# dust-tt/dust

Custom AI agent platform to speed up your work.

Repository: https://github.com/dust-tt/dust
Canonical: https://ross.abutalabs.com/products/dust-tt-dust
Homepage: https://dust.tt
Language: TypeScript
License: MIT
License Family: permissive
Topics: large-language-models, rust, agents, llm
Last push: 2026-08-26T18:53:20+00:00

## Health v2 (maintenance only)
Score: 99/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 100
- inputs: {"age_days": 1475, "days_push": 7, "days_rel": 15, "gap_med": 0.0, "n_releases_24m": 53}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1442, forks 335 (observed 2026-08-28T04:04:44.747886+00:00)

## What it is
Dust is an open-source platform for building, deploying, and managing custom AI agents powered by large language models. It combines a web application with backend services so teams can create assistants that connect to company data and tools.

## Use cases
- build custom ai agents for my team
- create an assistant connected to company knowledge
- deploy an llm chatbot for internal use
- platform to build and manage ai assistants
- self-host an agent platform with rag over company docs
- automate work tasks with llm agents

## When to choose
- you want a production-ready platform for building custom AI assistants
- you need agents grounded in company data with tool integrations
- you prefer an open-source, self-hostable alternative to closed agent platforms

## When to avoid
- you only need a simple single-purpose chatbot with minimal setup
- you want a lightweight library to embed agents in your own app rather than a full platform
- you cannot operate the required backend infrastructure

## Facets
- artifact type: service
- maturity: active
- function: agent-framework, llm-inference, chatbot, rag
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: self-hosted, rust
- tags: ai-agents, llm-platform, assistant, enterprise, open-source, web-server, docker, typescript

## Member repositories
- dust-tt/dust (main) score 99

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:44.747886+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 2026-08-30T04:36:24.102875+00:00, confidence not recorded.
  - readme: https://github.com/dust-tt/dust (fetched 2026-08-28T04:04:44.747886+00:00, sha 332b604fbd82)
  - homepage: https://dust.tt (fetched 2026-08-29T11:46:52.166859+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.