A leaderboard that ranks AI agents, models, tools, and frameworks using ELO-style ratings from head-to-head
Freemium - free tier available
A leaderboard comparing AI model performance on MCP tasks, tracking how different models and harness
Freemium - free tier available
A controllable world of apps and people for benchmarking interactive coding agents, with state-based and
Freemium - free plan for individuals
A standalone, self-hostable web environment for evaluating autonomous agents on realistic tasks, making it a
Freemium - free tier available
An extension of OSWorld that evaluates AI agents on real-world computer tasks using the Model Context
Freemium - free tier available
A real computer-use benchmark with 369 tasks across Ubuntu, Windows, and macOS, complete with initial-state
Freemium - free tier available
The Terminal-Bench 2.0 announcement, useful for understanding the harder tasks and generalized evaluation
Freemium - free tier available
UK AISI's open-source evaluation framework with solver, scorer, sandboxing, tool-use, MCP, and log-viewer
Freemium - free tier available
An operations-oriented companion focused on context discipline, validation, and reproducible agent workflows.
Freemium - free tier available
Practitioner guidance on concurrency bounds, decorrelated backoff, circuit breakers, and idempotency for
Freemium - free tier available
A concrete pattern for giving a scheduled agent real purchasing authority without real risk: a
Freemium - free tier available
OpenHands' design for bounded conversation memory that preserves goals, progress, critical files, and failing
Freemium - free tier available