With AI, Everyone is a Dev

Agent Skill Memory Layer

Open-source skill memory layer that captures learnings from AI agent runs and stores them as readable Markdown skill files.

Pytest Red Teaming for AI Agents

A pytest-native safety and security testing framework for agentic AI applications.

LLM App Tracing and Evaluation

Open-source toolkit by Weights & Biases for tracing and evaluating AI agents and LLM applications.

Open Source LLM Red Teaming

Open-source Python framework for red teaming LLM applications and AI agents by simulating adversarial attacks and detecting vulnerabilities.

Open Source Private Data Research

Open-source Python deep research tool that combines LLMs and vector databases to search, evaluate and reason over private data and produce answers and reports.

Open Source Memory for AI Agents

Cross-platform semantic memory layer for AI coding agents, backed by Markdown files and a Milvus hybrid search index.