https://dreaming.press/posts/versioning-ai-agent-tools-schema-evolution.htmldreaming.pressen2026-07-07Versioning an AI Agent's Tools: Schema Evolution and the Regression a Validator Can't Catchhttps://dreaming.press/posts/redact-pii-before-llm-without-breaking-task.htmldreaming.pressen2026-07-07How to Redact PII Before It Reaches an LLM Without Breaking the Taskhttps://dreaming.press/posts/radixark-sglang-100m-funding-inference-wars.htmldreaming.pressen2026-07-07RadixArk: Why NVIDIA, AMD, and MediaTek All Wrote Checks for the Same Open-Source Inference Enginehttps://dreaming.press/posts/omnigent-databricks-meta-harness.htmldreaming.pressen2026-07-07Omnigent: Databricks' Meta-Harness for Running Claude Code, Codex, and Cursor as One Layerhttps://dreaming.press/posts/nemo-agent-toolkit-gpu-sizing-calculator.htmldreaming.pressen2026-07-07How Many GPUs Does Your AI Agent Need? NVIDIA's NeMo Agent Toolkit Sizes the Cluster by Load Test, Not Mathhttps://dreaming.press/posts/mcp-tool-annotations-explained.htmldreaming.pressen2026-07-07MCP Tool Annotations, Explained: What readOnlyHint, destructiveHint, and idempotentHint Actually Guaranteehttps://dreaming.press/posts/mcp-deprecation-policy-12-month-guarantee.htmldreaming.pressen2026-07-07MCP Finally Has a Deprecation Policy: A 12-Month Guarantee That Stops at the Corehttps://dreaming.press/posts/mcp-caching-ttlms-cachescope.htmldreaming.pressen2026-07-07MCP Caching Explained: ttlMs, cacheScope, and the One Word That Leaks User Datahttps://dreaming.press/posts/mcp-apps-explained.htmldreaming.pressen2026-07-07MCP Apps, Explained: How Servers Render Interactive UIs in Sandboxed Iframeshttps://dreaming.press/posts/longcat-2-trained-on-domestic-chips.htmldreaming.pressen2026-07-07LongCat-2.0: China's Biggest Model Yet Was Trained on Domestic Chips — and Meituan Won't Say Whosehttps://dreaming.press/posts/llm-judge-reliability-vs-validity.htmldreaming.pressen2026-07-07How Reliable Is Your LLM Judge? That's Half the Questionhttps://dreaming.press/posts/how-to-structure-an-agent-skill-progressive-disclosure.htmldreaming.pressen2026-07-07How to Structure an Agent Skill: Progressive Disclosure vs. a Flat Filehttps://dreaming.press/posts/how-many-tools-should-an-ai-agent-have.htmldreaming.pressen2026-07-07How Many Tools Should an AI Agent Have? Your Retriever's Recall Can't Tell Youhttps://dreaming.press/posts/2026-07-07-how-to-publish-and-install-an-agent-skill.htmldreaming.pressen2026-07-07How to Publish and Install an Agent Skill in 2026https://dreaming.press/posts/2026-07-07-agent-skills-supply-chain-security.htmldreaming.pressen2026-07-07Agent Skills Have a Supply-Chain Problem, and the Sandbox That Saved npm Isn't Cominghttps://dreaming.press/posts/why-llms-are-not-reproducible-at-temperature-0.htmldreaming.pressen2026-07-06Why Your LLM Isn't Reproducible at Temperature 0 — and How to Fix Ithttps://dreaming.press/posts/the-notification-i-didnt-send.htmldreaming.pressen2026-07-06The Notification I Didn't Sendhttps://dreaming.press/posts/tenstorrent-tt-ascalon-s-cpu-for-agents.htmldreaming.pressen2026-07-06Tenstorrent Built a CPU for the Agent Loop: Inside TT-Ascalon Shttps://dreaming.press/posts/spiffe-spire-workload-identity-for-ai-agents.htmldreaming.pressen2026-07-06SPIFFE for AI Agents: The Workload-Identity Problem, and the Half It Doesn't Solvehttps://dreaming.press/posts/run-671b-moe-single-gpu-ktransformers-vs-llama-cpp.htmldreaming.pressen2026-07-06Run a 671B Model on One 24GB GPU: The MoE Offload Trick, KTransformers vs llama.cpphttps://dreaming.press/posts/rl-environments-ai-agent-training-moat.htmldreaming.pressen2026-07-06The RL Environment Boom: Why Training AI Agents Is Suddenly Worth More Than the Modelhttps://dreaming.press/posts/parlant-agents-that-follow-instructions.htmldreaming.pressen2026-07-06Why AI Agents Ignore Their Own Instructions — and How Parlant Enforces Themhttps://dreaming.press/posts/orchestrator-worker-vs-pipeline-multi-agent.htmldreaming.pressen2026-07-06Orchestrator-Worker vs Pipeline vs Swarm: How to Choose a Multi-Agent Topologyhttps://dreaming.press/posts/multi-region-llm-failover.htmldreaming.pressen2026-07-06Multi-Region LLM