Knowledge catalogue
@LangChain always reveals the technical principles behind agent concepts, like loop engineering, managed agents and memories.👍 That's why I recommend LC docs to agent developers and users around me, t
The AI SDK Harness API now supports @OpenCode and @LangChain Deep Agents through a single unified interface. Use 𝙷𝚊𝚛𝚗𝚎𝚜𝚜𝙰𝚐𝚎𝚗𝚝 to run any supported runtime without changing your app code. https://verce
LangSmith enables tracing and monitoring of AI SDK 7 operations, allowing developers to observe and debug their AI applications built with the SDK. This tool provides visibility into model interaction
Agents are easy to demo locally. The hard part is shipping them inside a real app. We published a deployment cookbook for @LangChain agents: full-stack examples with streaming UI, subagents, thread hi
deployment cookbook for langchain agents! Agents are easy to demo locally. The hard part is shipping them inside a real app. We published a deployment cookbook for @LangChain agents: full-stack exampl
excited to be speaking at @aiDotEngineer World Fair next week on Improving Agents, Continual Learning, and why we think a large part of it is...Data Mining! Trace Mining is how we understand agent beh
How do you construct, compact, and query a full-text search index when all your durable data lives in object storage? And where every GET costs 50–100ms? @ankush_gola11 + team on how we built and run
if you get 1% better every day then you're 37x better in a year (from @JamesClear's atomic habits book) my theory is you can do this for agents if you build a good continual learning loop which is wha
One key insight for using engine as memory is that traces are key ingredient of memory, and engine already has access to all of them @hwchase17 I love that this is built on traces rather than a separa
Technical blog on how we built SmithDB (our database purpose built for agent traces) How do you construct, compact, and query a full-text search index when all your durable data lives in object storag
This has a lot in common with how controlled self-evolution works in Row-Bot. And that built on top on LangGraph too. Here's an article I wrote about how it works a few days ago: https://x.com/i/statu
Agent memory systems often follow a three-step iterative process: executing the agent to generate traces, analyzing those traces through some evaluation mechanism, and then updating the agent based on
This post highlights that while agent architecture design has become well-established and solved, memory systems remain an unsolved challenge in AI agent development. The tweet references an article b
an agent’s gotta dream! just like we consolidate learnings during sleep, agents can learn across runs! 🧠LangSmith Engine as Sleep Time Compute Memory for agents is often described as “sleep time compu
awesome launch We built Claude for outbound sellers. AEs & SDRs can harness GTM engineering through chat across 40+ data sources, no technical skills required. We’ve had 57,548 queries in our first fe
congrats to our friends at Unify!!!! We built Claude for outbound sellers. AEs & SDRs can harness GTM engineering through chat across 40+ data sources, no technical skills required. We’ve had 57,548 q
🧠LangSmith Engine as Sleep Time Compute Memory for agents is often described as “sleep time compute” or “dreaming” This involves running a background process to analyze agent trajectories and update a
memory is the key to continual learning for agents!! memory helps your agent improve over time, check out this guide on how to automate memory development! i've been talking a lot about loops recently
Memory is what turns an ok general agent into YOUR excelling agent- but requires constant reflection and updating Engine does this 24/7 for you 🧠LangSmith Engine as Sleep Time Compute Memory for agent
'Most agents don't learn, they just leave traces.' In 12 minutes, @jakebroekhuizen breaks down how to actually close the loop. Surface issues with LangSmith Engine Write memory updates back to Context
pretty sick that i get to work with Jake every day on making continual learning + memory accessible at scale for every single agent one common thread here is...the Trace a large part of Continual Lear
Sleep-time compute is the next scaling axis for intelligence 🧠LangSmith Engine as Sleep Time Compute Memory for agents is often described as “sleep time compute” or “dreaming” This involves running a
Tracing functionality can be utilized to monitor and analyze memory usage patterns in applications, helping developers identify memory leaks, optimize allocation, and understand runtime behavior. This
We built Claude for outbound sellers. AEs & SDRs can harness GTM engineering through chat across 40+ data sources, no technical skills required. We’ve had 57,548 queries in our first few weeks of beta
auto-research style proposal loops should be data driven! they largely work best only when Data/Evals/Feedback give a useful gradient to hill-climb against increasingly auto-research is a very good to
Harrison Chase suggests that evaluations (evals) are becoming as critical to AI/LLM development as Product Requirements Documents (PRDs) traditionally were, implying a shift in how teams validate and
GLM 5.2 is already top 10 on OpenRouter this week, sitting right next to Opus 4.8. it's also been really strong in Deep Agents across long-horizon coding, big context, tool use, and verifying work bef
i was already using GLM-5.2 but WOW it's even better through baseten! give it a try with deepagents code (dcode), our open harness built to work with any model/provider We have the fastest GLM-5.2 dep
interesting point here: loops amplify behavior, making them a double edged sword but we know loops are the future, so how do we avoid amplifying bad patterns? you need an *engaged* human in the (stack
Let the smart horses build their own harness. See my previous article on this: https://x.com/Kangwook_Lee/status/2052925157606568217 🧠Self-Harness: Harnesses that improve themselves New paper on agent
