Knowledge catalogue
this video goes into more detail on how our integrations with @harborframework actually work! if the blog yesterday caught your eye definitely watch this! thanks for all the help @kobe0938 @alexgshaw!
we built the @hyperspell filesystem around this principle every source in your company feeds into a context graph where we resolve conflicts and assign permissions there’s a filesystem on top of the g
We call ours Operational Language Wiki, essentially a pattern for building memory to fill in the delta between the “dialect” of a team vs the “world language” that the LLM is trained on. Use it to cap
Wiki!!! One unexpected outcome of this is that I'm now using the wiki as the ONLY place I run Claude Code I use it as a master controller for all of my repos, kicking off cross-repo tasks and using To
This post announces the release of an open source tool or example demonstrating how to implement wikis for memory management, following up on a previous discussion about this trending approach. The re
you can now build RLMs with Deep Agents! the more context agents accumulate, the worse they perform, a phenomenon called context rot. RLMs, proposed by @a1zhang from MIT, help: instead of working mode
Recursive Language Model (RLM) workflows are now available as a feature in Deep Agents, allowing AI systems to iteratively call language models within multi-step processes. This capability enables mor
You can start building with GLM 5.2 in minutes: 1️⃣ Download dcode 2️⃣ Select your model (GLM 5.2) 3️⃣ Enter your API key …and you're ready to go with frontier performance on open weights. Great demo
This post describes a common architectural pattern for integrating memory components into AI systems, illustrated through examples like DeepWiki and AutoWiki that automatically generate and maintain k
A great read from @LangChain Best framing I've seen for agent architecture. Every non-model piece like the filesystem, sandbox, compaction, Ralph loops exists to patch a specific model limitation. htt
a very cool Harbor x LangSmith flow I love to help you “look at the data”: 1. you do evals or rollouts for RL 2. all reward metrics and traces and rollouts get automatically propulates into Experiment
Code-writing AI agents can solve complex problems more effectively than agents using other approaches, but deploying them requires executing potentially untrusted generated code within sandboxed or is
agree a lot with this - the actual storage layer for memory (eg which database you use) matters less than the process around that data (retrieval, ingestion, etc) @hwchase17 what if memory is not stor
Building voice agents can come with tradeoffs. 💬 Better convos w/ speech to speech models Vs 🥪 More reliable harnesses w/ sandwich architecture How to build a voice research agent with both: ✅ Gemini
This post likely discusses how to evaluate AI agents built with LangChain using Harbor, a tool for testing and monitoring. It covers practical approaches for assessing agent performance, reliability,
Giving agents the ability to write code makes them dramatically more capable. It also makes security a lot harder. At LangChain, we have spent a lot of time this year figuring out how to do both. http
good description of how someone has done wiki memory in the wild @hwchase17 @cognition @FactoryAI @karpathy We implemented wiki idea by hosting the 'files' as doc db objects, added an API for db query
harbor is a great framework for running evals for long running, stateful agents its becoming industry standard, powering benchmarks like terminal bench 2 we've integrated deeply with harbor: across La
.@harborframework can now integrate directly with Deep Agents, LangSmith Sandboxes, and LangSmith Observability. You need to run agents in a real, reproducible, isolated environment, many times in par
Harrison Chase discusses techniques for executing agent code safely without requiring a complete sandbox environment, highlighting hardening measures implemented in their code interpreter runtime. The
human in the loop is very nice for these wiki memory systems @hwchase17 My rule is that nothing gets added to the knowledge system without me reviewing it first, which has served me well so far, along
@hwchase17 very spot-on! for our (http://qontext.ai) customers, the journey is usually: local .md files -> shared github repo (-> gbrain) before these approaches break down at a) multiplayer (incl acc
This post expresses enthusiasm for command-line interface (CLI) loading spinners, highlighting the aesthetic and user experience satisfaction they provide during software operations. The author apprec
joined @LangChain almost three months ago and have spent a ton of time thinking about evals! i think that harbor is the future of eval frameworks so really enjoyed being able to bring it into tighter
LangChain 今天连发两记，直接把 agent reliability 往前推了一步：一套统一评估栈，一个不用完整沙箱的代码执行方案。 先说评估。长运行、有状态的 agent 怎么测？Harbor + LangSmith 的组合给出一个 runner，能挂载 sandbox、接入 observability，终于不是靠单元测试糊弄了。 再看代码执行。Deep Agents 需要跑不受信代码，
Memory has somehow consistently been the most exciting area of agent development over the last 3 years (imo), and it's still a largely unsolved problem!! Wiki's are the biggest advancement I've seen i
Row-Bot's approach to memory is hybrid. We have taken the best of both worlds. A knowledge graph for the agent + bi-directionaly synced Wiki for human readability/audit. With in-app graph visualizatio
This post likely discusses technical decisions and design patterns for dynamically displaying subagents within an AI system, documenting the alignment the team reached after encountering implementatio
this may be ai generated, but is true - the hardest part of wikis (and memory in general) is the process that condenses raw data into learnings/memory @hwchase17 @cognition @FactoryAI @karpathy wiki m
Tutorial on using Gemini live to build a voice agent Uses deepagents as a tool: offload complex work to this subagent, use Gemini live for the naturalness/latency Building voice agents can come with t
