In partnership with

Hey builders,

Every week developers release incredible new tools on GitHub.

This week I discovered 20 trending open-source projects focused on AI agents, automation, developer tools, and infrastructure.

Here are some of the most interesting discoveries.

⚡ Featured GitHub Projects

1️⃣ Bitnet.cpp

An open-source inference framework from Microsoft designed to run 1-bit large language models efficiently on CPUs and GPUs.
It includes optimized kernels that enable extremely fast inference while drastically reducing compute and memory usage. This makes running local LLMs much more practical for developers building AI systems.

2️⃣ OpenRAG

A complete Retrieval-Augmented Generation platform for building AI applications that search documents and generate contextual answers.

It integrates document ingestion, indexing, embeddings, and language model pipelines in one system, making it easier to build AI knowledge assistants and internal search tools.

3️⃣ Lightpanda Browser

A lightweight headless browser built for automation and AI agents.

It runs JavaScript, parses HTML, and exposes browser controls via Chrome DevTools Protocol, allowing tools like Puppeteer or Playwright to automate tasks, scrape websites, or build AI-driven web workflows.

4️⃣ Promptfoo

A powerful tool designed to test and evaluate LLM applications.

Developers can run automated prompt tests, compare outputs across different models, and run red-team security checks to identify vulnerabilities in AI systems.

5️⃣ Dolt

A relational SQL database that brings Git-style version control to data.

Developers can commit, branch, merge, and diff database changes just like they do with source code, making collaboration on datasets much easier.

AI Agents Are Reading Your Docs. Are You Ready?

Last month, 48% of visitors to documentation sites across Mintlify were AI agents—not humans.

Claude Code, Cursor, and other coding agents are becoming the actual customers reading your docs. And they read everything.

This changes what good documentation means. Humans skim and forgive gaps. Agents methodically check every endpoint, read every guide, and compare you against alternatives with zero fatigue.

Your docs aren't just helping users anymore—they're your product's first interview with the machines deciding whether to recommend you.

That means:
→ Clear schema markup so agents can parse your content
→ Real benchmarks, not marketing fluff
→ Open endpoints agents can actually test
→ Honest comparisons that emphasize strengths without hype

In the agentic world, documentation becomes 10x more important. Companies that make their products machine-understandable will win distribution through AI.

Make Your Docs Agent-Ready