Agents Directory Blog
Guides, model comparisons, cost breakdowns, and practical workflows for AI agents, skills, plugins, and MCP servers.
GPT-5.6 Sol, Terra and Luna benchmark results
GPT-5.6 Sol leads OpenAI's new family, while Terra and Luna target lower costs. Here are the independent and official benchmark results that matter.
•5 min read
Grok 4.5 benchmarks: frontier coding at a lower price
Grok 4.5 reaches 54 on the Artificial Analysis Intelligence Index and stays close to the leading coding models while using fewer tokens.
•3 min read
Z.ai launches GLM-5.2: 1M context, Coding Plan only, API to follow
GLM-5.2 is live on every GLM Coding Plan tier with a usable 1M-token context and High and Max effort levels. No standalone API yet, no open weights yet, and no benchmarks at launch. Here is what is actually confirmed.
•3 min read
What is OpenRouter Fusion? How the compound model works
OpenRouter Fusion fans your prompt out to a panel of models, has a judge structure their answers, then a synthesizer writes the final one. Here is how it works, what it costs, and when to use it.
•5 min read
There are ads in Claude Code now. It earns more than your subscription cost: Kickbacks.ai
Kickbacks.ai sells the Claude Code spinner as ad space and pays you 50% of the revenue, by the founder's math more than a Max plan costs. We installed it: it works in Claude Code (VS Code and CLI), but it's still sloppy in Codex.
•4 min read
Moonshot launches Kimi K2.7 Code, its open-source coding model
Kimi K2.7 Code is out and open-sourced: a 1T-parameter MoE for agentic coding, with double-digit gains over K2.6 and tool use that edges past Opus 4.8.
•3 min read
How Claude Fable 5 ranks on benchmarks
Claude Fable 5 led CursorBench 3.1 at launch and remains the reference point for newer frontier coding models. Here are the numbers and the caveat that matters.
•3 min read