9 min read—
Gemini 4 Hydrogen: Fast, Cheap Model for Coding Agents
Gemini 4 Hydrogen launched 12 Nov 2026: 2.5x faster than Gemini 3.8 Flash, $1.50/$7.50 per million tokens, free tier included — how to use it for coding agents.
Tag: AI agent
All the articles with the tag "AI agent".
- 9 min read—
Nod n8n: Open-Source Personal Agent with Its Own PC
Nod n8n is n8n Labs' open-source personal agent with its own Linux computer and browser for real errands on the web. Setup, architecture, safety, limits.
- 10 min read—
BotPsy-0.8B: Tiny On-Device Agent Model That Out-Calls Tools
BotPsy-0.8B is a 0.8B-parameter agent model that runs fully on-device and beats a 2.5x larger model at tool calling. Run it locally with vLLM and llama.cpp.
- 11 min read—
Claude Fable 5.2 vs Opus 5.5: When Is It Worth It?
Anthropic launched Claude Fable 5.2 and Mythos 5.2 on 9 Nov 2026: up to 30% faster, $8/$40 per million tokens. When it beats Opus 5.5 — and where it loses.
- 10 min read—
Claude Code Remote on AWS Bedrock AgentCore
Run Claude Code remotely on AWS Bedrock AgentCore: one microVM per task, model calls only via Bedrock, and a pull request when done. Setup guide and limits.
- 13 min read—
Anthropic on Agent Memory: Notes, Wikis, and Dreaming
Anthropic's agent memory architecture: transcripts, notes, wikis, and 'dreaming' that fixes wrong notes. CL-Bench, Pokémon, and wiki results, plus six rules.
- 10 min read—
OpenMausBot: Open-Source Grok Bot You Can Self-Host
OpenMausBot is an open-source Grok Bot alternative: a team of AI bots in a chat app, each with its own computer, running on your Claude, Codex, or grok CLI.
- 9 min read—
Auto Ontology: A Semantic Layer for AI Agents
NVIDIA Auto Ontology builds a certified semantic layer for AI agents: verified definitions generate SQL with provenance, and out-of-scope questions are refused.