Run agent evals and private benchmarks in sandboxed cloud environments — compare Claude Code, Codex, Cursor and Copilot on the same real tasks.
Coding & DevelopmentFreemium
Evaluation
Measuring whether models, agents and prompts actually work — scores, traces and test harnesses.
9 apps, 2 skills and 2 MCP servers tagged Evaluation.
Apps
Microsoft's open-source optimizer that trains an agent's SKILL.md like a model parameter — epochs, learning-rate budgets and a held-out validation gate, with frozen weights.
Coding & DevelopmentFree
Continuous automated QA for voice and chat AI agents, from pre-launch simulation to live call monitoring.
Coding & DevelopmentFreemium
An open-source platform for building production LLM applications — visual workflows, RAG, and agents in one place.
Automation & WorkflowsFreemium
The framework and observability platform most teams use to build, debug, and ship LLM agents.
Coding & DevelopmentFreemium
Open-source LLM observability — trace, evaluate, and improve AI applications with production data.
Data & AnalyticsFreemium
Evaluation-first AI development — measure whether a prompt or model change actually improved anything.
Data & AnalyticsFreemium
The standard experiment tracker for machine learning, now with tracing and evaluation for LLM applications.
Data & AnalyticsFreemium
Agent observability and evaluation that scores every production run for quality, drift and risk — and can pause or block a risky action before it executes.
Coding & DevelopmentFreemium
Skills
Tencent's skill-evolution harness: it rewrites a whole skill folder — SKILL.md, scripts and references together — and lands every decision as a real Git issue, PR and wiki entry you can review.
4 views
Skill: MCP Builder
by Anthropic
Anthropic's guide for building high-quality MCP servers end to end — research, tool design, implementation in TypeScript or Python, testing, and a 10-question evaluation suite.
1 views
MCP servers
Query Braintrust evals and production logs in SQL from your editor — compare experiments against a baseline, debug a bad trace, and hand a teammate a permalink.
Langfuse's own MCP server for LLM observability — read traces and observations, manage prompt versions, run datasets and evaluators, and query cost and latency metrics from inside your agent.
Related tags
Tags that appear alongside this one, ranked by how often.