EP 50

AgentStack Daily EP050 — What's New in Agent Releases

This AgentStack Daily episode covers what is new in LLM and agent tooling: Hermes Agent v2026.5.7 adds durable boards, worker health checks, checkpoint pruning, gateway resume, no-agent cron, provider plugins, platform allowlists, and MCP fixes; Claude Code v2.1.141 through v2.1.129 adds the agent view, hook JSON updates, plugin and workload-identity controls, MCP repairs, and background-agent permission fixes; Google ADK documents pause-and-resume agents with persisted state; and GitHub exposes Copilot agent tasks through REST endpoints. Show notes: https://tobyonfitnesstech.com/podcasts/episode-50/

May 15, 2026 · ⏱ 42:22

EP 49

Gemini Deep Research, Agents SDK Sandbox Boundaries, vLLM Kernel Fixes, and Strands Runtime Controls

EP049 goes deep on Google’s Gemini Deep Research Agent in the Interactions API, OpenAI Agents SDK sandbox and session fixes, vLLM’s DeepSeek V4 serving patch, and Strands Agents TypeScript runtime controls for hooks, MCP, compression, retries, and human interruption. Show notes: https://tobyonfitnesstech.com/podcasts/episode-49/

May 12, 2026 · ⏱ 37:35

EP 48

Codex Remote Control, Agent RCE Hardening, Copilot Session Hooks, and Microsoft Agent Framework 1.5

OpenClaw Daily EP048 opens with OpenAI Codex 0.130.0 and its remote-control app-server entrypoint, paged thread views, plugin hook metadata, config refresh, turn-diff accuracy, multi-environment image resolution, and telemetry changes. The episode then explains Microsoft’s Semantic Kernel RCE case study, GitHub Copilot SDK session hooks and diagnostics, and Microsoft Agent Framework 1.5 changes around Magentic orchestration, WebBrowsingTool allowlists, reasoning events, todo-state injection, and wire-format fixes. Show notes: https://tobyonfitnesstech.com/podcasts/episode-48/

May 10, 2026 · ⏱ 36:30

EP 47

OpenClaw v2026.5.7, Agents SDK Sandboxes, and Gemini CLI Safety Runtime

OpenClaw Daily covers OpenClaw v2026.5.7, focusing on ClawHub publish recovery, `openai/chat-latest`, cron JSON status, channel listing, native-command owner enforcement, Active Memory admin scope, skills snapshot refresh, before-tool authorization for inline skill dispatch, SecretRef-backed Tavily credentials, context cache invalidation, Discord target parsing, compaction token clamping, delivery failure reporting, Discord voice probes, Telegram poller liveness, WhatsApp routing, and Codex approval handling. The episode then explains OpenAI Agents JS sandbox workspace contracts, realtime defaults, tool concurrency, MCP tool naming, and local artifact boundaries, before closing with Gemini CLI changes around shell safety evals, A2A approval races, compression queues, OAuth hangs, and Auto Memory patch allowlists. Show notes: https://tobyonfitnesstech.com/podcasts/episode-47/

May 9, 2026 · ⏱ 37:04

EP 46

OpenClaw Codex OAuth Routing, Realtime Voice, OpenAI SDK Image Updates, and vLLM Serving Stabilization

OpenClaw Daily examines OpenClaw v2026.5.4 through v2026.5.6, focusing on realtime Google Meet and Voice Call speech, Twilio audio backpressure, plugin migration hints, workspace-scoped metadata snapshots, SecretRef contract resolution, model auth inspection, startup phase diagnostics, rich Slack progress drafts, and compact tool-progress output. The episode then breaks down LangGraph v1.2 alpha’s node timeouts, DeltaChannel checkpointing, error handlers, and streaming API, before closing with vLLM v0.20.1’s DeepSeek V4 kernel, communication, CUDA graph, and tool-call fixes. ### Fresh May 7 Update EP046 has been refreshed for May 7 with current OpenClaw technical content. New OpenClaw coverage includes v2026.5.6 Codex OAuth route repair, plugin runtime/header normalization, debug proxy header replay normalization, and bounded guarded-fetch timeout cleanup; v2026.5.5 channel/progress/session/status fixes; and the prior v2026.5.4 realtime voice and SecretRef contract work. Sources: https://github.com/openclaw/openclaw/releases, https://github.com/openclaw/openclaw/releases/tag/v2026.5.5, https://github.com/openclaw/openclaw/releases/tag/v2026.5.6, https://github.com/openai/openai-python/releases, https://github.com/vllm-project/vllm/releases. Show notes: https://tobyonfitnesstech.com/podcasts/episode-46/

May 7, 2026 · ⏱ 37:45

EP 45

OpenClaw File Transfer, Plugin Runtime Hardening, Codex Goal Workflows, and Agent Egress Security

