Harrison Chase

specialized agents or one mega agent? we're having this debate internally...

Good take on harnesses

we're seeing our coding agent costs decrease significantly for second month in row longer blog on this later, but three quick steps we took 1/ cost visibility. you cant control what you cant measure. Start tracking everything to langsmith. This gives us super granular visibility into who is using what, how they are using it, etc. LangSmith supports first party integrations with all main coding harnesses https://www.langchain.com/blog/your-coding-agents-are-a-black-box-heres-how-to-crack-them-open 2/ cost controls. Through our LLM gateway, set user level cost caps. (You can increase your cap by talking to our VPE). This helps curb unexpected or accidental spend. https://docs.langchain.com/langsmith/llm-gateway 3/ optimize the harness. Obviously 3rd party harnesses are tougher to optimize, but we are doing more and more coding through OpenSWE, our open source cloud agent harness. Things like model routing help bring the cost down https://www.langchain.com/blog/how-to-build-a-model-router-in-the-harness feel free to reach out if you want help implementing these at your co!

cool to see cognition doing "dreaming" - memory needs an offline cleanup loop, not just better retrieval, otherwise stale records pile up open q is how inferred memories get validated before the agent uses them glad it's an open standard too - memory should be open https://x.com/cognition/status/2107165034463867001

We have a really strong team :) Come join us!

cool project by @dbreunig in langchain this is ModelRouterMiddleware - jev reads the first message, picks the model, and that model handles the whole run jev is cheap enough that you can also re-pick after each tool result with a custom hook docs: https://docs.langchain.com/oss/python/integrations/providers/typesafe#model-routing https://x.com/dbreunig/status/2106456056042025235

Ha gave this take to our team last week Will share some (very basic) stuff I vibe coded around this shortly Lots to be explored here!

One cool thing deepagents now supports: dynamically loading tools when is a skill is loaded Some skills require specific tools that you may not always want to have available. This now allows you to pair them With openai/anthropic models, it’s possible to do this in a way where it doesn’t break the prompt cache!

interrupt london is next tuesday really looking forward to hearing from Orange and OVO on what's actually working with agents in production. we're also running hands-on workshops on Deep Agents and Engine https://x.com/LangChain/status/2107456553452261751

Most of the interesting agent harness work is happening at intersection of harness and infra: 1/ dreaming 2/ async subagents 3/ heartbeats 4/ letting agent schedule reminders Part of reason im so bullish on managed agents platforms! All of these in managed deep agents!

love to see this integration

this is a great talk if you want to just follow along in slides, extracted screenshots here to make it easy writing up thoughts as we speak https://a-2jp6ke32btx7kfwxvhewash4vi.smithbox.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