braintrust

Braintrust tracing plugin for pi

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.

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

Dual-modular platform combating SRE alert burnout and securing generative AI deployments using Spring Boot and FastAPI. Tracks on-call fairness via Gini coefficients and uses AST/CST analysis to detect fragile, low-quality, or overly AI-dependent code in CI/CD pipelines while introducing quantifiable engineering contribution metric

A causal debugger for distributed AI systems—isolated Daytona worlds, Braintrust evals, and evidence-first incident response.

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.

Can you eval an art form? Canon is a continuity linter for serialized TV, YouTube and micro-drama fiction. Canon plays the role of whats currently the scriptwriting coordinator, verifies your story's logic and cites the scene. No GenAI writing here. That's left to the humans.

AI-powered coloring page generator for kids, parents, and teachers.

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.

AI agent that turns regulated enterprise conversations into decision-ready briefs and audited actions. Permission-aware RAG with grounded citations, deterministic policy gates, HITL approval loop, and a 3-vertical eval scorecard.

Darwin evolves the best whole agent for your task, its prompt, tools, code, and the model it runs on, generation over generation, inside sandboxes it can't escape and against a grader it can't game.

coding agent example solving for one-shot runnable applications

Orchestrate other AI CLIs (agy, Codex, Grok, OpenCode, Claude Code) for second opinions, research, and codebase analysis. No Gemini CLI. Hybrid always-on skill (eval-backed).

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.

CacheCatch audits AI agent context and shows what to move so repeated tokens hit cache instead of full-price input — it finds context waste, prompt cache misses, and hidden agent cost leaks; and give you actionable insights how to fix them.

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

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

A regulated-agent deployment kit for turning traces, evals, regressions, and approval gates into launch/no-launch decisions

An eval and observability cockpit for coding agents. It runs policy-controlled coding agents in sandboxed toy repos, tool-use traces, MCP tools, compares harness policies, scores recovery and safety behavior with Python evals, and supports CI-gated verification and Braintrust/Weave export.