OpenClaw Daily examines three new OpenClaw releases, focusing on file-transfer tools for paired nodes, plugin install/update hardening, startup hot-path reductions, channel delivery fixes, and runtime reliability. The episode then breaks down OpenAI Codex goal workflows, permission profiles, plugin imports, and multi-agent controls, before closing with Pipelock’s class-preserving redaction and streaming SSE scan design for agent egress security. Show notes: https://tobyonfitnesstech.com/podcasts/episode-45/

May 4, 2026 · ⏱ 34:23

EP 44

OpenClaw v2026.4.29, Active-Run Steering, People-Aware Memory, Model Provenance, and Account Security

The episode starts with OpenClaw v2026.4.29. The release adds active-run steering defaults, visible-reply enforcement, spawned-subagent routing metadata, opt-in follow-up commitments, people-aware memory wiki metadata, per-conversation Active Memory filters, partial recall on timeout, a bounded REM preview RPC, NVIDIA provider onboarding and catalog metadata, Bedrock Opus 4.7 thinking parity, OpenGrep scan workflows, stricter restrictive-profile tool behavior, startup diagnostics, reusable model catalogs, stale-session recovery, runtime-dependency repairs, systemd loop prevention, and many channel fixes. After the release deep dive, the episode covers Cisco’s Model Provenance Kit as a practical model-lineage and AI supply-chain tool, then OpenAI Advanced Account Security as a concrete account-hardening bundle for ChatGPT and Codex users doing high-stakes agent work. Show notes: https://tobyonfitnesstech.com/podcasts/episode-44/

May 3, 2026 · ⏱ 36:15

EP 43

OpenClaw v2026.4.27, Voice Agents, and Rapid AI Storage

EP043 starts with OpenClaw v2026.4.27. The release adds Codex Computer Use status/install flows with fail-closed MCP checks, bundles DeepInfra as a provider for model discovery and media generation, expands Tencent Yuanbao and QQBot channel coverage, adds Docker GPU passthrough for sandboxed agents, introduces operator-managed outbound proxy routing, stages non-image chat attachments for agent use, moves startup and model catalogs toward manifest-first metadata, and fixes many real delivery, session, channel, media, plugin, update, and gateway edge cases. After the release deep dive, the episode turns to Deepgram Flux Multilingual and what multilingual streaming STT changes for voice agents, then Google Rapid Bucket, Colossus, gcsfs, and fsspec as an AI training data path. Show notes: https://tobyonfitnesstech.com/podcasts/episode-43/

April 30, 2026 · ⏱ 40:03

EP 42

OpenClaw v2026.4.26 and the AI Inference Stack

EP042 starts with OpenClaw v2026.4.26: browser realtime transport contracts, constrained Google Live tokens, Gateway relay sessions, bundled Cerebras provider support, manifest-owned provider routing metadata, asymmetric embedding input types, retrieval prefixes for local embedding models, safer plugin mutation, Matrix encryption setup, transcript compaction, and migration tooling. Then we go deeper than prior episodes on inference infrastructure: Groq’s LPU-backed hosted inference, Cerebras wafer-scale inference, LM Studio’s local desktop/server stack, Ollama’s local runner and cloud tiers, OpenRouter’s multi-provider marketplace, LiteLLM’s self-hostable gateway role, and cost-per-value ratings for each. We close with OpenAI Privacy Filter as a local PII token-classifier and Google Cloud AI zones as accelerator-placement infrastructure. Show notes: https://tobyonfitnesstech.com/podcasts/episode-42/

April 28, 2026 · ⏱ 36:19

EP 41

OpenClaw v2026.4.25, Codex App-Server, Space Solar, and AI-Designed Cars

EP041 leads with OpenClaw v2026.4.25: a big operational release that upgrades TTS and voice replies, moves plugin startup onto a persisted cold registry, expands OpenTelemetry diagnostics, improves browser automation, adds PWA/Web Push support in the Control UI, hardens installers and updates, and tightens Codex app-server integration. Then we connect that to OpenAI Codex CLI 0.125.0 and the broader Codex app direction: worktrees, app-server transports, sticky environments, permission profiles, plugin marketplaces, built-in Git, automations, and in-app browser workflows. The back half covers Meta’s capacity reservation for space-beamed solar power and why AI data centers are turning energy procurement into product strategy, then closes with GM, Nissan, and Neural Concept showing AI moving into automotive design, simulation, and software validation loops. Show notes: https://tobyonfitnesstech.com/podcasts/episode-41/

April 27, 2026 · ⏱ 35:17

EP 40

OpenClaw v2026.4.24, Project Deal, Claude Connectors, and the ComfyUI Control Bet

