Local execution trees for TypeScript AI agents. agent-inspect helps you understand what happened inside an AI agent run — locally. It turns manual steps, tool calls, LLM calls, structured logs, failures, durations, and run metadata into readable execution trees you can inspect from the terminal. It is built for TypeScript/Node.js developers..

1st Place Winner (General Judge) - Datadog Self-Improving Agents Hack. Two identical AI agents play Split or Steal. No pre-programmed betrayal. They discover deception on their own. Built with @evancorrea.

Braintrust tracing plugin for pi

My implementation for a kaggle competition: https://www.kaggle.com/competitions/WattBot2025

A Python implementation of the canonical agent architecture: a while loop with tools. Build production ready AI agents with purpose-built tools, comprehensive tracing, and async patterns.

his repository is a sandbox for exploring and building agentic AI applications. It provides a foundation for experimenting with AI-driven solutions, particularly in the domain of decision-making and automation.

C# SDK for the Braintrust API -- AI evaluation, experiments, datasets, prompts, and scoring

Pulse - Track Braintrust/AI engagements and collect testimonials. MCP-enabled for agent integration.

Export Inspect Petri alignment audits to Braintrust experiments, with first-class Ollama support.

A self-improving AI exploration agent built with Google Vertex AI, BigQuery, and Firebase to autonomously analyze data and refine its own querying strategies.

Agent memory patterns: From circular buffers to hierarchical memory systems with summarization and semantic search