agentmark-ai/agentmark

Markdown for the AI era

48
/ 100
Emerging

This platform helps AI developers build reliable AI agents by letting them define prompts in Markdown, run them with popular AI SDKs, and evaluate their quality using datasets. You input your prompt definitions as `.prompt.mdx` files and get out robust, testable, and observable AI agent behavior. AI engineers and developers building applications that use large language models are the primary users.

340 stars.

Use this if you are developing AI agents and need a systematic way to manage prompts, ensure type safety, incorporate tools, and thoroughly test and observe their performance.

Not ideal if you are looking for a no-code solution or a tool to directly interact with AI models without writing code, as this is a developer-focused platform.

AI development prompt engineering agentic AI LLM application development AI testing
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

340

Forks

20

Language

TypeScript

License

MIT

Last pushed

Mar 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/agentmark-ai/agentmark"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.