, specialized models

⭐ Very popular: 15k stars, gaining about 6 a week

View on GitHub ↗

repo profile

vintage 2023 3 years old
language Python
license Apache-2.0

momentum

total stars 15k
stars added last week +6
HN peak 51 pts 2y 6mo ago
binary downloads 33 total · GitHub releases
used by 124 repos & packages
commits / week 0 steady
contributors 89
release cadence monthly
last activity 3mo ago

durability

backing community / independent independent
openness permissive
bus factor 1 solo
top-author share 100% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

since we covered it

monthly average + 213/mo (+2%/mo) · + 4k total since PR#4

why it's a big deal

  • llmware is designed to be RAG-ready, seamlessly integrating enterprise knowledge with generative AI.
  • It includes over 50 small, specialized models optimized for fact-based question-answering, classification, summarization, and extraction.
  • The framework is lightweight and efficient, allowing models to run without a GPU directly on a laptop.

under the hood

  • llmware features SLIM function call models, which are pre-quantized small models designed for rapid execution.
  • It provides advanced RAG tools, including hybrid search, metadata filters, and knowledge retrieval.
  • The built-in model catalog allows users to access and benchmark all models from a unified interface.

our take from PR#4, 2025-03-19

star history

PR#4 · 11k15k now Sep 2023Aug 2026
  1. PR#4 11k 2025-03-19
  2. now 15k + 4k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Better known than its recent output, coasting a little on attention.

-30 understory score output 13 · clout 43
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#4 2025-03-19 on the radar

    Unified framework for building enterprise RAG pipelines with small, specialized models

similar projects

compare these →
  • 📑 PageIndex

    2.4× the stars

    📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

    35k ACTIVE
  • 🧠 Mem0

    4.3× the stars

    Universal memory layer for AI Agents

    63k ACTIVE
  • 📚 Haystack

    Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

    26k ACTIVE

comments

Sign in with GitHub to add your blip on llmware.

loading comments…