A human approves a $40 refund and the runtime executes something else — no injection, no sandbox escape, just an approval stored as a boolean against an identifier while the arguments stayed writable. Loopjacking reproduced it across seven Agno releases; one SDK in the sample rejected it, and the difference is three lines of design.
OpenAI opened the Agents API in public beta on 10 September, putting the managed Codex harness — sessions, subagent orchestration, recovery and context compaction — behind one API call, with no fee beyond tokens and containers. The compaction step is the part worth arguing about: it is the transformation that quietly rewrites what your agent is trying to do, and it now runs on a version you cannot pin, diff or roll back. Your eval numbers stop describing a system you control the moment you adopt it.
Flowise archived itself on 13 August 2026 and its maintainers named the reason: coding agents now handle the complexity that a rigid low-code workflow hits a wall on. The three still standing are not surviving on the canvas either — each is defending something underneath it, and each licence says exactly what. n8n forbids offering it to others, Dify forbids multi-tenant operation, Langflow forbids nothing and is owned by IBM. Read the clause before the feature list.
All four resume a crashed run from its last completed step, so that is not the decision. An agent’s durable record is a transcript that grows with every turn, not a handful of small step results — and the engines differ on where that growth is stored, what ceiling it hits, and whether your model call is allowed to sit in replayed code. Temporal terminates a workflow at 51,201 events or 50 MB of history; Inngest caps a step output at 4 MB and run state at 32 MB; Restate and DBOS push the growth into storage you operate. Decide on that, then on billing shape, and the feature tables stop mattering.
GEPA's reported margins — up to 20% over GRPO, 13% over MIPROv2 — were all measured where an automatic checker was free and a failed run could be described in words. Two of these four optimizers run on a bare scalar; two need a sentence. What your eval function returns decides which half of the field you can use, so change the metric before you change the optimizer.
Two of the four bill the agent loop at about nine cents per vCPU-hour and their prices are 3.6% apart; the other two do not charge for it at all. What each is actually selling is a place to keep the conversation — and AWS closing Bedrock Agents Classic to new customers on 30 July 2026 is the clearest evidence yet about which half of a managed runtime you can afford to rent.
Framework comparisons argue about graphs versus crews versus handoffs, but the metaphor stops mattering by week three. What you cannot re-pick eighteen months in is where a run lives, what resume means after a crash, and whether a human can pause a half-finished task — so choose on the state model and the rest of the comparison resolves itself.
Every AI gateway sells the same headline feature: automatic failover to a second provider. That feature is not an availability win — it is an untested deploy that fires only during an incident, onto a model your evals never covered. Choose instead on who operates the hop, because that is the decision you cannot reverse cheaply.
Naive agent loops die on minute 29 of a 30-minute job. Durable-execution engines journal every step so the next process can pick up exactly where the previous one died — and 2026 was the year hyperscalers shipped their own. Four engines now compete on the same primitive, with very different architectures and bills.
Four orchestration frameworks let you wire up the same workflow — and the feature lists nearly match. The thing that decides which one survives production is invisible there: where your agent's state actually lives.