Single cloud agent, heartbeat passes
One cloud agent with scheduled cron/heartbeat passes and tool connectors.
You already have four shapes on the bench — the cloud agent on a heartbeat, the resident local agent, the same-persona federation, and the human attendant over resident units. This survey covers the other configurations companies and hobbyists are using in late 2025–2026: what each one is, who is really doing it, which design variables it sets differently, and whether a small version can run at home.
Bench rule, in your words: “I have no opinion until I've done it a few times.” One run is an anecdote, not a finding — so the shortlist below tracks repetitions, not verdicts. Evidence note: two Anthropic primary sources were read in full; everything else comes from the web index and is flagged as such in the sources.
Parallelise reads, not writes.
Anthropic's production Research system — an orchestrator fanning out to parallel subagents — beat its single-agent baseline by 90.2% on an internal eval, at roughly 15× the tokens of chat. Cognition (Devin), publishing a day earlier, argued the opposite default for write-heavy work: parallel agents make conflicting implicit decisions. Its April 2026 follow-up narrowed the truce — multi-agent works when writes stay single-threaded and extra agents contribute intelligence (reading, reviewing), not actions. A 2026 benchmark cited in secondary coverage (CooperBench, Stanford/SAP) found success roughly halving when a coding task was split across two agents editing shared files.
Anthropic, multi-agent research system · Cognition critique via secondary coverage — see sources.
Used here only as contrasts. Everything after this strip is an other configuration.
One cloud agent with scheduled cron/heartbeat passes and tool connectors.
Local-LLM agent on home hardware, outbound-only, escalating to a cloud agent via shared files or its own API key.
Hub-and-spoke federation of instances of the same persona, with signed tasking.
One human supervising several resident agent units at client sites.
Framework names mostly re-implement the same four or five topologies with different ergonomics. These are the axes where a real difference lives — the survey's cards are organised around them.
Code, a supervisor LLM, the agents themselves, or an event stream. This decides whether behaviour is predictable, emergent, or reactive.
Per-agent context, a shared blackboard, a durable workflow log, or a self-edited memory store. Each brings a different failure class.
In-process calls, handoff tools, conversation, or the cross-vendor A2A protocol — from one process to strangers' agents.
A human prompt, an issue assignment, an event, a voice, or its own task list. The trigger model is often the cleanest break from K1's cron.
Ten benches, furthest-from-known first. Effort is the report's estimate for a small home version. Tap +1 run as you complete repetitions in this session — three runs is where an anecdote starts becoming a finding.
Each card states who is actually doing it, the seven design variables — residency, topology, channel, identity & credentials, supervision, memory, trigger — and the honest home-bench verdict.
Not a topology, but these recur so consistently they function as configurations. OWASP's organising principle is least agency: only the autonomy, tools and access a task requires, only for as long as it requires them. Together, G1+G2+G3 on your existing benches is a half-weekend that upgrades every other configuration here.
A human decision immediately before irreversible side effects — push/merge, deploy, delete, send, spend, permission change — showing the exact command and arguments, not a summary. LangGraph interrupt(), HumanLayer-style @require_approval decorators (gate in code, not in the prompt), and the rule that an agent never approves or merges its own PR. Design against approval fatigue by allowlisting low-risk actions inside a sandbox — not by rubber-stamping.
Permission prompts are not a security boundary; isolation is. Disposable container or microVM per run, no production credentials inside, no home-directory mounts, and a network egress allowlist — the main control against exfiltration after a prompt injection succeeds. Know your sandbox's scope: several products sandbox only shell commands, not file tools or MCP servers.
Each agent gets its own non-human identity — service account, GitHub App, bot user — attributable and independently revocable, with scoped short-lived tokens (OIDC / secrets-manager issued, per task), zero standing privileges where feasible, and a read/write split where the platform allows. The enterprise form is Entra Agent ID (C12); the direct opposite is C18's traditional “operator's broad API key.”
Explicit verdicts from the survey. If you take one section into a job conversation, it's this one — most vendor taxonomies are the same menu in different vocabularies.
| Claim / name | Verdict | Why |
|---|---|---|
| Supervisor vs orchestrator–worker vs CrewAI “hierarchical” vs LangGraph supervisor vs ADK root-agent delegation | SAME SHAPE · C1 | Four vocabularies for one star topology. ADK's single-parent tree is a real constraint difference; the rest is ergonomics. |
| Microsoft's five patterns (Sequential, Concurrent, Group Chat, Handoff, Magentic) | CATALOGUE | Useful, but not five architectures: Sequential/Concurrent = C3; Handoff = C2; Group Chat = C4; Magentic = C1 with a ledger + replanning (C5 flavour). |
| Anthropic's five workflows | CATALOGUE | Maps ~1:1 onto Microsoft's: chaining/routing/parallelisation = C3; orchestrator–workers = C1; evaluator-optimizer = C6. |
| “Swarm” (OpenAI Swarm, Agency Swarm, LangGraph Swarm, “swarm intelligence”) | ONE PATTERN, WRONG NAME · C2 | There is no stigmergy, no emergence, no parallelism — one active agent at a time. True swarm/stigmergy designs in production are C9 blackboards and C21 societies, rarely labelled “swarm.” |
| Maker–checker vs evaluator–optimizer vs generator–verifier vs reflection loop | IDENTICAL · C6 | Three vendors, one loop. |
| Debate / council / roundtable | DISTINCT PROTOCOL, BORROWED TOPOLOGY · C7 | C6 extended to N proposers on C4's plumbing. Only distinct if the first round is genuinely independent. |
| “Ambient agent” vs Copilot Studio “autonomous agent” vs “autopilot” vs “background agent” | SAME SHAPE · C15 | LangChain coined the useful name; later renames add nothing architectural. n8n / Home Assistant event-triggered LLM workflows are the same shape at hobbyist scale. |
| “Digital employee / digital worker” (most vendors) | TEST IT · C19 | A rename of C1/C3 inside a SaaS tenant — unless the agent holds a platform-scoped identity and works under the platform's permission/audit model. Apply that test to every claim. |
| “Chief of staff” / “second brain” assistants (Lindy; Khoj) | NOT NEW · ≈K1 | Lindy ≈ K1 (hosted single agent, connectors, inbox) with assistant-specific tooling — a valuable product, not a new architecture. “Second brain” (Khoj) is a memory/retrieval feature, not a topology. |
| MetaGPT “AI software company” | MOSTLY DISTINCT · C8 | The org metaphor is marketing, but SOP document contracts + a pub/sub artefact pool are a real design choice CrewAI-style role prompts do not make. |
| Manus “general agent” / Devin “AI software engineer” | PRODUCT NAMES · C13 | Names over C13 (sandbox-per-task) + C5 planning (+ C1 fan-out for Manus Wide Research). The VM-per-task isolation is the architecture; the job titles are not. |
| MCP vs A2A | NOT COMPETITORS | MCP = agent→tool (C11); A2A = agent→agent (C12). Any source framing them as rivals is selling something. An A2A agent commonly uses MCP internally. |
| Letta “stateful agents” | DISTINCT ON ONE AXIS · C10 | Distinct on the memory axis only; its multi-agent features reduce to C1/C9. The contribution is self-edited tiered memory, full stop. |
| Voice “AI receptionist” products (Vapi/Retell wrappers) | MANAGED INSTANCES · C16(a) | The cascaded-vs-speech-to-speech fork is real; the vertical branding (dental, legal, HVAC…) is not. |
Carried plainly, with the hedges the research attached:
All read 2026-11-15. FETCHED = full text retrieved; INDEX = search-index full text.