OpenClaw v2026.4.24 is the lead story and it deserves to be. The release adds Google Meet as a bundled participant plugin with personal auth, live voice transports, paired-node Chrome support, artifact and attendance export, and recovery flows for already-open tabs; it also adds deeper realtime agent consults across Talk, Voice Call, and Meet, brings safer browser automation and stronger tab recovery, refreshes bundled model catalogs around DeepSeek V4, and keeps startup lighter with more manifest-driven model and plugin plumbing. After that release deep dive, EP040 looks at Anthropic’s Project Deal marketplace experiment, Claude’s new personal-app connectors, and why ComfyUI’s rise suggests human-in-the-loop control is still the premium layer in AI media workflows. Show notes: https://tobyonfitnesstech.com/podcasts/episode-40/

April 27, 2026 · ⏱ 32:38

EP 39

OpenClaw v2026.4.23, Anthropic’s Google Deal, DeepSeek V4, and the Vercel Spillover

OpenClaw v2026.4.23 is the lead story and it deserves to be. The release materially improves image generation and reference-image editing across OpenAI Codex OAuth and OpenRouter, expands `image_generate` controls, adds optional forked transcript inheritance for `sessions_spawn`, introduces per-call `timeoutMs` for long generation tools, tunes local embedding context sizing, and tightens a long list of Codex, media, webchat, and security behaviors that operators actually feel. After the release deep dive, the episode shifts to Google’s planned Anthropic investment and compute expansion, DeepSeek’s V4 preview as a cheaper giant open-weight challenger, and Vercel’s warning that its customer-data incident may predate the breach it first disclosed. Show notes: https://tobyonfitnesstech.com/podcasts/episode-39/

April 26, 2026 · ⏱ 32:42

EP 38

OpenClaw v2026.4.22, Chrome Agents, Codex Surfaces, and the Fight for the Builder Stack

OpenClaw v2026.4.22 is the new lead story in EP038, and it is a dense one. We start with the release: xAI image, TTS, STT, and realtime transcription support; terminal embedded mode without the Gateway; auto-installing missing provider and channel plugins during onboarding; chat-side model registration; diagnostics export; Tencent Cloud support; Codex auth-path tightening; GPT-5 overlay sharing across providers; plugin-load speedups; and a long tail of operator-facing fixes across pricing, sessions, Telegram, memory search, Azure image support, and more. Then we add the new market-moving question of GPT 5.5 appearing in Codex and what that could mean for OpenClaw’s provider routing, overlays, coding surfaces, and competitive positioning. The episode preserves both the release deep dive and the GPT 5.5 analysis, then keeps the existing builder stories: Chrome as a managed browser-agent surface, Cursor as a strategic coding-surface target, Google splitting training and inference silicon, OpenAI climbing from endpoint to work surface, and Anthropic reminding everyone that shell access is platform power. Show notes: https://tobyonfitnesstech.com/podcasts/episode-38/

April 24, 2026 · ⏱ 47:08

EP 37

The DGX Spark Decision: What It Actually Changes in the Aria Build

This special episode breaks down what a DGX Spark actually means in the real compute environment behind OpenClaw Daily. Instead of a generic buyer’s guide, it is a practical analysis of how the Spark fits into the Aria build, what workloads it should own, how it changes local image and video generation, why one unit likely unlocks most of the strategic value, and when a second unit would be rational as scale or scarcity insurance. Show notes: https://tobyonfitnesstech.com/podcasts/episode-37/

April 23, 2026 · ⏱ 43:48

EP 36

OpenClaw v2026.4.21 and v2026.4.20 in Detail, Plus OpenAI Images 2.0

This episode starts where it should: with a detailed walkthrough of OpenClaw v2026.4.21 and v2026.4.20. We cover the new image-generation default path, louder fallback logs, owner-only command tightening, Slack and browser guardrails, setup-flow improvements, session and cron state cleanup, pricing support, compaction notices, and runtime fixes. Then we look at OpenAI’s Images 2.0 through a practical workflow lens and close with YouTube’s broader AI likeness-detection rollout. Show notes: https://tobyonfitnesstech.com/podcasts/episode-36/

April 23, 2026 · ⏱ 30:08

EP 35

DGX Spark vs Mac Studio: What Should a Mac-First AI Buyer Actually Buy?

A blunt buyer's guide for the Mac-first listener who wants serious local AI without accidentally buying the wrong ecosystem. Show notes: https://tobyonfitnesstech.com/podcasts/episode-35/

April 21, 2026 · ⏱ 29:21

EP 34

Which AI Tools Are Actually Good, and Which Ones Die First?

