Knowledge catalogue
Memory + harness, or as @matt_slotnick put it, memory + intent. Something I describe a lot about @usebrief, that *why* you remember something is more important than pure recall. A moment that’s trivia
Harrison Chase, co-founder of LangChain, shared thoughts on AI memory and the risks of vendor lock-in when major AI providers like OpenAI and Anthropic control user memory systems. The post highlights
memory isn't a retrieval widget. it's write policy. the harness decides what survives compaction, what gets promoted, and what becomes reusable state. https://x.com/hwchase17/status/204297850056760973
Most illuminating graph I have seen for definition of harness. Memory and context are deeply coupled with harness. In my humble opinion, how they are injected and managed are one of most important pie
Open Everything 🤝 Own your intelligence 🤝 Builder Choice We’re in the v0.1 of deploying agentic intelligence across the economy. Agents are data generating beasts! Experiential Memory: Each piece of g
Relying on model providers' stateful APIs or harnesses creates lock-in: switching models means losing your agent's memory -- a cost that only grows as agents get better at learning a big part of agent
Harrison Chase, co-founder and CEO of LangChain, received positive feedback from a follower referencing a distinction he made at a Daytona conference, suggesting he regularly shares accessible and wel
the fact that http://pi.dev agent is so good, with virtually no sophisticated harness whatsoever, is a testament to the fact token vendor (codex/claude) agents are overrated. highly. today's moat of c
The most important post I've read all week by @hwchase17 . Memory, particularly memory consistency is the biggest performance inhibitor to AI agents today. As we interact with different harnesses and
the team spent a lot of time totally revamping docs with care❤️ ofc for LangChain+deepagents DX but lots of ppl use them as general learning guides on patterns across Agents, Context Eng, Infra, Prod,
this is a good point around taking advantage of model/api provider features i agree that prompt caching is great! we make sure to use it in deepagents! but that alone doesnt lock in - you can switch p
This is the right frame. We’re currently designing our agent memory platform, and the hardest part isn’t storage — it’s deciding what to remember, when to retrieve, and how to keep context clean. All
I was unable to retrieve the content of that specific X (Twitter) post, as web search results did not surface the tweet or its content. X.com posts are generally not indexed in a way that makes the...
This post is so so good. We are at this interesting point where we’ve started to really figure out ‘memory’ with these LLM-based systems. And @hwchase17 is totally right - memory is basically just con
time to help builders own their intelligence, open everything 🤝 the data produced and Experiential Memory gained from every agent interaction is the one of the most valuable things you can own to impr
What if owning the memory layer goes far beyond escaping lock-in? What if memory becomes fully editable intelligence? You could debug bad patterns, reinforce good ones, and crucially synthesize new on
LangChain's concept of 'your harness = your memory' explores how the surrounding infrastructure and framework around an AI agent effectively functions as its memory system. The post likely discusses h
Agent harnesses are spark LangSmith is databricks harnesses seem to be the abstraction that encapsulates all of the 'business logic' or 'business connections' into a coherent unit that you can iterate
Agent skills are great. I wanted to share some of my favorites from Jesse Vincent's 'Superpowers' skill pack 𝚠𝚛𝚒𝚝𝚒𝚗𝚐-𝚙𝚕𝚊𝚗𝚜 skill produces much better plans than any harness' built in plan mode that I'
The specific tweet (status ID 2042726390617764234) could not be retrieved directly, as it does not appear in available search results and X/Twitter requires authentication to access individual post...
**deepagents** (github.com/langchain-ai/deepagents) is an open-source, MIT-licensed agent harness built on LangChain and LangGraph, equipped with built-in task planning, a filesystem backend, subag...
As agent systems scale, the control layer becomes the main source of complexity. What starts simple turns into coordination and composition problems. I built langchain-middleware-stack to better struc
LangChain launched **Deep Agents Deploy** in beta as an open-source, model-agnostic alternative to Anthropic's Claude Managed Agents. It is designed to be the fastest way to deploy a model-agnosti...
Deep Agents deploy gets you the best AI infrastructure operators in the game! cc @h_dhanushkodi @WHinthorn Deep Agents deploy gets you: - Deep Agents harness - Sandbox of your choice (@daytonaio , @mo
For anyone building agentic workflows: the real bottleneck isn't the model, it's the harness. Open standards are a must, not just for flexibility, but to ensure we actually own the long-term memory th
I was unable to retrieve the specific content of the linked tweet, as X (formerly Twitter) requires JavaScript and login to display individual posts. The search results did surface a highly relevan...
great question! knowledge (system prompt, skills) and tools (apis, clis, whatnot) will always be needed, even as the best way to build agents changes i would focus on those and processes around those
Help us grow our list of community middlewares! https://docs.langchain.com/oss/python/integrations/middleware#community-integrations @IeloEmanuele is on a roll! you can now use claude code's advisor s
LangChain's Middleware abstraction, introduced by Harrison Chase (@hwchase17) in LangChain 1.0 Alpha, addresses context engineering in AI agents by providing clean `before_model`, `after_model`, an...
A developer expressed enthusiasm for the emerging convergence of `AGENTS.md`, agent skills (SKILL.md), and tool configuration toward portable, cross-tool interfaces rather than siloed, tool-specifi...
