Episode 62: Codex 0.136, Stanford's Agent Guidelines, AWS OpenAI, and GPU Efficiency

Episode 63: Episode 63

[00:00] Episode hook OpenClaw v2026.6.1, Hermes Agent v2026.5.29.2, and Claude Code 2.1.162 drop in the same episode window. The stable OpenClaw tag is v2026.6.1, the Hermes stable tag stays at v2026.5.29.2, and the latest Claude Code npm `latest` is 2.1.162. OpenClaw v2026.6.1 ships Workboard orchestration, a governed Skill Workshop, SQLite-backed state recovery, and MiniMax M3 provider support. Claude Code 2.1.162 adds waiting-for visibility in `claude agents --json` and a batch of permission and interrupt fixes across five releases from 2.1.158 to 2.1.162. Qwen 3.7 Max and Plus split the coding-reasoning and multimodal-vision lanes. agentmemory makes every agent on your machine share a persistent context layer. This is a 60-minute episode — keep the existing builder stories and extend runtime. Show notes: https://tobyonfitnesstech.com/podcasts/episode-63/

Episode 62: Codex 0.136, Stanford's Agent Guidelines, AWS OpenAI, and GPU Efficiency

AgentStack Daily EP062 leads with Codex `rust-v0.136.0`: better TUI diagnostics and error context, improved app-server lifecycle handling, named hooks and permission scopes, Python SDK and Node SDK improvements, and non-interactive installation support. Stanford's CS336 course publishes a formal AI agent guidelines document that reaches 1,863 stars in under 24 hours — institutional validation that agent workflow guidelines are becoming a first-class engineering concern. OpenAI puts GPT-4.5, o3, and Codex on AWS Bedrock, completing the pattern where both major labs distribute through the same cloud. Expanse from YC P26 uses cluster-specific fine-tuned models to predict GPU job resource needs and outperforms frontier LLMs by 8x on that task, backed by real HPC telemetry and SLURM/Kubernetes integration. The project radar covers agent OS for hardware, terminal context managers, MCP workflow templates, and physical agent scheduling. Show notes: https://tobyonfitnesstech.com/podcasts/episode-62/

Episode 61: OpenClaw 2026.5.28, MiniMax M3, Claude Code 2.1.159, and Code Graphs

OpenClaw `v2026.5.28` leads with steadier agent and Codex runtime recovery, safer channel delivery, stricter browser and automation inputs, provider and media expansion, externalized plugin surfaces, and bounded release proof. MiniMax M3 follows as the model-discovery headline: an open-weight-positioned coding and agent model with MSA sparse attention, up to 1M context, native multimodality, API availability, MiniMax Code integration, and open weights promised after the launch window. Claude Code `2.1.159` is the quiet CLI hygiene lane. Then EP061 evaluates Understand Anything, agentgateway, MCPJungle, and CodeAlmanac as practical tools for codebase graphs, agent traffic control, MCP management, and persistent repo context. Show notes: https://tobyonfitnesstech.com/podcasts/episode-61/

Episode 60: Claude Code 2.1.158, Codex Windows Control, Runtime Instructions, and Local Agent Memory

Claude Code `2.1.158` on npm `latest` adds auto mode for Bedrock, Vertex, and Foundry when `CLAUDE_CODE_ENABLE_AUTO_MODE=1` is set. OpenAI's May 29 Codex update adds Windows computer use in the Codex app, remote control from mobile or Mac while the Windows host keeps project files and local context, in-app browser infrastructure improvements, and Codex Profiles for identity, activity, usage stats, and token activity. The episode then covers Anthropic's Messages API system entries as a runtime-control surface, plus OpenLore, Mnemo, OpenMonoAgent, and Prometheus as project-radar examples of local architectural memory, persistent agent cognition, local-only coding agents, and graph-backed repair loops. Show notes: https://tobyonfitnesstech.com/podcasts/episode-60/

Episode 59: Hermes Agent 0.15.x, Codex 0.135, Claude Code 2.1.157, Opus 4.8, Browser MCP, and Usage Telemetry

AgentStack Daily EP059 leads with a current agent-stack release readout. Hermes Agent moves from `v0.14.0` to the `v0.15.x` line with a major kanban/orchestration expansion, faster launch and session search, promptware defense, Bitwarden Secrets Manager support, skill bundles, an Ink multi-session TUI, image provider additions, a Nous-approved MCP catalog, ntfy messaging, and follow-up fixes for dashboard loopback auth, Docker insecure-mode opt-in, MCP PATH resolution, `.md` media delivery, plugin packaging, and wheel/sdist manifests. Codex `rust-v0.135.0` adds richer `doctor` diagnostics, remote `/status` details, Vim text objects, named permission profiles, bundled zsh helper discovery, Python SDK sandbox presets, non-interactive install mode, and TUI/session reliability fixes. Claude Code `2.1.154` through `2.1.157` adds Opus 4.8, dynamic workflows, effort controls, automatic skill loading from `.claude/skills`, plugin scaffolding, `claude agents` worktree/session improvements, richer telemetry options, and many background-session, sandbox, MCP, image, terminal, and worktree fixes. The episode then covers Anthropic Opus 4.8, OpenAI workspace-agent controls, Chrome DevTools MCP, local code-flow tools, usage/quota telemetry, and programmable video rendering for agent-built media. Show notes: https://tobyonfitnesstech.com/podcasts/episode-59/