Havuz

Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered c

Harness-oriented agent system framework for production-grade LLM agent applications

A dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The ga

Stateful ride-support agent: versioned claims, evidence-backed RAG, durable memory and guarded MCP tools.

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augment

skilled: open-source agent skill evaluation CLI and MCP server for Codex and Claude Code. Test skills, detect regressions, and improve with

The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it,

Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs

The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learn

AI Agent / LLM application engineer Chinese interview question bank: 2,038 questions with reference answers

An external memory for LLMs: a bi-temporal knowledge graph with hybrid (keyword + vector) retrieval and a self-improving reflection loop. Be

Robot data infrastructure and runtime: turn video, state, actions, and telemetry into training episodes, RL environments, policy rollouts, a

The open testing standard for voice AI agents. Deterministic + semantic + RAG augmented evaluation. Local first. Zero telemetry.