@IeloEmanuele is on a roll! you can now use claude code's advisor strategy with @LangChain agents because langchain/deepagents are provider agnostic, you can use different providers for your advisor a
I was unable to retrieve the content of the specified X (Twitter) post. The URL `https://x.com/masondrxy/status/2042728855123661203` could not be accessed through search — the status ID appears to ...
im excited about agent harnesses because i think are the first stable agent abstractions we can build on top (which is why we're investing so much in deepagents) we always wanted to run llms in a loop
Just shipped advisor-middleware: an open-source implementation of @AnthropicAI’s Advisor Strategy for @langchain DeepAgents. Pair a cheap executor (Haiku) with a powerful advisor (Opus): execute end-t
LangSmith for Startups Spotlight: @tryflint Flint is an autonomous website platform that generates on brand landing pages. Flint’s marketing agent works behind the scenes to get your message out to th
Love this new podcast format ❤️ super insightful! 🎙️Introducing Max Agency Max Agency is a new podcast where we go deep on how the best agents are actually being built: architecture decisions, tradeof
Max volume for Max Agency 📣🗣️ 🎙️Introducing Max Agency Max Agency is a new podcast where we go deep on how the best agents are actually being built: architecture decisions, tradeoffs, evals, and every
I wasn't able to retrieve the content of that specific tweet or URL from the search results. X (Twitter) posts are generally not indexed in a way that allows direct retrieval of their content, and ...
Multi-Agent Orchestration is a great tool in building agentic products thankfully @sydneyrunkle put together a guide with runnable code for each pattern earlier this year 🙏 (link below) choose any mod
My X bookmarks have an 'intellectual shape' Apparently mine is: Technique-heavy, Tool-obsessed, Light on Opinion I didn't know until I ran the numbers OSS I've been building w/@LangChain to explore Ge
New Guide: Incorporating human judgment in the agent improvement loop Building agents is hard. Everyone talks about the code. What gets less attention is how to capture domain expert knowledge and act
An **Open Harness** is a unified architectural layer that sits between AI agents and model providers, abstracting away provider-specific APIs and patterns. Because every AI agent harness has its o...
Open swe uses deepagents under the hood Deepagents is general purpose, openswe is focused on coding @hwchase17 @LangChain This is a very interesting comparison. Now my question is: how to compare Deep
Portable agents @hwchase17 Ngl I really like this direction. The more AGENTS.md, skills, and tool config start looking like portable interfaces instead of app-specific hacks, the more usable this whol
Speed of open source! Anthropic adds advisor strategy yesterday -> Emanuele adds an implementation as middleware less than 24 hours later! Just shipped advisor-middleware: an open-source implementatio
The ‘agent harness’ is essentially the new runtime. It’s like a lightweight OS around an LLM—handling memory, tool calls, retries, and control flow. @hwchase17 im excited about agent harnesses because
The challenge with agent harnesses is not only building them but distribution. If we want agent products to scale like saas, the interfaces and ecosystem still need a fundamental breakthrough. im exci
tldr > evals are the new training data. instead of updating weights, you're updating the agent harness > problem is agents are famous cheaters. they will reward-hack your evals and overfit just to mak
we are doing this podcast specifically to highlight the innermost details of building agents in production may be a little niche, but its a niche i like 🤷♂️ @hwchase17 Great content, really appreciat
What does it actually take to make agents better over time? A system that starts with a trace. You capture traces of agent behavior, enrich them with evaluations and human feedback, identify what’s fa
what he said 🗣️ the very best agents today obsessively tailor the harness layer around the model I’m looking at you “5 things I learned from the Claude code leak” bros 👀 orchestration patterns, tool d
why not? what in the current harnesses are not bitter lesson-pilled? off top of head: will go away: - planning tools - compaction (or at least will matter less) not going away: - sub agents - skills -
1️⃣✅❌ 2️⃣✅❌ 3️⃣✅❌ One of the benefits of Deep Agents deploy is model optionality Choose from models from @OpenAI @GeminiApp @AnthropicAI @FireworksAI_HQ @baseten @OpenRouter @ollama @nvidia and many o
a useful mental model on how teams can think about good data design to improve their models/agents: Evals ~= Training Data ~= Environments - in Classical Deep Learning, we learn from each training exa
And that is what Thoth uses for its agents in the backend. Thanks for your contributions to oss @LangChain @hwchase17 https://github.com/siddsachar/Thoth AI that doesn't just work for you, it knows yo
Announcing the @LangChain podcast -- Max Agency. Deep context to give you the edge while building and iterating on agents. Watch the full episode on: - Youtube: https://www.youtube.com/watch?v=Xyh1Eqc
calling all of my fellow podcast nerds! 🎙️Introducing Max Agency Max Agency is a new podcast where we go deep on how the best agents are actually being built: architecture decisions, tradeoffs, evals,
Can’t get enough of Harrison and his AI takes? Lucky for you, we’re announcing Max Agency where you can hear him & other industry experts talk agents, harnesses, models, evals, and more!! 🎙️Introducin
Checkout our new Max Agency podcast - the first episode is already out! 🎙️Introducing Max Agency Max Agency is a new podcast where we go deep on how the best agents are actually being built: architect
Claude Agent SDK tracing in LangSmith just got an upgrade. Now you can trace: → Subagents → Child runs inside MCP tools → Cost tracking + more Update to the latest Python SDK to try it out. Docs: http