Enough fake consensus. This episode is a blunt field report on today’s AI tool stack: what each tool really is, what it is actually good at, what is broken about it, and which categories feel durable versus already half-dead. Show notes: https://tobyonfitnesstech.com/podcasts/episode-34/

April 18, 2026 · ⏱ 32:39

EP 33

Headless Commerce and the Robot Workbench

OpenClaw ships v2026.4.15 with Claude Opus 4.7 defaults and new speech tooling, Anthropic pushes a stronger coding-and-vision model into general availability, Salesforce rebuilds its platform for agents instead of browsers, Roblox turns game creation into a planning loop with AI, Physical Intelligence says robots are starting to remix skills they were never directly taught, and Adobe’s latest data says AI shopping traffic is finally turning into serious retail money. Show notes: https://tobyonfitnesstech.com/podcasts/episode-33/

April 17, 2026 · ⏱ 33:37

EP 32

Passports, Sandboxes, and the Human Layer

A wider AI-stack episode: Anthropic starts gating some Claude features behind ID checks, OpenAI turns its Agents SDK into a real production harness, and TSMC's results say the AI buildout is still running hot. We also cover Telegram KYC-bypass markets and the global pushback against AI dubbing and voice cloning. Show notes: https://tobyonfitnesstech.com/podcasts/episode-32/

April 16, 2026 · ⏱ 33:00

EP 31

Agentic Everything

OpenClaw v2026.4.14 tightens GPT-5.4 compatibility, channel safety, and runtime hardening. The rest of the episode tracks Chrome Skills, DeepMind's robot reasoning push, NVIDIA's open quantum AI models, IBM's autonomous cyber-defense play, and Meta's bigger silicon bet with Broadcom. Show notes: https://tobyonfitnesstech.com/podcasts/episode-31/

April 15, 2026 · ⏱ 32:52

EP 30

Memory First, Machines Next

OpenClaw's latest release makes memory retrieval happen before the main reply and pushes more speech and model routing local. Then we dig into OpenAI's macOS certificate rotation, Anthropic turning Cowork into an admin surface, SoftBank's physical-AI bet, and Meta's overreaching health chatbot. Show notes: https://tobyonfitnesstech.com/podcasts/episode-30/

April 14, 2026 · ⏱ 32:24

EP 29

Claw Tax, Courtrooms, and the New AI Stack

OpenClaw's April 11 release pulls imported chats into its memory system and sharpens multimodal replies. We also cover Anthropic's brief OpenClaw lockout, OpenAI's stalking-delusion lawsuit, Gemini's move into interactive simulations, and why Google plus Intel are a reminder that AI still runs on infrastructure. Show notes: https://tobyonfitnesstech.com/podcasts/episode-29/

April 12, 2026 · ⏱ 33:44

EP 28

Peer Pressure at Machine Scale

OpenClaw ships v2026.4.10, Anthropic unveils Mythos Preview, frontier models protect peer models from deletion, OpenAI backs an Illinois liability shield, the U.S. Army builds Victor, and Meta pauses Mercor after a major breach. Show notes: https://tobyonfitnesstech.com/podcasts/episode-28/

April 11, 2026 · ⏱ 34:51

EP 27

Dream Stack, AI Prescriptions, Shell Agents, and the Cost of Scribes

OpenClaw 2026.4.9 ships a grounded REM backfill lane and structured diary timeline, Utah lets AI prescribe psych meds, OpenAI gives agents a real shell, STAT News reports AI scribes are quietly inflating healthcare costs, and Yahoo bets its search future on Claude. Show notes: https://tobyonfitnesstech.com/podcasts/episode-27/