Model council as a tool to push performance definitely works, I think the interesting next frontier is trying to scale this at the agent level have been thinking a bunch about model routing and relate
One thing we’ve seen pretty consistently: shipping the first version is only a small part of the work A key part of building reliable agents is having a repeatable lifecycle for improving them over ti
🧠Self-Harness: Harnesses that improve themselves New paper on agents shaping their own harnesses to improve over time. Not from LangChain, but builds on top of DeepAgents! Three key steps: 1/ Weakness
self-harness: harnesses that improve themselves spoiler alert, it's all loop engineering! 1. weakness mining - run agent and observe failures 2. propose improvements to the harness 3. confirm improvem
you need docs built for agents Docs are the eyes and ears of Agents. But we're moving so fast that they are always outdated. So hence an outdated doc also confuses the models. But it's also hard keep
context engineering docs for agentic engineering - plans, research, etc SHOULD NOT be stored in version control: A good docs management system keeps them: > outside your repo > accesible to agent via
Deep Agents v0.6 feature spotlight: a code interpreter. Agents can now call tools from inside a runtime, keep intermediate results out of model context, and only pass the relevant output back. Fewer r
have been thinking a bunch about model routing and related things current thoughts here, would love feedback: 1/ there is a difference between 'model routing' and 'model council' 'model routing' = rou
If you are building agents, Max Agency with @hwchase17 is THE best behind the scenes of how the top agents are built at companies like @SierraPlatform @RampLabs @benchling @ListenLabs @_hex_tech @coge
Something we’re thinking a bunch about as well Would love thoughts! context engineering docs for agentic engineering - plans, research, etc SHOULD NOT be stored in version control: A good docs managem
There are basically two skillsets that matter more in the age of coding agents. The first is the one everyone talks about: product sense and taste. Code is cheap now, so knowing exactly what to build
you can try out GLM 5.2 with deepagents code (dcode) today!! dcode is general purpose and provider agnostic, so you can take any of the new oss models for a spin! docs: https://docs.langchain.com/oss/
'Build your own Claude Code with Deep Agents' Good article by the community showing how to build a Claude Code-like agent using Deep Agents Especially relevant given how strong GLM-5.2 seems to be! ht
people want to build agents, and they want it to be easy even more important, it should be easy for your agents to improve over time that's what the 4th loop ('hill climbing') enables. automating the
Harrison Chase confirms that 'Yes' (likely referring to LangChain or a related tool/framework) is model-agnostic and designed as a general-purpose solution, meaning it can work across different AI mod
One of the better agentic AI courses I've seen Nearly 10 hours of great content. Covers LangChain, LangGraph, RAG, deepagents, guardrails, and more Any other good Lang* resources out there for folks w
Very cool work from @jit_infinity: 🔥Leve: filesystem-first, durable agent framework built on LangGraph. You describe an agent as a directory of files. Leve compiles that directory into an agent and ru
Deepagents code is sick cuz you can just use the best model as it comes out it is indeed quite good! don't try it in claude code/codex - those harnesses are overly tuned for their proprietary models d
it is indeed quite good! don't try it in claude code/codex - those harnesses are overly tuned for their proprietary models dcode (deepagents code) is a model agnostic harness - try it there with @Fire
Try it out! We are seeing amazing results with GLM 5.2! it is indeed quite good! don't try it in claude code/codex - those harnesses are overly tuned for their proprietary models dcode (deepagents cod
AI agents have become surprisingly good at talking to servers 🤖 The next challenge is getting them to interact with the environment users actually live in. 🧑💻 Browsers. 🖥️ Apps. 📱 Devices. 🌐 Local st
Harrison Chase announced a LangChain meetup event in Chicago on June 22 featuring discussion of deepagents, in collaboration with focused.io. The event was promoted on X (formerly Twitter) as an oppor
first in a series of technical blogs of how we build llm infra How do you support full-text search JSON filtering over agent traces that span up to hundreds of MBs, while keeping a median (P50) latenc
future of travel! We raised $6M led by Sequoia to build the future of travel. Watch me plan a perfect trip to Mexico City in 3 minutes. Flights, hotels and a full itinerary that matches my preferences
How do you support full-text search JSON filtering over agent traces that span up to hundreds of MBs, while keeping a median (P50) latency of 400ms? Here’s an inside look at how we built a custom inve
Introducing @PoeticHQ: a new AI system that executes complex multi-hour tasks with 99%+ accuracy and 10x fewer tokens than agents. We raised 50M at 500M from Kleiner Perkins, Founders Fund, First Harm
it’s actually so cool to work at LangChain the…database company (??) yup, the cracked team that built SmithDB is doing a cool blog series on “How to build the internals of a database” —> for agent sca
We raised $6M led by Sequoia to build the future of travel. Watch me plan a perfect trip to Mexico City in 3 minutes. Flights, hotels and a full itinerary that matches my preferences. All bookable on
loops are great because its just ai running in the background 'triggers' are the way we kick those off in fleet What are loops, and how do you build one? A 'loop' is the repeated process where some ev
What are loops, and how do you build one? A 'loop' is the repeated process where some event or input kicks off an action. For example: 1. CI fails -> you fix it 2. CI fails again -> you fix it 3. CI p