PromptForge
The ultimate prompt engineering workbench
Visit website →About
PromptForge is an open-source workbench for prompt engineering. It gives a structured place to draft prompts, run them against models, and compare outputs side by side, rather than testing ad hoc in a chat window.
It supports versioning prompts, running the same prompt across inputs, scoring results, and keeping a record of what changed and why, so a prompt can be improved systematically and regressions are caught.
It is aimed at developers and researchers who treat prompts as part of a codebase and need a repeatable evaluation loop. The project is available on GitHub and can be self-hosted, with no vendor lock-in around a particular model provider.
AI-assisted draft, human-reviewed before publishing — see how we choose & review tools.
Why we picked it
PromptForge stood out for versioning prompts with a record of what changed and why — that's the difference between iterating on a prompt deliberately and re-typing variations in a chat window and forgetting which one actually worked better.
Related tools
- 1 Tiden Verifies coding agents built what you asked for — specs as code Trial
- 2 GitGlow Local Git workbench with smart review for your changes and agent edits Freemium
- 3 GitHub Copilot AI coding assistant inside your editor, with a free tier Freemium
- 4 Together Link Run frontier open models in the coding harness you already use Paid
- 5 Octri Turns OpenAPI specs into docs, SDKs in 10 languages, and MCP server Freemium
- 6 FastRouter.ai One OpenAI-compatible API to route across 200+ LLMs with smart failover Freemium