# langchain-ai/openwork

Repository: https://github.com/langchain-ai/openwork
Canonical: https://ross.abutalabs.com/products/langchain-ai-openwork
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-08-26T17:56:28+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 67, longevity 16
- inputs: {"age_days": 232, "days_push": 7, "days_rel": 222, "gap_med": 1, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1448, forks 195 (observed 2026-08-28T04:04:45.477999+00:00)

## What it is
Openwork is an Electron-based desktop interface for deepagentsjs, providing a harness for building and running deep AI agents with filesystem access, planning, and subagent delegation. It supports models from Anthropic, OpenAI, and Google and can be run via npx or installed globally.

## Use cases
- run AI agents with filesystem access on my desktop
- delegate tasks to subagents with a planning harness
- chat with Claude, GPT, or Gemini models locally
- approve agent tool calls before shell execution
- build deep agents with deepagentsjs through a GUI

## When to choose
- you want a desktop GUI for deepagentsjs agents
- you need agents that can read/write files and run shell commands with approval
- you want multi-provider LLM support (Anthropic, OpenAI, Google) in one interface

## When to avoid
- you only need a headless agent library or API
- you cannot grant an agent filesystem and shell access
- you need a web-based or mobile agent interface

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, developer-tools, file-system, chat-interface
- domain: large-language-models, developer-tools, desktop-applications
- platform: cross-platform, cli
- tags: deepagentsjs, ai-agents, electron-app, filesystem-access, shell-execution, subagent-delegation, langchain, desktop, nodejs, electron

## Member repositories
- langchain-ai/openwork (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:45.477999+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 2026-08-30T04:36:04.230626+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/openwork (fetched 2026-08-28T04:04:45.477999+00:00, sha ea8c44444f2a)
  - registry_npm: https://registry.npmjs.org/openwork (fetched 2026-08-29T11:45:57.009929+00:00, sha 1434ecf24807)
- Data as of 2026-08-30T08:39:29.467469+00:00.