Research, experiments, and implementation notes filed under devtools.
Hugging Face Funes Turns Agent Sessions Into Owned Memory
Hugging Face's funes is a practical local-first memory layer for coding agents: index raw session traces, keep provenance, and share through a dataset only when you choose.
OpenAI Agents SDK Makes Sandboxes A First-Class Boundary
OpenAI's Agents SDK update is a practical reminder that production agents need explicit workspaces, isolated compute, durable state, and credential boundaries.
Codex Turns Agent Runtime Into Platform Work
OpenAI's Codex platform post is a practical reminder that useful agents need runtime boundaries, product-owned context, streaming, and approval flows, not just a chat box.
Ollama Brings Local Models Into Claude Desktop
Ollama's Claude Desktop support gives builders a simple way to route desktop AI work to local or Ollama-hosted open models, with a practical smoke test before trusting the...
GitHub Rule Insights Make Repository Governance Easier To See
GitHub's rule insights dashboard is now generally available at repository and organization levels, giving teams a faster way to audit ruleset failures, bypasses, and enforcement trends.
VS Code Agent Host Makes Coding Sessions Less Tied To One Window
VS Code 1.134 moves agent sessions toward a dedicated Agent Host process, making long-running coding work easier to share, resume, and run near the workspace.
Coding Agent Allowlists Are Not A Security Boundary
A practical look at why trusted-command allowlists can fail for coding agents, and what teams should move into the sandbox boundary instead.
GitHub's License Data Update Makes SBOM Reviews Less Noisy
GitHub is prioritizing registry license metadata in the dependency graph, which should make SBOMs and dependency review checks easier to trust.
Docker Sandboxes Make ESP32 Agent Workflows Less Risky
A practical look at reproducible ESP32 firmware builds, remote serial flashing, and safer AI-assisted hardware loops with Docker Sandboxes.
What MCP Traffic Detection Can—and Cannot—Protect
Where Cloudflare's MCP traffic detection helps, where it cannot, and which controls still belong at the server.
A Workable Artifact Layout for LeRobot Training Runs
Using manifests, checksums, and Hugging Face Storage Buckets to keep mutable robotics runs under control.
What Agent Plugins 1.0 Gets Right About Portable Tooling
A closer look at the portable packaging layer for skills, commands, hooks, and MCP configuration.