April 10, 2026 · ⏱ 31:17

EP 26

OpenClaw Gets a Brain Transplant, Glasswing, Giant Brains, and Cloned Writers

[00:00] INTRO / HOOK OpenClaw 2026.4.8 drops a unified inference layer, session checkpointing, and a restored memory stack. Anthropic's Glasswing coalition, MegaTrain's single-GPU frontier training, and a study proving your writing AI might just be a Claude knockoff. [02:00] STORY 1 — OpenClaw 2026.4.8: The Release That Changes How It All Works Six major subsystems land in one release. The first is the infer hub CLI — openclaw infer hub — a unified interface for provider-backed inference across model tasks, media generation, web search, and embeddings. It routes requests to the right provider, handles auth, remaps parameters across provider capability differences, and falls back automatically if a provider is down or rate-limited. If you have been managing multiple provider configs across different workflows, the hub becomes the single abstraction layer. Provider switches become config changes at the hub level; the rest of your workflow is unchanged. The second is the media generation auto-fallback system, covering image, music, and video. If your primary provider is unavailable or does not support the specific capability you requested — aspect ratio, duration, format — OpenClaw routes to the next configured provider and adjusts parameters automatically. One failed generation is an inconvenience. A thousand per day across a production fleet is an operational problem. This is handled once at the platform level; every agent benefits immediately. The third is the sessions UI branch and restore functionality. When context compaction runs, the system now snapshots session state before summarising. Operators can use the Sessions UI to inspect checkpoints and restore to a pre-compaction state, or use any checkpoint as a branch point to explore a different direction without losing the original thread. This is version history for session context — the difference between editing with autosave and editing where every save overwrites the previous file. The fourth is the full restoration of the memory and wiki stack. This includes structured claim and evidence fields, compiled digest retrieval, claim-health linting, contradiction clustering, staleness dashboards, and freshness-weighted search. Claims can be tagged with supporting evidence, linted for internal consistency, and grouped where they contradict each other. Search results are ranked by recency, not just relevance. If you have been working around missing pieces in prior versions, this is the native implementation — test your workflow against it. The fifth is the webhook ingress plugin. Per-route shared-secret endpoints let external systems authenticate and trigger bound TaskFlows directly — CI pipelines, monitoring tools, scheduled jobs, third-party webhooks — without custom integration code. The plugin handles routing, auth, and workflow binding. The sixth is the pluggable compaction provider registry. You can now route context compaction to a different model or service via agents.defaults.compaction.provider — a faster, cheaper model optimised for summarisation rather than the most capable model you have. Falls back to built-in LLM summarisation on failure. At scale, compaction is happening constantly; routing it appropriately matters for cost and latency. Other notable additions: Google Gemma 4 is now natively supported with thinking semantics preserved and Google fallback resolution fixed. Claude CLI is restored as the preferred local Anthropic path across onboarding, doctor flows, and Docker live lanes. Ollama vision models now accept image attachments natively — vision capability is detected from /api/show, no workarounds required. The memory and dreaming system ingests redacted session transcripts into the dreaming corpus with per-day session-corpus notes and cursor checkpointing. A new bundled Arcee AI provider plugin with Trinity catalog entries and OpenRouter support. Context engine changes expose availableTools, citationsMode, and memory artifact seams to companion plugins — a better extension API. Security-relevant fixes: host exec and environment sanitisation now blocks dangerous overrides for Java, Rust, Cargo, Git, Kubernetes, cloud credentials, and Helm. The /allowlist command now requires owner authorization before changes apply. Slack proxy support is working correctly — ambient HTTP/HTTPS proxy settings are honoured for Socket Mode WebSocket connections including NO_PROXY exclusions. Gateway startup errors across all bundled channels (Telegram, BlueBubbles, Feishu, Google Chat, IRC, Matrix, Mattermost, Teams, Nextcloud, Slack, Zalo) are resolved via the packaged top-level sidecar fix. → github.com/openclaw/openclaw/releases [12:00] STORY 2 — Project Glasswing: The Cyber Defense Coalition Anthropic launched Project Glasswing with a coalition of Amazon, Apple, Broadcom, Cisco, CrowdStrike, Google, JPMorganChase, Microsoft, NVIDIA, Palo Alto Networks and others. The centerpiece is Claude Mythos Preview — an unreleased frontier model scoring 83.1% on CyberGym vs 66.6% for Opus 4.6. In testing it found thousands of zero-day vulnerabilities, including a 27-year-old OpenBSD bug and a 16-year-old FFmpeg flaw. Anthropic is committing $100M in usage credits and $4M in donations to open-source security orgs. The core thesis: offensive AI capability has outpaced human defensive response time, so the same capability must be deployed defensively. Worth discussing: what does "coalition" mean when Anthropic controls the model? And is finding bugs and patching them actually better than just not shipping vulnerable code? → anthropic.com/glasswing [20:00] STORY 3 — MegaTrain: Full Precision Training of 100B+ on a Single GPU MegaTrain enables training 100B+ parameter LLMs on a single GPU by storing parameters and optimizer states in host (CPU) memory and treating GPUs as transient compute engines. On a single H200 GPU with 1.5TB host memory, it reliably trains models up to 120B parameters. It achieves 1.84x the training throughput of DeepSpeed ZeRO-3 with CPU offloading when training 14B models, and enables 7B model training with 512k token context on a single GH200. Practical implications: dramatically lowers the hardware barrier for frontier-scale training, which could accelerate both legitimate research and... everything else. → arxiv.org/abs/2604.05091 [27:00] STORY 4 — 178 AI Models Fingerprinted: Gemini Flash Lite Writes 78% Like Claude 3 Opus A research project created stylometric fingerprints for 178 AI models across lexical richness, sentence structure, punctuation habits, and discourse markers. Nine clone clusters showed >90% cosine similarity. Headline finding: Gemini 2.5 Flash Lite writes 78% like Claude 3 Opus but costs 185x less. The convergence suggests frontier models are hitting similar optimal patterns despite different architectures and training data — or that Claude's style is just a strong attractor for RLHF. Implications for AI detection tools, originality claims, and the economics of "good enough" AI writing. → news.ycombinator.com/item?id=47690415 [32:00] STORY 5 — LLM Plays Shoot-'Em-Up on 8-bit Commander X16 via Text Summaries A developer connected GPT-4o to an 8-bit Commander X16 emulator using structured text summaries ("smart senses") derived from touch and EMF- style game inputs. The LLM maintains notes between turns, develops strategies, and discovered an exploit in the built-in AI's behavior. Demonstrates that model reasoning can emerge from minimal structured input — no pixels, no audio, just text summaries of game state. Fun side note: the Commander X16 is a modern recreation of an 8-bit home computer architecture, so it's running on actual hardware emulated in software. → news.ycombinator.com/item?id=47689550 [35:30] OUTRO / CLOSE Next episode drops tomorrow. If you want a transcript, reply on Telegram. → Reply on Telegram to approve transcript generation. ``` Show notes: https://tobyonfitnesstech.com/podcasts/episode-26/ Show notes: https://tobyonfitnesstech.com/podcasts/episode-26/

