workflowstacks
ai-evals

baml: Streamline Prompt Engineering Across Any Language

baml lets founders embed robust prompt engineering directly into Python, TypeScript, Ruby, Java, C#, Rust, or Go code—perfect for building reliable AI products. 9.4k+ GitHub stars.

From the repo · “The programming language for agents”

intermediate⏱ 30 minutes💵 Free + LLM API costs
9,427 stars+18★ this week499 forksRustGuide quality 8/10 · reviewed Oct 8Updated 10/22/2026100% free · open source
What it is

Engineers use this to create structured AI prompts with better results.

Real use case example

"A founder uses Baml to create a script that adds new Shopify customers to their Trello board and sends a welcome email with a unique discount code. First, she sets up her Shopify webhook to send new customer data to Claude, then she uses Claude to prompt the creation of a new Trello card and draft the email with the right code."

Best insideClaude Code
When to use it
  • •When you need to fine-tune your AI prompts for better results
  • •When you want to automate the process of generating high-quality prompts
  • •When you're working with multiple AI models and need a standardized prompt engineering approach
Ready-to-paste prompt
baml run --prompt 'What are the top 3 benefits of using {product_name} for {industry}?' --model gpt-3
Heads up: Make sure you have Rust and Cargo installed on your system before attempting to install Baml, as it is built using Rust and uses Cargo as its package manager.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/baml && curl -fsSL https://workflowstacks.com/api/skills/baml/claude-skill -o ~/.claude/skills/baml/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How baml: Streamline Prompt Engineering Across Any Language works
Codeflow
Free to inspect

Baml: Streamline Prompt Engineering Across Any Language is a very large Rust project (~1.3M lines across 5258 code files, plus 598 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~1.3M lines · 5258 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Node.js
No API keys detected
Rust 58%TypeScript 14%BAML 10%C# 4%Python 3%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    baml/main.go
    Where the program starts running
  3. 3
    go.mod
    Dependencies and the commands it exposes
What's in each folder
baml/Core code — the actual logic3 files
skills/Prompts, skills & agent definitions2 files
docs/Documentation3 files
baml_language/Folder4247 files
engine/Folder3019 files
typescript2/Folder1944 files
integ-tests/Folder512 files
typescript/Folder504 files
READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
BoundaryML
Language
Rust
Category
ai-evals
Published
10/6/2023

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/baml.svg)](https://workflowstacks.com/skills/baml?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Free n8n template

Abandoned Cart Win-Back

Draft a personalized, non-pushy win-back email for every abandoned cart — referencing the exact product left behind. You approve before sending.

Outcome guide

Recover abandoned carts with personalized emails

Export abandoned carts to a Google Sheet and the workflow drafts a warm, specific win-back email for each — referencing the actual product, without desperate discount-spam. You review and send.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

Related skills

More ai-evals tools founders pair with this one.

ai-evals★ 6,283
adversarial-robustness-toolbox
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
ai-evals★ 2,175
adversary_emulation_library
An open library of adversary emulation plans designed to empower organizations to test their defenses based on real-world TTPs.
ai-evals★ 755
agentsight – Low‑overhead AI Agent Tracing with eBPF
Monitor system‑level AI agents in real time without instrumentation, using eBPF. Ideal for founders building observability into LLM‑driven services.
ai-evals★ 682
Build AI Agents with Agentos
Get a TypeScript AI agent framework for multi-agent orchestration. For founders needing autonomous AI agents.
ai-evals★ 366
verifywise: Streamline AI Governance & LLM Evaluations for Startups
A TypeScript platform that lets founders align LLMs with the EU AI Act, ISO 42001, NIST AI RMF and 20+ other standards—ideal for compliance‑focused teams.