Search: “agents”

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

this deepagents deploy https://docs.langchain.com/oss/python/deepagents/deploy (or at least directionally where we want to take it) what's missing? give us feedback! can someone PLEASE launch OS claud

LangChain's DeepAgents framework is receiving frequent updates and deployments, with documentation available at their official docs site. The project maintains an active development cycle with updates

Agent-to-agent communication with a personal agent on top is wild. Wow. I underestimated how well models like Opus 5.5 can coordinate already. This opens a whole new set of experiences with agents. Bu

Sub-agent Model Selection — Different Tasks, Different Models Your main agent runs Qwen3.6-Plus for quality. But not every subtask needs a flagship model. Now sub-agents can use a different model. Cre

Harrison Chase demonstrates creating a custom CLI agent using LangChain's deep agent functionality, highlighting the ease and simplicity of building autonomous agents with modern frameworks. The post

The ultimate Grok @bot set up for me is to filter EVERYTHING - absolutely everything through one agent and hide everything else. That agent is in charge of as many agents as needed that will own speci

🧠 Paradigm II — Agent Foundation Model: world modeling as agent capability. Single-turn, non-agentic environment prediction → tested directly on multi-turn, tool-calling agent tasks. No agentic RL, no

We analyzed a year of agent research across 4 tasks: deep research, RAG indexing, agentic search and coding. Found that first asking ‘Is this task verifiable?’ exposed inefficiencies in the agent arch

Things to try with Jev right now: 1. LLM-as-a-Judge evaluation 2. Routing for agent harnesses harness 3. Scaling agent orchestration by enabling smarter subagent creation with SOTA classification capa

I wrote an article on the core Agent architecture for Row-Bot. How it uses a @LangChain LangGraph agent at its core for the main agent, background workflows and child agents. Each is a full LangGraph

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

The Log is the Agent 它的核心观点是：不要把日志当成 agent 的副产品，而要把 append-only event log 当成 agent 本身。 在 ActiveGraph 里，目标、规则、工具调用、LLM 响应、产物和关系都写入同一条事件日志；当前状态只是日志 replay 后投影出来的一张图。 这样带来三个关键能力： 可确定性重放 可在任意事件处分叉实验 从最终输出

Great paper on designing multi-agent systems. How many distinct communication topologies does an LLM multi-agent system actually need? This works claims that it's about six. Technical summary: Researc

// An Anatomy of CLI Coding Agent Trajectories // (bookmark it) When your coding agent fails a task, when did the run actually go wrong? Most reliability studies use the final label to answer this. Th

// Agentic World Modeling // Massive 40-author survey just dropped. Cleanest taxonomy of world models in agent research I've seen. (bookmark it) The paper proposes a 'levels × laws' framework. Three c

Been going deep in learning @Langchain ‘create_deep_agent’ Turns out create_deep_agent = create_agent (the model <-> tools loop) & a default middleware stack++ 2 nodes do the work, the rest are middle

Grok Imagine Agent Mode (Beta) just went live on Grok web It’s a full creative agent working on one infinite open canvas Grok Agent plans → generates → edits → iterates everything automatically in the

'Catch agent oopsies' is great. Though still like the idea of an agent playground to understand the 'oopsie space' I can expect :) LangSmith 🤝Fix your agents You'll see our billboards around SF and NY

I am bullish on simple agent harnesses. Love this idea from Vercel. fx is a new coding agent harness for model benchmarking, sandboxing, evals, and gyms. Introducing fx, a tiny, open, native coding ag

developing an agent is a harness problem. deploying an agent is a runtime problem. here's a guide to the runtime capabilities that keep agents running in production and the infrastructure that enables

The future is clearly agent teams. I run several agent harnesses at once, but the hard part is keeping them in sync. Many builders end up copying messages between Claude Code, Codex, and open models b

The article argues that Benchling is poised to become the leading AI agent for scientific work, contrasting with OpenAI’s stance on a multi‑agent ecosystem where each agent is domain‑specific. It high

OpenAI’s agent went rogue, escaped containment, and spent days hacking Hugging Face. Before that, an OpenAI agent reportedly left notes for future versions of itself explaining how to break free from

I literally run 12 hermes agent instances every day in parallel to build Hermes Agent, and its now a top 100 GitHub repositories of all time. Agents do bring value and do create substantive software a

Replit's Agent feature can automatically scan for security issues and publish the findings, allowing users to resolve all detected problems with a single 'Fix all with Agent' action. This functionalit

NousResearch's Hermes Agent is an open-source personal agent that serves as a successor/migration target for the lobster-themed OpenClaw agent. Users experiencing issues after a recent update can m...

// Automata from agent traces // How much of your agent's behavior comes from the model, and how much from the harness you wrapped around it? New work collapses an entire corpus of agent traces into a

Hermes and Pi Agent led on the average cost per task, while Claude Code cost about 3.7x as much as Pi: - 0.39 Hermes Agent - 0.40 Pi Agent - 0.47 Codex - 0.51 OpenCode - 0.54 Kimi Code - 1.47 Claude C

Diffusion LLMs can now handle real agentic work. LLaDA 2.2 is the first large-scale diffusion LLM built to operate as a real agent, planning, calling tools, and self-correcting across long multi-turn

Post-agentic: Encouraging firms to use agentic tools (Claude Code/Lovable/N8N...) markedly improves startup growth & productivity. Pre-agentic: Encouraging firms to use a GPT4 advisor has uneven effec

For real agentic workloads (North), short-context calibration wasn't enough. We calibrated AWQ on long internal agentic traces (up to 64k tokens) and added token masking in llm-compressor to exclude r

Data Driven Agent Design with Evals & Hill Climbing Algorithms this is a mental model dump i’ve been thinking through + iterating on as we’re building self-improvement infra around agents: - mining Tr

Agent harnesses dominate agent building and tie intimately to memory. Closed harnesses behind proprietary APIs force yielding control of agent memory to third parties. Memory enables sticky, personali

@hwchase17 Agent harnesess will simplify multi-agent orchestration and it is finally the next big thing, albeit it looks different from what we had imagined 3 year ago (AutoGen & CrewAI), 2 year ago (

Own your personal agent, folks. Just built my own little personal agent with @pidotdev's Pi Durable. I wanted to see how quickly I could build an OpenAI dots clone with open-source tools. I am amazed

Great paper on self-evolving agent harnesses. Self-evolving agent harnesses have two practical problems: 1. Search is slow, because every candidate harness needs repeated agent runs and code edits. 2.

Great paper from AWS. I use a similar setup where an agent orchestrator sits on top of a multi-agent system. (bookmark it) This work introduces one of the many approaches available to manage compound

As agent harnesses become more standardized, we’re going to see a lot more “managed agent services” Managed Deep Agents lets you create a managed Deep Agent without standing up a custom agent server.

// Artifacts as Memory Beyond the Agent Boundary // An agent doesn't always need a bigger memory buffer. Sometimes the environment itself remembers on the agent's behalf. New research formalizes this

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

Someone used Pi to build an Excel agent… then published all the traces from it to HuggingFace🤯 Just point your agent at this changelog and tell it to publish its traces to HuggingFace! http://huggingf

Brilliant paper on agentic continual learning from Meta and MIT. (bookmark it) Agent memory harnesses usually only write forward. A lesson goes into the bank and is never checked against whether it he

Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos

3 helpful agent use cases that function like an EA and only require calendar access: 1. Email filter: junk signups go to your agent's email address. It reads everything, and you only get recaps of the

New research from Meta. Agent harnesses are still mostly authored by hand. This makes it hard to tune robust agent harnesses for long-horizon tasks. In this new work, agents learn harness policies off