These are practical first configurations for common workflows. Treat them as a testable baseline, then measure successful work, review effort, and total cost.
A self-hosted coding loop for developers who want agent help without routing every prompt through a cloud API — Continue or Cline in the editor, Ollama or MLX on the Mac, and optional GPU sizing when a desktop card beats Apple Silicon.
Solo developers, privacy-conscious builders, and hobbyists who accept local ops work in exchange for data control.
Suggested stack
Continue or Cline in VS Code or Cursor for the editor surface — pick assistive chat (Continue) or an autonomous loop (Cline).
Ollama on port 11434 (or MLX on Apple Silicon, LM Studio on 1234, llama.cpp server on ~8080) with a quant at Q4_K_M or better for tool-calling agents.
Set OLLAMA_CONTEXT_LENGTH or num_ctx to 16k–32k before blaming the model for “forgetting” files; verify the endpoint with curl before wiring harnesses.
Optional hybrid: escalate ambiguous refactors to a usage-capped cloud model while routine edits stay local.
Tradeoffs
Local models need operator time for pulls, context tuning, and quant trade-offs — Q2/Q3 quants often break tool schemas.
Aider needs ollama_chat/model, not bare ollama/; OpenCode expects an OpenAI-compatible /v1 base URL.
A solo local stack only wins when review discipline stays intact; privacy does not remove the need to read diffs.
A fast-moving default for small teams: one primary agent surface (Cursor or Claude Code), a usage-aware cloud model tier, and an optional local fallback for bursts or privacy-sensitive slices.
Seed-stage and Series A engineering teams that need speed without letting agent spend or outages block delivery.
Suggested stack
Cursor for continuous editor work, or Claude Code when terminal delegation and long-horizon tasks dominate.
A documented model routing rule: frontier for ambiguous cross-system work, cheaper tier for tests, docs, and bounded fixes.
Optional local fallback (Ollama + Cline or Aider) for outages, quota caps, or a sanitized practice repo.
One AGENTS.md source of truth, branch protections intact, and a shared review checklist before merge.
Tradeoffs
Hybrid routing adds prompt and config maintenance — document which tasks stay cloud vs local.
Dual-running Cursor and Claude Code on the same branch without worktrees creates collision risk.
Startup velocity dies if generated patches skip review; measure accepted patch rate, not prompt count.
A procurement-aware pattern for regulated teams: Copilot or Cursor on the enterprise path, MCP allowlisting, SSO lifecycle, and explicit human review gates tied to the rollout checklist.
Security, platform, and engineering leaders rolling out coding agents under DPA, residency, and audit requirements.
Suggested stack
GitHub Copilot Business/Enterprise or Cursor Teams/Enterprise as the managed seat path with SSO/SCIM and org-wide policy controls.
MCP and extension allowlist: fail closed on unknown servers, review folder and network scope before install, log tool calls.
CLAUDE Code or OpenAI Codex only after the same security review as the editor — each surface can differ on retention and training defaults.
Human review gate on every agent output: plan, tool log, diff, tests, and rollback path documented in the rollout guide.
Tradeoffs
Enterprise seats plus realistic agent usage often exceed the sticker price — budget seat baseline and metered overage separately.
SSO on the IDE plugin does not automatically cover CLI, cloud agent, or API paths; approve each surface.
Governance overhead is real; the payoff is fewer shadow seats and auditable tool permissions.