we launched code interpreters for deep agents last month. Basic idea is to let agents plan, delegate, and organize context using code instead of chained tool calls Code interpreters don't need a sandb
Deep Agents now supports dynamic subagents. Instead of invoking subagents with tool calls, the main agent writes orchestration code to coordinate work at scale. This enables workflows like processing
Deep Agents supports sandboxes from any provider; with first-class support for E2B, Daytona, LangSmith, Modal, Vercel, Runloop, AgentCore, and BYOS (bring-your-own-sandbox implementation) support http
DeepAgents introduces dynamic subagents that can be created programmatically at runtime, enabling more flexible and adaptive agent architectures. The post highlights six different practical use cases
I cannot provide an accurate summary without access to the actual content of this X/Twitter post. The URL provided appears to have an invalid status ID format, and I don't have the ability to browse e
it's never been easier to turn langgraph agents into voice agents! great tutorial on how to do so, featuring @pipecat_ai Turn any LangGraph agent into a voice agent, no rebuilding required. A how-to o
Masterclass deep-dive into programmatic spawning of subagents - highly encourage taking a look! @colifran_ dropping elite ball knowledge per usual this blog covers 6 common workflow patterns we see wi
Row-Bot runs a LangGraph agent at its core. And supports 2 voice pipelines: - Local STT using whisper + Local TTS using kokoro - A real-time voice pipeline using GPT realtime 2. Both support full agen
the most common FUD our competitors throw against LangSmith is that it only works if you use our open source. but actually as of this month, a MAJORITY of our active self-serve customers build without
The product of some of the work the LangChain Labs team has been up to recently 📌 You can read more about it here - https://www.langchain.com/blog/building-a-100x-cheaper-trace-judge-with-fireworks -
this blog covers 6 common workflow patterns we see with dynamic subagents (fanout and synthesize, adversarial verification, etc) if you'd prefer to learn w/ a video, check out this excellent guide fro
Turn any LangGraph agent into a voice agent, no rebuilding required. A how-to on: ✅ Making LangGraph the LLM layer of a voice agent built with @pipecat_ai ✅ Tracing your entire voice agents – from aud
very cool if like me you're curious about how they steer the harness to do this, you can just look at the OSS code here 👇 https://github.com/langchain-ai/deepagents/blob/5e01fec72d8b179a3b075b07268162
We are starting to role out our Trace Judge model to early partners today Designed to detect errors in agent trajectories at 1/100th of the cost compared to closed models If interested in early access
we just released dynamic subagents, which let your agent programmatically orchestrate subagents in a code interpreter. this lets agents do work at scale that tool calls can't reliably handle, like pro
Dcode does a bunch of work to standardize message format, making it easy to switch providers mid thread Claude Opus -> GLM 5.2 in under 10 seconds dcode isn't just provider-agnostic. it makes the cros
Fleet agents can be shared in channels where your company is already doing work. Slack, Teams, etc Video from Caspar showing how to bring them into Slack! For agents to spread through a company they h
For agents to spread through a company they have to meet people where work already happens. Fleet is built around this: agents are not confined to our UI, they can be used from Slack, Teams, email...
harbor is a great way to run evals that require sandboxing: https://docs.langchain.com/langsmith/harbor-integrations self hosted sandboxes coming soon @hwchase17 How do you do evals in langsmith sandb
Harness: ✅ (DeepAgents) Sandboxes: ✅ (LangSmith Sandboxes) Eval: ✅ (LangSmith Sandboxes Model: integrate with all the popular models and providers Plus we have the engine that helps you turn this flyw
Harrison Chase comments positively on the utility of DeepAgents within Harness, suggesting this tool or integration provides significant practical value. The post likely reflects on features or capabi
🧑🏫3hr Long Deep Agents Course Great course from a member of the community on Deep Agents Covers task planning, file systems for context management, subagent-spawning, and long-term memory https://www
> Better Caching – Cache misses are the easiest way to drive your cost up. All of our requests are cache aware, so we’re reusing a warm cache wherever possible. We do this for you in Deep Agents - see
langchain is one of the few teams that actually explains the engineering behind agent concepts instead of just naming them. loop engineering, managed agents, memory systems. every time a new concept d
langgraph <3 New category drop on the Arena: ✨AI agent frameworks✨ Agent Experience (AX) update as of 06/26: 1/ @LangChain LangGraph 2/ @vercel AI SDK 3/ @crewAIInc 4/ @mastra For context: we evaluate
💪deep agents harness 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 ap
Frontier models are getting really expensive Model providers give us a bunch of features to reduce costs, but the support landscape is….inconsistent We made prompt caching support model-agnostic in de
I cannot provide a summary of this specific X/Twitter post as the URL appears to be either incorrect or from a future date (status ID 2070556265906917860 exceeds current Twitter IDs), making it inacce
'If I had to choose just one metric, I'd argue that the KV-cache hit rate is the single most important metric for a production-stage AI agent.' - Manus AI prompt caching is important! read about how w
In a real conversation, deciding when to speak takes about as much brainpower as deciding what to say. Voice agents haven't been built that way. @SierraPlatform's unlock was parallelizing thinking, li