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

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/

Episode 58: OpenClaw 2026.5.27, Codex 0.134, Claude Code 2.1.153, MCP Gateways, Local Code Graphs, and Private Agent Control

AgentStack Daily EP058 leads with a new release gap: OpenClaw v2026.5.27, Codex rust-v0.134.0, and Claude Code 2.1.152/2.1.153 all landed after the last approved draft. OpenClaw strengthens prompt/content boundaries, no-auth exposure checks, Codex app-server recovery, metadata caching, durable channel delivery, provider coverage, embedding-provider support, Pixverse, DeepInfra catalog browsing, VLLM thinking params, Claude OAuth overlays, release checks, and CI proof paths. Codex adds local conversation-history search, a profile-first configuration model, better MCP setup with per-server environment targeting and OAuth for streamable HTTP, read-only MCP concurrency, richer hook and extension context, connector-schema preservation, and remote reliability fixes. Claude Code adds code-review fix mode, skill/tool restrictions, skill reload hooks, message-display hooks, plugin suggestion marketplaces, fallback-model continuity, background/workflow status improvements, MCP and remote fixes, then follows with LFS-skip plugin source options, update/doctor visibility, stricter subagent MCP policy handling, OAuth gateway credential fixes, macOS background-agent permission continuity, and many background-session repairs. The outside slate then covers MCP gateway governance, code-intelligence tools, shared agent memory and task state, mobile control bridges for local agents, local model routers and OpenAI-compatible serving, and DGX Spark / LM Studio as a private high-performance local model server. Show notes: https://tobyonfitnesstech.com/podcasts/episode-58/