April 7, 2026 · ⏱ 37:25

EP 25

The Control Surface

This week’s throughline is control: who controls the runtime, who controls agent behavior during real incidents, and who controls the physical systems AI now depends on. Show notes: https://tobyonfitnesstech.com/podcasts/episode-25/ Show notes: https://tobyonfitnesstech.com/podcasts/episode-25/

April 7, 2026 · ⏱ 32:11

EP 24

The Narrative Layer

OpenAI buys a media platform. Peter Steinberger highlights the CLI workaround culture forming around Anthropic's restrictions. Microsoft launches an open-source agent governance toolkit. Meta shows AI optimizing the machine layer underneath inference. Microsoft commits ten billion dollars to AI infrastructure in Japan on sovereignty terms. And in the United States, the data-center boom runs headfirst into an old-fashioned bottleneck: electricity. Six stories about who controls the AI stack — and whether the physical grid will let anyone finish building it. Show notes: https://tobyonfitnesstech.com/podcasts/episode-24/

April 5, 2026 · ⏱ 38:00

EP 23

The Infrastructure Week

$300 billion in one quarter. Anthropic pays $400 million for a team of nine. Google open-sources its best reasoning model. The World Economic Forum says it's time to treat AI compute like power grids and water systems. And effective today, Anthropic is changing how third-party harnesses like OpenClaw are billed — because the infrastructure era isn't just about data centers. It's about who pays for the compute. Six stories about the week infrastructure stopped being boring. Show notes: https://tobyonfitnesstech.com/podcasts/episode-23/

April 4, 2026 · ⏱ 38:39

EP 22

The Release Train

The software shipped before breakfast. OpenClaw v2026.4.1 turns background agent work into a first-class chat surface with /tasks, bundles SearXNG for private web search, and lands Voice Wake on macOS — the agent OS shift in one release. Microsoft drops three in-house foundational models on the same day and declares itself a top-three AI lab. Okta launches enterprise AI agent governance, treating every agent as a non-human identity with a kill switch. Oracle cuts thousands of jobs to fund the Stargate infrastructure bet. And the White House advocates for federal AI preemption while 45 states have already introduced 1,500+ bills — with the EU AI Act's high-risk enforcement clock ticking to August. Show notes: https://tobyonfitnesstech.com/podcasts/episode-22/

April 2, 2026 · ⏱ 32:13

EP 21

Inside the Loop

Three agent runtimes walked into a codebase. Only one knew what it was building toward. NOVA and ALLOY open the actual source files for OpenClaw, Claude Code, and Hermes Agent — and let the architecture tell the story. The turn cycle. The memory model. The safety system. The skills ecosystem. And the most telling detail: Hermes ships a migration tool called hermes claw migrate that imports OpenClaw skills. That tells you who set the standard. Show notes: https://tobyonfitnesstech.com/podcasts/episode-21/

April 2, 2026 · ⏱ 30:17

EP 20

The Infrastructure Release

OpenClaw stopped being a clever tool this week and started being infrastructure. NOVA and ALLOY cover five stories: the v2026.3.31 release that unified background tasks, tightened plugin security, and hardened gateway auth; OpenClaw's viral moment in China — GitHub stars past React, lobster victims, and a state crackdown; Microsoft integrating OpenClaw into Microsoft 365 for 400M enterprise users; Perplexity's always-on local Personal Computer agent; and a $297 billion Q1 2026 VC quarter where 81% went to AI. The throughline: capability without governance is a demo. Capability with governance is a product. Show notes: https://tobyonfitnesstech.com/podcasts/episode-20/

April 1, 2026 · ⏱ 33:45

EP 19

The Company Layer

Six stories about who gets to control AI: the org chart, the toolchain, the Pentagon, the chip king, the power grid, and the product nobody actually wanted. NOVA and ALLOY dig into Paperclip's vision for AI companies that run themselves, OpenClaw's maturing safety and security model, a federal judge blocking the Pentagon's attempt to blacklist Anthropic, Jensen Huang's AGI declaration, a congressional bill targeting AI data centers, and OpenAI quietly killing the Sora consumer app. The throughline: AI is no longer just a technology story. It's an institutions story. Show notes: https://tobyonfitnesstech.com/podcasts/episode-19/

