# vercel-labs/tersa

Tersa is an open source canvas for building AI workflows.

Repository: https://github.com/vercel-labs/tersa
Canonical: https://ross.abutalabs.com/products/tersa
Homepage: https://tersa-phi.vercel.app
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, aisdk, anthropic, canvas, openai
Last push: 2026-05-01T11:38:29+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 80, release rhythm 59, longevity 35
- inputs: {"age_days": 499, "days_push": 124, "days_rel": 194, "gap_med": 0, "n_releases_24m": 82}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1039, forks 174 (observed 2026-08-28T04:03:20.062745+00:00)

## What it is
Tersa is an open-source visual AI playground built as a Next.js web application where users drag, drop, and connect nodes on a canvas to build AI workflows. It supports text, image, and video models from 25+ providers via the Vercel AI SDK Gateway, with streaming responses and cost indicators.

## Use cases
- build ai workflows visually without writing code
- compare outputs from different llm providers side by side
- prototype multi-step ai pipelines on a node canvas
- test image and video generation models in one place
- estimate relative costs of different ai models
- chain prompts and models together with drag-and-drop nodes

## When to choose
- you want a visual, node-based canvas for experimenting with AI models
- you need access to many model providers through a single gateway
- you want a self-hostable alternative to closed AI workflow tools
- you prefer streaming responses and reasoning visibility while prototyping

## When to avoid
- you need production-grade workflow orchestration with scheduling and retries
- you want a headless API or CLI rather than a browser-based canvas
- you need offline operation without provider API keys
- your workflows require non-AI data transformation steps

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, chat-interface, workflow-automation, ui-components, state-management
- domain: artificial-intelligence, large-language-models, web-development, frontend, developer-tools
- platform: self-hosted, cross-platform
- tags: visual-workflow-builder, ai-canvas, node-based-editor, vercel-ai-sdk, multi-model, drag-and-drop, nextjs, reactflow, ai-agents, web-server, nodejs

## Member repositories
- vercel-labs/tersa (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.062745+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 2026-08-30T07:03:56.213478+00:00, confidence not recorded.
  - readme: https://github.com/vercel-labs/tersa (fetched 2026-08-28T04:03:20.062745+00:00, sha b89cb48ae8c9)
- Data as of 2026-08-30T08:39:29.467469+00:00.