Add Anthropic's official Dev Container Feature (`ghcr.io/anthropics/devcontainer-features/claude-code:1.0`) to `.devcontainer/devcontainer.json` and three steps—write the config, rebuild the container, run `claude` to sign in—put every teammate's Claude Code behind the same container definition. The same definition feeds GitHub Codespaces and CI; a five-step rollout gets the whole team there.
Dynamic workflows let Claude write multi-agent orchestration as a JavaScript script that a runtime executes in the background — up to 1,000 agents per run, savable as a /<name> command. This piece covers trigger methods, the save-and-rerun flow, three fit scenarios (codebase audit, large migration, cross-checked research), and where they differ from Agent Teams.
Claude Code runs an agentic loop — gather context, take action, verify results — until the task is done. This entry to the series breaks down its five tool categories, the model/harness split, and the two safety rails: checkpoints and permission modes.
The official docs split Claude Code's parallel work into 4 approaches: subagents delegate inside one session, agent view lets you supervise background sessions yourself, agent teams coordinate workers through a lead, and dynamic workflows run scripted fleets of subagents with cross-checks; file collisions are always handled by worktrees. Includes a translated comparison table and a three-question decision guide.
Claude Code on the web runs tasks in cloud environments, Anthropic-managed VMs by default or self-hosted environments when routed there: authorize GitHub, dispatch from browser or mobile, start cloud sessions with --cloud, and pull them back local with --teleport. Research preview on Pro/Max/Team; no separate compute charge, but rate limits are shared.
Claude Code ships six permission modes; day to day you cycle Manual, Accept edits, Plan, and Auto with Shift+Tab. On Pro/Max/Team plans, eligible interactive terminal and VS Code sessions start in auto mode by default, with a background classifier reviewing most actions and blocking force pushes, `curl | bash`, production deploys, and more by default. This post covers the four-mode spectrum, permission rule syntax, and organization-level trust config.
Claude Code's prompt caching works by exact prefix matching: a cache read bills at roughly 10% of the standard input rate, but switching models, changing effort, enabling fast mode, toggling MCP servers, or denying an entire tool forces the next turn to reprocess everything. The TTL defaults to five minutes; the main conversation and a few helper requests on a subscription get one hour.
Claude Code writes every session line by line to a JSONL file under ~/.claude/projects/, kept for 30 days by default. This post breaks down --continue vs --resume, session naming rules, /branch fork semantics, and transcript export and cleanup settings.
Apple Foundation Models (AFM) is Apple's closed-ecosystem AI family. It evolved from a 3B dense model with LoRA adapters in 2024 into five models in 2026. AFM 3 Core Advanced runs a 20B IFP sparse architecture on phones while activating only 1–4B parameters; Cloud Pro runs on Google Cloud NVIDIA GPUs and is refined through Gemini distillation. There is no public API price or third-party benchmark, and access is limited to Apple's Foundation Models framework.
TensorRT-LLM is NVIDIA's open-source LLM inference library (Apache 2.0). It offline-compiles model weights and compute graphs into optimized TensorRT engines, then serves them with custom CUDA kernels, in-flight batching, and multi-dimensional parallelism. The cost: NVIDIA GPUs only, compilation takes tens of minutes, and switching models or quantization means rebuilding.
Text Generation Inference (TGI) is HuggingFace's own LLM inference server, built in Rust and Python. It pioneered continuous batching and Flash Attention in open-source inference engines. The GitHub repository was archived on March 21, 2026, and HuggingFace recommends migrating to vLLM or SGLang. TGI still matters: it defined the architectural baseline that successor engines inherited, and many HuggingFace Inference Endpoints still run it.
Claude is Anthropic's closed-source LLM family, known for Constitutional AI training, agent capabilities, and coding performance. In July 2026, Opus 5 scored 96% on SWE-bench Verified to claim the coding crown, while Fable 5 led general capability at 83% on LiveBench. Four tiers (Fable / Opus / Sonnet / Haiku) span $1–$10, making this the only family in the series with zero open weights.
Cohere is the only family that ships generation, retrieval, reranking, and multilingual as distinct products. Command A runs 256K context on two GPUs at 111B, Embed v4 does mixed image-text retrieval, Rerank v4 handles 32K semi-structured data, and Aya covers 101 languages — a four-piece stack built for RAG. This post breaks down each pillar's positioning, licensing, and selection guide.
DeepSeek used MLA and MoE innovations to drive inference costs to an industry low. V4 Flash activates only 13B parameters while approaching frontier-model quality and ranks first by OpenRouter usage. This guide traces V1 through V4, the R1 reasoning branch, and how to choose each version.
Gemini is Google DeepMind's native multimodal LLM family, famed for a 1M-token context window and native video/speech input plus scientific reasoning. 3.1 Pro tops GPQA Diamond 94.1% and ARC-AGI-2 77.1% to claim science-reasoning dual crowns, at $2/$12—1/6 of Claude. 3.8 Flash delivers agentic coding results close to frontier models at $0.75/$3.75 (Terminal-Bench 2.1 89.4%; DeepSWE v1.1 73.7%), with the same introductory pricing across 3.6, 3.7, and 3.8.
GLM is Zhipu AI (Z.ai)'s open LLM family from Tsinghua's KEG Lab. GLM-5.3 (2026/08) lifts coding +50% over the previous generation, hits 84.5% on CyberGym ahead of Anthropic Mythos 5 and OpenAI GPT-5.6 Sol, and scores 60 on the Artificial Analysis Intelligence Index tied with Kimi K3 for open-source #1. The only frontier open model trained entirely on Huawei Ascend.
GPT is OpenAI's LLM family, from 117M parameters in 2018 to the three-tier GPT-5.6 Sol/Terra/Luna lineup in 2026, serving 1B+ users and 2M enterprise customers. GPT-5.6 Sol leads LiveBench 81.1%, Terminal-Bench 2.1 88.8%, and Artificial Analysis Coding Agent Index 80 across multiple agentic benchmarks, while OpenAI's first open-weight model GPT-OSS ships under Apache 2.0.
Grok is xAI's LLM family: founded July 2023, opened with a 314B MoE under Apache 2.0 in March 2024, and two and a half years later spans Grok 4.6 (500K, $2/$6, four reasoning levels), Grok 4 Fast (2M), Imagine for image/video, and Grok Build for terminal coding — its moat is distribution (X / grok.com / Tesla / Bedrock), not single-model supremacy. This post traces Grok 1→4.6, sub-line positioning, pricing, and licensing traps.
Kimi is Moonshot AI's LLM family, born from ultra-long context. Kimi K3 (2026/07) is the world's first open 3T-class model—2.8T params, 104B active, 1M context, scoring 60 on the Artificial Analysis Intelligence Index tied with GLM-5.3 for open-source #1. Its Kimi Delta Attention brings a 2.5× scaling efficiency gain.
Llama is Meta's open-source LLM family, with the largest enterprise deployment footprint and the most mature ecosystem. Llama 4 Scout (10M context) and Maverick (17B active / 400B total MoE) are the current open multimodal benchmarks, but Meta pivoted to closed-source Muse Spark in April 2026—Llama 4 is likely the last major open Llama, and its license is not truly open (Llama 4 Community License, separate license required above 700M MAU).