LLM app frameworks

Specialized embedding stores sold as the default. Mid-market folded back into Postgres — after the vendor tour.

From scripting glue to the default language of data and AI. Readability as a growth strategy.

Coding agents that edit the repo — now table stakes. Generation outran review capacity; ownership is the bottleneck.

Chains, tools, memory, and agents as a framework — LangChain-class glue sold as architecture. Fatigue was real; the repos became MCP clients, not tombstones.

$ Teams adopted chain/agent frameworks before they had a single reliable tool call. Abstraction layers multiplied while prompt quality stayed flat.

Retrieval-augmented generation as the answer to every knowledge problem — then "just stuff the window" as the counter-fad. Often right; often Postgres with pgvector would suffice.

$ Teams stood up vector pipelines, chunking strategies, and rerankers before asking if fine-tuning or a SQL query would answer the question. Retrieval infra became the product.

The Codex/Claude loop as a product SKU — durable sessions, compaction, subagents, and a sandbox you do not own.

$ Teams replaced a weekend of LangGraph glue with a managed session API, then discovered residency, recovery, and kill switches all live on the vendor side of the harness.

Standard ways for models to talk to tools and data — MCP after the 2026 stateless rewrite, not one-off plugin snowflakes.