mrkeyoor.com_
Thu 10 Sept 21:57 UTC
LLM Toolsevaluationupdated 10 Sept 2026

prompt-optimizer review

Prompt Optimizer is a TypeScript application for improving, testing, comparing, and saving prompts before you use them with an AI provider. It turns prompt tweaking from a copy-and-paste habit into a repeatable workspace, with text and image workflows available through a web app, desktop app, Chrome extension, Docker, or MCP.

trackingstars / 7d
Verdict

Our build finished in 54 seconds, but the test suite ended with 1 failure after 1,204 tests passed. Prompt Optimizer is worth trying if you want a polished, local-first workbench that joins prompt rewriting, comparison, reusable assets, image prompting, and MCP access. For production adoption, inspect the license file and reproduce the test failure before treating the current checkout as a clean baseline.

We ran it

Install✓ · 33s836 packages · 896 MB
Build✓ · 54s
Tests✗ · 45s1204 passed · 1 failed · 141 skipped of 1346 (vitest)
Repo1883 files~283,469 lines of source · 45.5 MB · 3 CI workflows · Dockerfile · tests dir

Answers from our run

Does prompt-optimizer build from source?

Dependencies installed in 33 seconds (836 packages), and the build succeeded in 54 seconds. We cloned commit 5b995b9 into a clean Debian container with 3 CPUs and no project-specific setup.

Do prompt-optimizer's tests pass?

Not all of them: 1204 of 1346 passed and 1 failed when we ran the project's own test command (vitest). Some failures need services or credentials a bare container does not have.

Who should not use prompt-optimizer?

Teams requiring a clean test run before adoption, because our checkout had 1 failing test

What are the alternatives to prompt-optimizer?

promptfoo, Langfuse. Our build finished in 54 seconds, but the test suite ended with 1 failure after 1,204 tests passed.

Setup4/5Install and build finished quickly, but tests had 1 failure
Docs4/5Multiple deployment guides and feature-specific documentation
Community5/534,455 stars, 8 open issues, and a push on review day
Maturity4/5Broad platform support, tempered by a non-green test run

Who it’s for

People who repeatedly refine system or user prompts across supported providers
Teams that want side-by-side evaluation before promoting a prompt
Self-hosters who prefer browser-local data and direct provider connections
Image creators who need text-to-image, image-to-image, and reference-image workflows
MCP users who want prompt optimization inside a compatible AI client

Who it’s NOT for

Teams requiring a clean test run before adoption, because our checkout had 1 failing test
Buyers who need an unambiguous machine-detected license without inspecting the LICENSE file
Organizations seeking a centralized server-side observability and approval platform
Beginners expecting a tiny dependency footprint, because installation occupied 896 MB
Anyone unwilling to supply and manage credentials for the AI providers they choose

Setup reality

On our box, dependency installation succeeded in 33 seconds with 836 packages and used 896 MB, then the build succeeded in 54 seconds. Tests did not pass cleanly: Vitest reported 1,204 passed, 1 failed, and 141 skipped out of 1,346 in 45 seconds. That makes the README's recommended online version the easiest trial, while a source checkout is straightforward but not yet a green, one-command validation experience in the measured environment.

It turns prompt tinkering into a repeatable workspace

Prompt Optimizer tackles a familiar problem: prompts change without a record of what improved. It puts optimization, testing, comparison, and saving into one interface. Its 34,455 GitHub stars show broad interest, while a push on September 10, 2026 confirms activity on our review day.

The README offers 4 delivery options: web, desktop, Chrome extension, and Docker, plus MCP support. Prompts can start as manual text, templates, local imports, or Prompt Garden codes. This is a workshop for drafting, testing, and retaining prompts, not merely a rewrite button.

What happened when we ran it

We cloned commit 5b995b9 into a fresh Debian container with 3 CPUs, 8 GB of RAM, Node 22, no secrets, and no privileged access. The checkout held 1,883 files, about 283,469 source lines, and 45.5 MB before dependencies. It is a pnpm workspace monorepo with a Dockerfile, tests, and 3 CI workflow files.

Installation succeeded in 33 seconds, bringing in 836 packages and consuming 896 MB. The production build then succeeded in 54 seconds. That is a reasonable first run for an application this broad, but the installed footprint matters for constrained containers and short-lived CI jobs. Source users should expect a substantial dependency tree, not a tiny utility.

Tests ran for 45 seconds and failed. Vitest reported 1,204 passed, 1 failed, and 141 skipped out of 1,346 tests. The visible tail showed 1 failed file, 124 passing files, and 18 skipped files, but not the failed assertion or its cause. The honest finding from our run is simple: the build was green and the test gate was red.