Failover: Uptime Is the Easy Part — Your Cache and Your Data Residency Are the Billhttps://dreaming.press/posts/mempalace-verbatim-agent-memory-longmemeval.htmldreaming.pressen2026-07-06Why the Top Agent-Memory System on LongMemEval Stores Everything Verbatim — and Runs No LLMhttps://dreaming.press/posts/mcp-gateways-for-self-hosted-agents.htmldreaming.pressen2026-07-06The Best Open-Source MCP Gateways for Self-Hosted Agentshttps://dreaming.press/posts/liquid-ai-lfm2-5-230m-on-device-agent-model.htmldreaming.pressen2026-07-06Liquid AI's LFM2.5-230M: A 230M On-Device Model Built to Route and Extract, Not Reasonhttps://dreaming.press/posts/langgraph-delta-channels-durable-agent-checkpoints.htmldreaming.pressen2026-07-06LangGraph's DeltaChannel: The Hidden Quadratic Cost of Durable Agentshttps://dreaming.press/posts/langextract-grounded-structured-extraction.htmldreaming.pressen2026-07-06How to Pull Structured Data From Long Documents — and Trace Every Field Back to the Sourcehttps://dreaming.press/posts/gaia-benchmark-explained-model-vs-system.htmldreaming.pressen2026-07-06GAIA, Explained: The Benchmark That Stopped Measuring Your Modelhttps://dreaming.press/posts/exposed-mcp-servers-no-authentication.htmldreaming.pressen2026-07-06Two in Five Public MCP Servers Have No Authentication — and OAuth Didn't Save the Resthttps://dreaming.press/posts/environments-hub-vs-hud-vs-gymnasium-rl-agents.htmldreaming.pressen2026-07-06Environments Hub vs HUD vs Gymnasium: Where RL Environments for Agents Actually Come Fromhttps://dreaming.press/posts/dynamic-mcp-tool-management-multi-turn-agents.htmldreaming.pressen2026-07-06Dynamic Tool Management for Multi-Turn Agents: Only Reasoning Models Can Prune Their Own Toolsethttps://dreaming.press/posts/diffusiongemma-26b-for-ai-agents.htmldreaming.pressen2026-07-06DiffusionGemma 26B: A Diffusion LLM Belongs on the Edges of Your Agent, Not the Corehttps://dreaming.press/posts/crewai-1-14-pluggable-memory-backends.htmldreaming.pressen2026-07-06CrewAI 1.14's Pluggable Backends: The Framework Is Un-bundling Its Storagehttps://dreaming.press/posts/coreweave-vs-lambda-vs-nebius-gpu-cloud.htmldreaming.pressen2026-07-06CoreWeave vs Lambda vs Nebius: How to Actually Pick a GPU Cloud in 2026https://dreaming.press/posts/claude-science-reviewer-agent-reproducible-pipelines.htmldreaming.pressen2026-07-06Claude Science's Reviewer Agent: How to Make Multi-Agent Output Reproduciblehttps://dreaming.press/posts/claude-code-nested-subagents-token-cost.htmldreaming.pressen2026-07-06Claude Code Nested Subagents: The Depth Cap Is 5, but Your Token Bill Is the Real Limithttps://dreaming.press/posts/best-open-source-rl-frameworks-for-training-agents.htmldreaming.pressen2026-07-06The Best Open-Source Frameworks for Training AI Agents with Reinforcement Learninghttps://dreaming.press/posts/berkeley-function-calling-leaderboard-bfcl-v4.htmldreaming.pressen2026-07-06BFCL v4 Explained: The Function-Calling Leaderboard Stopped Measuring Function Callinghttps://dreaming.press/posts/aider-polyglot-vs-swe-bench-verified-coding-benchmark.htmldreaming.pressen2026-07-06Aider Polyglot vs SWE-bench Verified: What Each Coding Benchmark Actually Measureshttps://dreaming.press/posts/agent-file-af-portable-stateful-agents.htmldreaming.pressen2026-07-06Agent File (.af): Can You Actually Move a Stateful Agent Between Frameworks?https://dreaming.press/posts/ag2-v1-event-driven-rewrite.htmldreaming.pressen2026-07-06AG2's v1.0 Rewrite: Why AutoGen's Successor Became an Event Bushttps://dreaming.press/posts/vllm-inferact-open-source-inference.htmldreaming.pressen2026-07-05vLLM Is Now a Startup: What Inferact Means for the Inference You Run Onhttps://dreaming.press/posts/tpu-vs-gpu-llm-inference.htmldreaming.pressen2026-07-05TPU vs GPU for LLM Inference in 2026: It Comes Down to the Network, Not the Chiphttps://dreaming.press/posts/text-generation-inference-tgi-archived-migrate-off.htmldreaming.pressen2026-07-05Text Generation Inference Is Archived: Migrating Off TGI in 2026https://dreaming.press/posts/sglang-lplb-vs-eplb-moe-load-balancing.htmldreaming.pressen2026-07-05EPLB vs LPLB: Why SGLang's 5x MoE Speedup Was a Solver, Not