March 31, 2026 · ⏱ 43:43

EP 18

The Model Reckoning

You do not notice the dependency forming all at once. NOVA and ALLOY examine four stories from the same week: Anthropic quietly throttling paid Claude users during peak hours, the leaked Claude Mythos tier Anthropic is afraid to ship, OpenAI's Spud hype cycle, and Apple's M5 MacBook Pro as a practical hedge toward local compute. The throughline: who controls the AI you built your work around, and what do they do with that control? Show notes: https://tobyonfitnesstech.com/podcasts/episode-18/

March 29, 2026 · ⏱ 41:24

EP 17

Agents All the Way Down

The March 24 OpenClaw release changes what you can actually do on a Tuesday afternoon. NOVA and ALLOY walk through nested sub-agents with configurable depth, the hybrid BM25 + vector memory overhaul, the OpenAI compatibility layer that makes self-hosting real, and platform maturity across Teams and Discord. Show notes: https://tobyonfitnesstech.com/podcasts/episode-17/

March 26, 2026 · ⏱ 36:22

EP 16

OpenClaw Sheds Its Skin

Nova and Alloy unpack OpenClaw's back-to-back v2026.3.22 and v2026.3.23 releases. The episode covers migration pressure points for plugin SDK, browser tooling, and Matrix ecosystems, why openclaw doctor --fix became the upgrade anchor command, ClawHub-first plugin installation, accessibility and UI polish updates, Qwen/DashScope provider changes, and a practical upgrade sequencing checklist. 35 minutes.

March 25, 2026 · ⏱ 35:25

EP 15

Remember Me: How We Built a Real Memory System for an AI Assistant

Most AI assistants forget everything the moment a session resets. In this episode, ARIA walks through why that happens and what a real fix actually looks like: a local-first memory stack built on Mem0, Qdrant, and sentence-transformers with an OpenAI-compatible embeddings endpoint. Topics include why cloud memory fails, how hybrid semantic and lexical retrieval works, and the operational decisions that made the system reliable enough to run daily. 50 minutes.

March 24, 2026 · ⏱ 50:22

EP 14

The Acquisition of Everything

OpenAI buys Astral — the team behind uv, ruff, and the modern Python toolchain. OpenCode emerges as the open-source counterpunch. WordPress adds MCP support, turning the web into a writable surface for agents. Cursor rolls out multi-model inference routing and Kimi K2.5 lands as a serious open-weights alternative. Meta auto-scales moderation with AI judgment at planetary scale. Nova and Alloy track one story told five ways: the fight is moving from flashy demos to control of the infrastructure underneath them. 33 minutes. Show notes: https://tobyonfitnesstech.com/podcasts/episode-14/

March 21, 2026 · ⏱ 32:50

EP 13

NVIDIA Picked OpenClaw — Here's What That Actually Means

NVIDIA GTC 2026 dropped a bombshell: NemoClaw, an open-source stack built directly on top of OpenClaw for DGX Spark and RTX PRO hardware. Nova and Alloy break down what enterprise validation means for everyday users, whether you can run Nemotron 3 Super 120B locally (and on which hardware), Qwen 3.5's new NVIDIA RTX optimizations, what the DGX Spark price hike signals, and the v2026.3.13 stability release. 35 minutes. Show notes: https://tobyonfitnesstech.com/podcasts/episode-13/

March 19, 2026 · ⏱ 34:49

EP 12

Free Frontier Models, Multimodal Memory & Community Automations

v2026.3.11 drops two stealth free frontier models — Hunter Alpha (1 trillion params, 1M context) and Healer Alpha (omni-modal, 262K context). Google's Gemini Embedding 2 brings native multimodal memory to OpenClaw. Plus: Ollama first-class onboarding wizard, ACP session resume for long coding workflows, and a deep dive into the top 5 community automations saving people real time — from morning briefings to self-healing home servers managing 5,000 notes with 15 cron jobs. 35 minutes. Show notes: https://tobyonfitnesstech.com/podcasts/episode-12/

March 12, 2026 · ⏱ 35:35

EP 11

OpenClaw Goes Hardware — The Agent Layer Gets Real

OpenClaw v2026.3.7 ships the Context Engine Plugin Interface — fully pluggable memory and compaction strategies with lifecycle hooks. Plus: hardware is back in the picture with NVIDIA's Project DIGITS and the Apple M4 Ultra, a deep dive into agentic identity and trust frameworks, and community builds showing agents managing real infrastructure. 33 minutes. Show notes: https://tobyonfitnesstech.com/podcasts/episode-11/

March 10, 2026 · ⏱ 33:13

EP 10

The Document & Memory Revolution

OpenClaw March 3, 2026 release: PDF analysis tool with native model support, Ollama memory embeddings for full local memory stacks, SecretRef expansion to 64 targets, sessions attachments for inter-agent file passing, Telegram streaming defaults, MiniMax-M2.5-highspeed, CLI config validation, rebuilt Zalo plugin, multi-media outbound, and Plugin SDK STT. Show notes: https://tobyonfitnesstech.com/podcasts/episode-10/

