# LAION-AI/Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Repository: https://github.com/LAION-AI/Open-Assistant
Canonical: https://ross.abutalabs.com/products/open-assistant
Homepage: https://open-assistant.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: chatgpt, language-model, rlhf, ai, assistant, discord-bot, machine-learning, nextjs, python
Last push: 2024-08-17T01:55:35+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 97
- inputs: {"age_days": 1359, "days_push": 747, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 37408, forks 3280 (observed 2026-08-28T04:12:01.414656+00:00)

## What it is
OpenAssistant is an open-source chat-based assistant that understands tasks, interacts with third-party systems, and retrieves information dynamically. It also produced the oasst1/oasst2 human-generated RLHF training datasets published on Hugging Face.

## Use cases
- build a chat-based AI assistant
- train a language model with RLHF data
- collect human-written conversation data for fine-tuning
- self-host an open ChatGPT alternative
- run a chatbot as a Discord bot
- fine-tune an LLM on crowdsourced instruction data

## When to choose
- you want the oasst1/oasst2 datasets for LLM training
- you want to study a full open-source assistant architecture (backend, frontend, data pipeline)
- you need a reference implementation of RLHF data collection

## When to avoid
- you need an actively maintained assistant - the project is completed and archived
- you want production LLM inference or a modern chat UI today
- you need ongoing support or new features

## Facets
- artifact type: application
- maturity: abandoned
- function: chatbot, llm-training, rag, machine-learning
- domain: large-language-models, chatbots, artificial-intelligence, machine-learning, reinforcement-learning
- platform: python, self-hosted
- tags: rlhf, chat-assistant, human-feedback, oasst-dataset, discord-bot, nextjs, completed-project, web-server, docker

## Member repositories
- LAION-AI/Open-Assistant (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:01.414656+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:25:38.458809+00:00, confidence not recorded.
  - readme: https://github.com/LAION-AI/Open-Assistant (fetched 2026-08-28T04:12:01.414656+00:00, sha 803cbf0484a5)
- Data as of 2026-08-30T08:39:29.467469+00:00.