Reference — examples by number

This page is the completeness surface — every shipped example listed by number, with a one-line summary. It exists so a reader who knows the file number can find it. It is not the primary discovery surface; for that, go to Lighthouse or Foundation.

There are 47 shipped examples. The first 32 are entry-level demonstrations of single SDK capabilities. The last 15 are lighthouse-grade walkthroughs with sibling READMEs. The example catalogue and positioning doc is the canonical contract.

Tier 1 — Quickstart

#	Example	Tier
01	hello_agent — `pip install && python` → working agent	1 (Quickstart)

Tier 2 — Foundation

#	Example	Capability
02	tool_agent	Tool calling
03	multi_model	Anthropic ↔ OpenAI swap
04	memory_agent	Memory basics
05	workflow	Multi-step workflows
06	guardrails	Safety filters
07	mcp_tools	MCP integration
08	directives	Directive library
13	model_routing	Routing rules
18	local_llm_routing	Ollama / LM Studio
27	app_factory	App-factory pattern

Tier 3 — Integrations

#	Example	Tool
09	proxy_claude_code	Claude Code CLI
10	proxy_cursor	Cursor IDE
11	proxy_codex	OpenAI Codex
14	register_agent	Registry — publish
15	discover_agents	Registry — consume
23	harness_proxy	Harness proxy primitives
24	harness_agent	Harness agent integration

Tier 4 — Production patterns

#	Example	Problem solved
12	budget_enforcement	Per-user/team/project budget caps
16	agent_governance	Approval flows + audit
19	domain_model	Domain-modelled agent state
20	fleet_workers	Distributed worker registration
21	full_stack	End-to-end SDK + workflow + fleet
22	memory_holds_across_llms	Memory portability across LLMs
25	training_data_pipeline	Curator-style data capture
26	fleet_scoped_dispatch	Capability-based dispatch
28	autopilot_quickstart	Autopilot without an LLM key
29	memory_strategies	Strategy-based memory extraction
31	grounded_multi_model	Multi-LLM grounded retrieval
32	global_shared_memory	Cross-agent shared knowledge
35	autopilot_hosted_service	Autopilot via hosted blueprint service

Tier 5 — Lighthouse

#	Example	Real-world problem	Lighthouse page
30	oncall_agent	The v1.0 lighthouse — incident response	(cross-cutting)
33	fleet_sealed_integration	Multi-tenant production with isolated tenants	Production multitenancy
34	observatory_cost_tracking	Show my CFO where the AI money goes	Observability and cost
36	autopilot_training_loop	Capture → fine-tune trigger	Train your own model
37	semantic_checkpoint_recall	Weak LLMs feel like Opus on long context	Memory and retrieval
38	unsloth_finetune	Real LoRA fine-tune, dual-backend	Train your own model
38a	mlx_lm_server_deploy	Apple Silicon deploy via `mlx_lm.server`	Inference deployment
39	sandbox_scoped_credentials	Sandbox + scoped credentials	Production multitenancy
40	fleet_under_load	20+ workers, Iron Man HUD live state	Observability and cost
41	graph_memory_incident_dependency	Graph beats vector for multi-hop	Memory and retrieval
42	support_triage_agent	Drop-in customer-support triage	Moderation and classification
43	observatory_live	Real telemetry → live dashboards	Observability and cost
44	colab_free_cuda	Free Tesla T4 via Drive-sync	Inference deployment
45	vastai_marketplace_bid	Bid-cheapest with reliability scoring	Inference deployment
46	custom_inference_as_tool	Bring-your-own endpoint	Inference deployment
47	runpod_finetune_orchestration	RunPod reliable rental	Inference deployment
48	modal_serverless_inference	Per-second serverless	Inference deployment
49	community_moderation	Three classifiers + LLM judge	Moderation and classification

Notes

Example 17 — unsloth_finetune (legacy stub): superseded by Example 38 (real fine-tune). Marked deprecated in its docstring; left in place for backward compatibility.
No example numbered 02-08 in the _factory, _perf_*, _soaks, or notebooks subdirectories — those are dev tools, not user-facing examples.
Numbering gaps and sibling-suffixes (e.g. 38a) follow the example-build-conventions — when two PRs collide on a number, the later one gets a lowercase-letter sibling suffix to preserve numeric reservations.