# langchain-ai/open-canvas

📃 A better UX for chat, writing content, and coding with LLMs.

Repository: https://github.com/langchain-ai/open-canvas
Canonical: https://ross.abutalabs.com/products/open-canvas
Homepage: https://opencanvas.langchain.com/
Language: TypeScript
License: MIT
License Family: permissive
Archived: true
Last push: 2026-02-25T06:31:51+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 69, release rhythm 35, longevity 49
- inputs: {"age_days": 699, "days_push": 189, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5490, forks 872 (observed 2026-08-28T04:09:19.799571+00:00)

## What it is
Open Canvas is an open-source web application for collaborating with LLM agents to write documents and code, inspired by OpenAI's Canvas. It features a built-in reflection agent with shared memory, artifact versioning, and side-by-side markdown/code editing.

## Use cases
- collaboratively write documents with an AI agent
- generate and edit code artifacts with an LLM
- chat with an assistant that remembers my style preferences across sessions
- start from an existing document and iterate on it with AI
- use custom quick-action prompts on my current artifact
- view rendered markdown while editing it live
- self-host an open-source alternative to OpenAI Canvas

## When to choose
- you want an open-source, self-hostable Canvas-style writing/coding assistant
- you need persistent user memory and reflections across chat sessions
- you want artifact versioning and mixed markdown/code editing in one workspace
- you want to study or extend a LangGraph-based agent application

## When to avoid
- you need a fully hosted service with support - the official demo is no longer live or maintained
- you want a simple chatbot without document/artifact editing
- you cannot provide your own LLM API keys (OpenAI, Anthropic, etc.)
- you need a production-ready product rather than a reference application

## Facets
- artifact type: application
- maturity: maintenance
- function: chatbot, agent-framework, llm-inference, rag, prompt-engineering, chat-interface, ui-components
- domain: artificial-intelligence, large-language-models, chatbots, web-development, developer-tools
- platform: self-hosted
- tags: langgraph, canvas-ux, artifact-editing, memory-agents, nextjs, open-source-llm-app, ai-agents, web-server, nodejs, typescript

## Member repositories
- langchain-ai/open-canvas (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:19.799571+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 2026-08-29T17:56:21.337332+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/open-canvas (fetched 2026-08-28T04:09:19.799571+00:00, sha a1c55c6b5bd2)
  - homepage: https://opencanvas.langchain.com/ (fetched 2026-08-29T08:51:45.615243+00:00, sha 8b44b13f3e5b)
- Data as of 2026-08-30T08:39:29.467469+00:00.