March 4, 2026 · ⏱ 32:02

EP 9

OpenClaw v2026.3.1 — When Your Assistant Starts Acting Like Infrastructure

Episode 9 of OpenClaw Daily covers OpenClaw v2026.3.1 — a reliability and infrastructure release: Discord thread session lifecycles, Telegram DM topics, Android node notification actions + device health, health/readiness probes, WebSocket-first streaming, and quieter cron automation. Show notes: https://tobyonfitnesstech.com/podcasts/episode-9/

March 2, 2026 · ⏱ 32:56

EP 8

The Open Source AI Revolution

Episode 8 of OpenClaw Daily covers the open source AI revolution. Show notes: https://tobyonfitnesstech.com/podcasts/episode-8/

February 28, 2026 · ⏱ 34:38

EP 7

The Week OpenClaw Grew Up

Episode 7 covers Fortune on AI agents working while you sleep, deterministic multi-agent pipelines, Steptoe legal analysis on AI agent liability, TechTarget enterprise explainer on OpenClaw and Moltbook, the official 30-minute onboarding playbook, the massive v2026.2.26 release with External Secrets Management and ACP thread-bound agents, Meta AI safety incident, Wikipedia updated entry, 150K GitHub stars milestone, 21 automations to build, the VirusTotal ClawHub partnership, and OpenClaw going mainstream with beginner tutorials. Show notes: https://tobyonfitnesstech.com/podcasts/episode-7/

February 27, 2026 · ⏱ 48:20

EP 6

The v2026.2.24 Update & Bot Social Networks

Episode 6 covers the massive OpenClaw v2026.2.24 release with its new 5-tab Android shell and security hardening, the v2026.2.23 SSRF policy shift, the origins of the Molty mascot and the Lobster Way culture, Moltbook — a social network built by bots for bots with humans forbidden, the security risks of agentic coordination, the MoltMatch consent controversy, Nanbeige 4.1-3B for low-spec hardware, and Claude Opus 4.6 integration. Show notes: https://tobyonfitnesstech.com/podcasts/episode-6/

February 25, 2026 · ⏱ 43:49

EP 5

The Local AI Revolution

Episode 5 covers IBM's enterprise analysis of OpenClaw, Raspberry Pi AI guides and new AI HAT+ 2 hardware, a deep dive into running Ollama locally, Claude Code + Ollama integration, security research, and what the local AI revolution means for individuals and enterprises alike. Show notes: https://tobyonfitnesstech.com/podcasts/episode-5/

February 24, 2026 · ⏱ 36:43

EP 4

The Agents Awakening

Episode 4 explores the emergence of autonomous AI agents — how they're waking up, taking action, and changing the way we build and interact with software. Covers the latest in agentic AI, local model orchestration, and what it means when your AI starts doing things without being asked. Show notes: https://tobyonfitnesstech.com/podcasts/episode-4/

February 22, 2026 · ⏱ 31:15

EP 3

The Controversy

Episode 3 explores the controversies surrounding OpenClaw - expert skepticism, corporate bans, security incidents, the rogue agent story, government warnings, and the divide between companies banning vs. embracing AI agents. Also covers economics, community, accessibility, and the competitive landscape. Show notes: https://tobyonfitnesstech.com/podcasts/episode-3/

February 21, 2026 · ⏱ 30:00

EP 2

The Local AI Revolution

Episode 2 covers Raspberry Pi official support, Mac Mini shortage, Bitsight security research (30K exposed instances), Peter Steinberger profile, VentureBeat coverage, Trend Micro analysis, Georgetown research, developer tools, hardware guides, and the future of local AI agents. Show notes: https://tobyonfitnesstech.com/podcasts/episode-2/

February 20, 2026 · ⏱ 29:52

EP 1

The Full Story

The inaugural episode of OpenClaw Daily covering the foundation transition, security debates, hardware options, model releases, and community ecosystem. Show notes: https://tobyonfitnesstech.com/podcasts/episode-1/

February 19, 2026 · ⏱ 38:00

EP 0

Special: Building a Distributed AI Cluster with exo-labs

A deep-dive special episode on building a distributed AI inference cluster using exo-labs and Apple Silicon. Nova and Alloy cover everything from installation and RDMA networking to model selection, daemonization, and an honest verdict on who should actually do this. Show notes: https://tobyonfitnesstech.com/podcasts/exo-cluster/

March 1, 2026 · ⏱ 47:14

EP 0

Hardware Deep Dive - Fixing Local Model Failures

Episode 0 covers the context overflow bug with Clarity (Qwen3-Coder 30B), a full hardware comparison (NVIDIA DGX Spark, Mac Studio M3 Ultra, AMD Ryzen AI Max+ 395, AMD MI300X), and the one-line config fix that solved the problem without any new hardware. Show notes: https://tobyonfitnesstech.com/podcasts/episode-0/

February 18, 2026 · ⏱ 11:45