while exploring harnesses, i came across my first and favourite agent orchestration framework @LangChain has launched deep-agents last year.…

while exploring harnesses, i came across my first and favourite agent orchestration framework @LangChain has launched deep-agents last year. it’s a wonderful harness, that has a lot of tools: - write_todos - ls, edit_file, read_file, write_file - task (specialized subagents) a proper long term memory. you are the one who declares the permissions. human in the loop (very important). you should use it when the task is too big to fit in one prompt - something that requires extreme agency, planning, parallelism, or memory across steps. something like “research this codebase and write a PR” - that’s deep agents territory. in short, deep agents = LLM + a plan + a desk + a team + guardrails. exactly the definition of harness i explained in the article below. do check it out. great work @hwchase17 🔥

Source: Harrison Chase (X) | 2026-05-03