Research

AI systems research, backed by open data

We compare coding agents, multi-agent systems, agent infrastructure, and generative media pipelines. Every article links to its dataset, sources, and downloads.

[Research pulse]

Agents·01 Jun 2026

AI Coding-Agent Primitives

Read

Compare 61 coding-agent capabilities across 28 tools, including plan mode, subagents, hooks, memory, MCP, and checkpoints. Browse all 1,708 coded cells.

Agents·04 Apr 2026

Multi-Agent Interaction Patterns

Read

A source-backed catalogue of 40 ways LLM agents coordinate, from role-based workflows and verification loops to debate, shared state, and adaptive topology.

Agents·21 Jun 2026

Harness-as-a-Service: Agent Runtimes, SDKs, and Sandboxes

Read

Compare 41 hosted runtimes, agent SDKs, code sandboxes, and browser services, drawn from a source-backed catalogue of 95 AI infrastructure products.

Workflows·03 Jul 2026

Generative Media Pipeline Patterns

Read

A catalogue of 75 generative media pipelines across image, video, audio-driven animation, and 3D, with sourced stages and explicit controls.

Evals·12 Jul 2026

Do Multi-Agent Patterns Beat a Single Model?

Read

We measured 13 multi-agent patterns against one-model controls, with token costs and injected faults. Most cost more and score less; verification decides containment.