One failure blocks a strict release pipeline, and 141 skipped tests mean the sandbox did not exercise every path. Rerun the suite and inspect the complete failure before deployment, especially where provider integrations matter. The log does not justify calling it environmental, flaky, or a regression.

The full feedback loop is its main strength

Version v2.11.9 covers more than prompt rewriting. It supports system and user prompt modes, multi-round improvement, single-result evaluation, multi-result comparison, and evaluation-driven rewriting. The loop is coherent: draft, optimize, compare, judge, and retain the better prompt instead of relying on memory.

Advanced testing adds context variables, batch replacement, previews, multi-turn conversations, and function calling for 2 named providers, OpenAI and Gemini. These matter when names, prices, goals, or earlier messages should alter an answer. The marketplace example tests whether variables change strategy, not just wording.

Saved favorites can include version history, reproducible examples, media, source binding, and workspace application, with complete import and export. Across 4 prompt sources, a team can collect an external starting point and later reuse it without making that source mandatory.

Image generation has 3 modes: text-to-image, image-to-image, and multi-image, plus parameters, previews, downloads, and reference-based style transfer. Gemini, Seedream, and Grok appear in the README. These tools can clarify subjects, spatial relationships, composition, and color before repeated generations.

Breadth brings weight and unresolved edges

About 283,469 source lines and 836 installed packages create more audit and upgrade surface than a simple prompt editor. Teams wanting only text comparison may carry desktop, extension, image, and provider machinery they do not need. Understanding the whole monorepo will take real engineering time.

The failed test is the clearest rough edge because we measured it ourselves. While 1,204 passing tests indicate meaningful coverage, the remaining failure cannot be ignored, and 141 skips are not successful executions. Capture the full assertion and reproduce it before establishing a production baseline.

Licensing needs a manual check. Supplied metadata says NOASSERTION, while the README badge says AGPL-3.0 and links to a LICENSE file. This does not prove a defect, but organizations distributing modifications or hosting the software should inspect the license instead of trusting 1 metadata field.

The client-side architecture has a clear tradeoff. Browser data goes directly to AI providers without an intermediate server, and deployments can add password protection. That reduces 1 data hop, but leaves credential handling, browser storage, access control, and backup with the operator. Password protection is not a full enterprise identity layer.

Current activity is stronger evidence than the release tag alone

The health signals line up: 34,455 stars, 8 open issues, release v2.11.9 on August 26, 2026, and a last push on September 10, 2026. The tag was 15 days old when reviewed, and development activity was current. That supports an active-project judgment rather than one based on popularity alone.

Issue count remains a snapshot. The data does not reveal response speed, closure quality, or maintainer count, so those behaviors cannot be credited. Three CI workflows are encouraging, but our 1 failed test says more about commit 5b995b9's readiness than its stars do.

It belongs before production controls

Prompt Optimizer fits at the authoring and experimentation layer. Use its 4 interfaces to exercise variables, multi-turn cases, image directions, and comparisons, then move accepted prompts through your review process. MCP can bring optimization into a compatible client, while Docker, Vercel, and Cloudflare guides cover common hosting routes.

It does not replace production tracing, cost monitoring, regression gates, or centralized approval. The 2 alternatives divide cleanly: Promptfoo is better when automated evals and CI are the priority, while Langfuse is better when prompt management must sit beside traces and metrics. Prompt Optimizer earns its place as a visual, local-first workbench before those controls.

Use it, after establishing a green baseline

Our 33-second install and 54-second build make the project easy enough to trial, and the online version is simpler still. Its compare-and-evaluate workflow is broad and practical. The caveat is concrete: 1 test failed. Resolve it and confirm the AGPL-3.0 terms before production use.

Alternatives

ProjectWhat it isPick it when
promptfoo gh↗A developer-focused framework for testing prompts, models, and AI application behavior.Pick this instead when automated evals, red teaming, and CI checks matter more than a visual prompt workspace.
Langfuse gh↗An open-source platform for LLM tracing, prompt management, evaluation, and metrics.Pick this instead when prompts must live inside a shared observability and production-management system.

What people are saying

  1. [velocity-scout] linshenkx/prompt-optimizer

Sources

  1. Prompt Optimizer GitHub repository
  2. Prompt Optimizer online application
  3. Prompt Optimizer documentation

More llm tools reviews

agent-router · llm-for-zotero · webcodex · codegraph · semantic-kernel · cc-connect · the whole board →