Pytest for AI Agents! (100% open-source and runs locally) Building agents with LangChain means chaining LLMs, tools, and retrieval steps together. Each component can fail differently. The output changes with every run. Traditional unit tests don't work here because there's no
@sumanth_077
-
The missing layer in AI agent pipelines: acting on data
By
–
The missing layer in most AI agent pipelines!
— Sumanth (@Sumanth_077) 17 juin 2026
AI agents are great at collecting data from the web. The gap shows up when they need to act on it – writing results to Notion, posting to Slack, updating a GitHub repo.
Apify is a platform where developers build and run Actors -… pic.twitter.com/YUI7TB2sJkThe missing layer in most AI agent pipelines! AI agents are great at collecting data from the web. The gap shows up when they need to act on it – writing results to Notion, posting to Slack, updating a GitHub repo. Apify is a platform where developers build and run Actors –
-
Get a letter grade for your AI agent in 5 minutes
By
–
Get a letter grade for your AI agent in under 5 minutes! iFixAi is an open-source diagnostic that catches AI operational misalignment before it damages your business. Actions your agent takes that don't match what you intended, designed, or expected. The dangerous part: these
-
LEANN: Index millions with 97% less storage via graph recomputation
By
–
Turn your laptop into a powerful RAG system! LEANN can index and search through millions of documents while using 97% less storage than traditional solutions without accuracy loss. LEANN achieves this through graph-based selective recomputation with high-degree preserving
-
50+ free open-source AI Agent and RAG apps
By
–
Also check out Hands on AI Engineering! 50+ AI Agent & RAG apps. 100% free and Open source.
-
Step-by-step repo to build and train a transformer LLM from scratch
By
–
Train your own LLM from scratch! A step-by-step repo that walks you through building and training a transformer model from scratch using PyTorch. From downloading training data all the way to generating text. The architecture is built from the ground up following the original
-
Self-evolving agent framework where agents learn and rewrite skills
By
–
Let Agents Design Agents! Memento-Skills is a self-evolving agent framework where agents learn from failures and rewrite their own skills. Most agent frameworks treat skills as static. You write them once, load them into context, and hope they work. When they fail, you debug
-
Repo2RLEnv turns GitHub repos into RL training environments
By
–
Turn any GitHub repo into an RL training environment!
— Sumanth (@Sumanth_077) 7 juin 2026
Repo2RLEnv is a new open-source tool from HuggingFace that synthesizes verifiable RL training data from any GitHub repository. Point it at any repo and it automatically generates tasks, verifies them, and pushes datasets… https://t.co/VXqSNNcVNp pic.twitter.com/p0zmmycsZSTurn any GitHub repo into an RL training environment! Repo2RLEnv is a new open-source tool from HuggingFace that synthesizes verifiable RL training data from any GitHub repository. Point it at any repo and it automatically generates tasks, verifies them, and pushes datasets
-
Open-source collection of 50+ hands-on AI engineering tutorials
By
–
Hands on AI Engineering! I open-sourced a collection of 50+ hands-on AI engineering tutorials. It features step-by-step projects and tutorials on: • AI Agents and Multi-agents
• RAG (Agentic, Vision, and Local)
• MCP AI Agents
• OCR Apps
• Voice AI Agents
• & so much -
Real-world agentic leaderboard from Arena measures actual performance
By
–
Huge! Real-world agentic leaderboard from Arena. Instead of synthetic benchmarks, it measures how models actually perform when real users put them to work – writing code, debugging projects, researching the web, building apps, analyzing documents. The methodology is different