Agents
router lives in the harness, not a gateway, bc the harness knows the task blog: https://www.langchain.com/blog/how-to-build-a-model-router-i…
router lives in the harness, not a gateway, bc the harness knows the task blog: https://www.langchain.com/blog/how-to-build-a-model-router-in-the-harness https://x.com/neil_xbt/status/2109979966859510
router lives in the harness, not a gateway, bc the harness knows the task blog: https://www.langchain.com/blog/how-to-build-a-model-router-in-the-harness https://x.com/neil_xbt/status/2109979966859510156 LangChain gave its coding agent three models and a router. Open SWE, their open-source coding agent, now sends each thread to the cheapest model likely to finish the job. they tested it on 973 threads, half routed and half always on GPT-6 Astra. median cost per thread: $0.94 agai…
Related
- Great article on harness engineering. https://www.langchain.com/blog/the-anatomy-of-an-agent-harness
- Model. Harness. Context. The 3 main components of agents. As you build more agents, context increasingly lives AGENTS.md, skills, policies, …
- if you haven't read this one by @Vtrivedy10, it's a must read! great overview of what components a harness needs to support an agent for lon…
- langchain create_agent is a super minimal agent harness very easy to customize with... middleware!!! as you build task-specific harnesses, g…
Source: Harrison Chase (X) | 2026-10-13