# ianarawjo/ChainForge

An open-source visual programming environment for battle-testing prompts to LLMs.

Repository: https://github.com/ianarawjo/ChainForge
Canonical: https://ross.abutalabs.com/products/chainforge
Homepage: https://chainforge.ai/docs
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, evaluation, large-language-models, llmops, llms, prompt-engineering
Last push: 2026-06-10T18:25:33+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 28, longevity 89
- inputs: {"age_days": 1256, "days_push": 84, "days_rel": 479, "gap_med": 45, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3027, forks 254 (observed 2026-08-28T04:07:38.821345+00:00)

## What it is
ChainForge is an open-source visual programming environment for battle-testing prompts to LLMs, built on ReactFlow and Flask. It lets users query multiple LLMs at once, compare responses across prompt permutations and models, and evaluate and visualize results with little to no coding.

## Use cases
- compare prompt variations across multiple LLMs
- evaluate LLM response quality with scoring metrics
- visualize prompt evaluation results across models
- test prompt robustness before deploying to production
- run ground-truth evaluations against benchmark datasets
- query OpenAI, Anthropic, Gemini, and Ollama models side by side
- build LLM evaluation flows without writing code

## When to choose
- you need to rapidly compare prompts, models, and settings across multiple LLM providers
- you want a visual, low-code interface for LLM evaluation and experimentation
- you need to score and plot LLM responses with custom Python/JavaScript evaluators or LLM-based scorers
- you want to test prompts against local models via Ollama or cloud APIs in one tool

## When to avoid
- you need a production LLM pipeline or deployment orchestration rather than experimentation
- you require Safari or other non-Chromium/Firefox browser support
- you want fully automated CI-based eval pipelines with no interactive UI
- you need to avoid executing untrusted code, since evaluator nodes run locally without sandboxing

## Facets
- artifact type: application
- maturity: active
- function: prompt-engineering, llm-inference, data-visualization, machine-learning, developer-tools
- domain: large-language-models, artificial-intelligence, developer-tools, data-visualization
- platform: python, cross-platform, browser, self-hosted
- tags: llm-evaluation, visual-programming, prompt-testing, llmops, reactflow, a-b-testing-prompts, model-comparison, web-server

## Member repositories
- ianarawjo/ChainForge (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:38.821345+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 2026-08-30T07:29:52.210179+00:00, confidence not recorded.
  - readme: https://github.com/ianarawjo/ChainForge (fetched 2026-08-28T04:07:38.821345+00:00, sha ad0e710fe1fe)
  - homepage: https://chainforge.ai/docs (fetched 2026-08-29T09:45:32.684881+00:00, sha f9b4b984a950)
  - site_page: https://chainforge.ai/docs/vis (fetched 2026-08-29T09:45:32.705312+00:00, sha 4af11824d20d)
  - site_page: https://chainforge.ai/docs/getting_started (fetched 2026-08-29T09:45:32.693956+00:00, sha 7907f20cd5f5)
  - site_page: https://chainforge.ai/docs/compare_prompts (fetched 2026-08-29T09:45:32.696146+00:00, sha cc96c7d8bc66)
  - site_page: https://chainforge.ai/docs/nodes (fetched 2026-08-29T09:45:32.697963+00:00, sha cfc071743aa9)
  - site_page: https://chainforge.ai/docs/prompt_templates (fetched 2026-08-29T09:45:32.700002+00:00, sha 8b46b2c20849)
  - site_page: https://chainforge.ai/docs/inspection (fetched 2026-08-29T09:45:32.701636+00:00, sha 1f86f8a5fb8b)
  - site_page: https://chainforge.ai/docs/evaluation (fetched 2026-08-29T09:45:32.703181+00:00, sha 28076ab086fa)
  - site_page: https://chainforge.ai/docs/model_support (fetched 2026-08-29T09:45:32.707070+00:00, sha a0fe0eb5ef18)
- Data as of 2026-08-30T08:39:29.467469+00:00.