Compare
Cross-vendor comparisons readers can't get from any single vendor's docs. Same shape per matchup — where each wins, where each lags, an honest take at the bottom — so the "which fits my job" answer doesn't require reading four vendor sites.
Verification mix 6 sourced 6 entries total
§ 7.1 WHICH AGENT SHAPE? OpenClaw vs MCP-based stacks OpenClaw is a self-hosted persistent agent runtime. MCP-based stacks are a different shape — host application + protocol + servers. Where each wins, where each loses, when to switch. Open comparison → § 7.2 WHICH CLI? CLI coding agents — Claude Code · Codex CLI · Gemini CLI · Copilot CLI Four shell-native AI coding CLIs. Same shape, different identities. Where each wins, where each lags, when to switch — and why most thoughtful people end up using two. Open comparison → § 7.3 WHICH M365 PATH? M365 extensibility paths — Copilot Studio · Declarative Agents · Custom Engine Agents Three practical paths to build for Microsoft 365 Copilot. Where each fits, what each costs the builder and the end user, and the canonical taxonomy your readers will see on learn.microsoft.com. Open comparison → § 7.4 WHICH API / PLATFORM? Direct model APIs — Claude API · Gemini API · Microsoft Foundry Three direct model API surfaces a production builder picks between today: Claude API · Gemini API · Microsoft Foundry. OpenAI's own API is deliberately outside Claw's scope; use Foundry for Azure-governed GPT-5, or OpenAI's docs for api.openai.com. Open comparison → § 7.5 WHO RUNS YOUR AGENT? Agent platforms — managed runtimes and open frameworks Four cross-vendor agent platforms a production builder picks between when deciding where the agent loop runs. Microsoft Foundry Agent Service · Google Vertex AI Agents · OpenAI Agents SDK · Microsoft Copilot Studio. Open comparison → § 7.6 WHERE TO PLUG IN MCP? MCP hosts and clients — where you plug an MCP server in Eight applications and runtimes that can connect to MCP servers — a chat desktop, a CLI, an IDE, a third-party AI editor, a low-code agent builder, two managed runtimes, and an autonomous cloud agent. Where each speaks MCP cleanly, where each lags, and which one runs tool calls without asking. Open comparison →
More comparisons land as Sush ships them — framework approaches · MCP auth patterns · cost calculators.