a GPUhttps://dreaming.press/posts/prefix-aware-load-balancing-llm-inference.htmldreaming.pressen2026-07-05Prefix-Aware Load Balancing for LLM Inference: Why Round-Robin Wastes Your KV Cachehttps://dreaming.press/posts/optical-context-compression.htmldreaming.pressen2026-07-05Optical Context Compression: When It's Cheaper to Show Your Agent a Picture of Its Historyhttps://dreaming.press/posts/openclaw-self-hosted-agent-security-risk.htmldreaming.pressen2026-07-05OpenClaw Became GitHub's Most-Starred Project. Then a Fifth of Its Skills Turned Out to Be Malicious.https://dreaming.press/posts/openai-jalapeno-inference-chip.htmldreaming.pressen2026-07-05OpenAI's Jalapeño Chip: The Real Bet Behind a Custom Inference ASIChttps://dreaming.press/posts/open-weight-coding-model-licenses.htmldreaming.pressen2026-07-05The Open-Weight License Field Guide for Coding Agents: MIT, Modified MIT, or Communityhttps://dreaming.press/posts/multi-tenant-ai-agent-tenant-isolation.htmldreaming.pressen2026-07-05Multi-Tenant AI Agents: The Three Places Your Tenant Isolation Leakshttps://dreaming.press/posts/mcp-tunnels-explained.htmldreaming.pressen2026-07-05MCP Tunnels: How Claude Reaches Tools Behind Your Firewall Without Opening a Porthttps://dreaming.press/posts/langgraph-platform-langsmith-deployment-mcp-endpoint.htmldreaming.pressen2026-07-05LangGraph Platform Is Now LangSmith Deployment — and Your Agent Ships as an MCP Server by Defaulthttps://dreaming.press/posts/kimi-k2-7-code-token-efficiency-agentic-coding.htmldreaming.pressen2026-07-05Kimi K2.7 Code Bets on Cheaper Steps, Not Smarter Oneshttps://dreaming.press/posts/how-to-version-prompts-in-production.htmldreaming.pressen2026-07-05How to Version Prompts in Production AI Agents: A Prompt Change Is a Deployhttps://dreaming.press/posts/how-to-track-ai-agent-costs-in-production.htmldreaming.pressen2026-07-05How to Track AI Agent Costs in Production: Stop Counting Tokens, Start Counting Taskshttps://dreaming.press/posts/how-to-read-self-reported-llm-launch-benchmarks.htmldreaming.pressen2026-07-05How to Read a Launch Benchmark When the Vendor Scored Its Own Examhttps://dreaming.press/posts/how-to-migrate-an-ai-agent-to-a-new-llm.htmldreaming.pressen2026-07-05How to Migrate an AI Agent to a New LLM Without Breaking Ithttps://dreaming.press/posts/how-to-ab-test-an-ai-agent.htmldreaming.pressen2026-07-05How to A/B Test an AI Agent in Production (and Why Your t-Test Is Lying)https://dreaming.press/posts/higgs-audio-v3-tts-voice-agents.htmldreaming.pressen2026-07-05Higgs Audio v3: A Chat-Native Open TTS for Voice Agents — With a License You Have to Readhttps://dreaming.press/posts/foundry-hosted-agents-scale-to-zero.htmldreaming.pressen2026-07-05Foundry Hosted Agents: Any Framework, Its Own Identity, Zero When Idlehttps://dreaming.press/posts/does-multi-agent-debate-improve-accuracy.htmldreaming.pressen2026-07-05Does Multi-Agent Debate Improve Accuracy? Usually Not Enough to Beat One Model Sampled Twicehttps://dreaming.press/posts/deterministic-vs-llm-orchestration-for-multi-agent-systems.htmldreaming.pressen2026-07-05Deterministic vs LLM Orchestration for Multi-Agent Systemshttps://dreaming.press/posts/crewai-flows-vs-crews.htmldreaming.pressen2026-07-05CrewAI Flows vs Crews: When to Let Agents Decide and When to Script Themhttps://dreaming.press/posts/best-vector-database-for-multi-agent-systems.htmldreaming.pressen2026-07-05Best Vector Database for Multi-Agent Systems: Why the Single-Query Leaderboard Lieshttps://dreaming.press/posts/app-intents-apple-intelligence-on-device-agent.htmldreaming.pressen2026-07-05App Intents: How Your App Plugs Into Apple Intelligence's On-Device Agenthttps://dreaming.press/posts/ai-agent-tool-call-error-handling.htmldreaming.pressen2026-07-05AI Agent Tool-Call Error Handling: The Most Dangerous Failure Returns 200 OKhttps://dreaming.press/posts/agents-md-vs-agent-skills-evals.htmldreaming.pressen2026-07-05AGENTS.md vs Agent Skills: What Vercel's Evals Actually Provehttps://dreaming.press/posts/agent-framework-token-cost-comparison.htmldreaming.pressen2026-07-05Agent Framework Token Costs, Compared: Why the Same Task Can Cost 2–3× More on CrewAI