Developer Tools
How Google Builds and Tests Agent Skills
Google's playbook for scaling Agent Skills: standard structure, CI, with-vs-without evals, accuracy and efficiency, ownership, and safe export.
ReadSandBase Blog — Page 14
Insights on AI agents, model routing, and building production-ready AI systems.
Page 14
Model Comparison
Google Model Routing vs LiteLLM vs OpenRouter
Compare Google Cloud API Gateway model routing, LiteLLM, and OpenRouter on model reach, routing control, fallbacks, data boundaries, cost, and operations.
Read
Developer Tools
Open Multi-Agent: Runtime DAGs in TypeScript
Review Open Multi-Agent's dynamic task DAGs, mixed coding-agent backends, approvals, replay, security defaults, and when the complexity pays off.
Read
Developer Tools
Orloj: Agent Infrastructure as Code
Review Orloj's infrastructure-as-code approach to multi-agent systems: declarative resources, governance, workers, retries, isolation, and trade-offs.
Read
Developer Tools
Ouroboros: A Self-Developing Coding Agent
Ouroboros can modify its own harness through reviewed Git commits. We examine its memory, evolution loop, benchmark claims, and safety boundaries.
Read
Developer Tools
UiPath for Coding Agents: An Operator's Guide
Review UiPath for Coding Agents: how skills and the uip CLI build and operate automations, where approvals sit, and what enterprises must validate.
Read
Developer Tools
Warp Agent CLI Becomes Oz (2026)
Warp Agent CLI has become Oz CLI. Learn local and cloud runs, profiles, MCP, skills, orchestration, and how it compares with Claude Code and Codex.
ReadDeveloper Tools
Build an Auditable Research Agent: Evidence Ledgers, Sandboxes, and Replay
A reproducible workflow combining a portable research Skill with sandboxed execution, audit trails, and replay using two open-source SandBase projects.
Read
Developer Tools
NVIDIA Switchyard: Run Coding Agents on Any LLM
NVIDIA Switchyard routes Claude Code, Codex, and OpenClaw to hosted or local LLMs. Learn how protocol translation, routing profiles, and fallback work.
Read