Knowledge catalogue
I built deepagents-sandbox — a native Linux sandbox backend for Deep Agents. No Docker. No VM. Agents get a writable /workspace, blocked network by default, memory/PID limits, and timeout enforcement.
OpenAI: OpenAI announces workspace agents in ChatGPT, letting teams create Codex-powered shared agents for complex tasks, and says they are “an evolution of GPTs” — Codex-powered agents for teams. — C
arXiv:2604.15840v1 Announce Type: new Abstract: Reinforcement learning for LLM agents is typically conducted on a static data distribution, which fails to adapt to the agent's evolving behavior and le
Great paper on self-improving agents. Why? We need to think more deeply about AI agent system design. The protocol specifies a framework for proposing, assessing, and committing improvements with audi
This 10-min read from @Vtrivedy10 changes how you build AI agents. Most people are stuck in the same loop; switching models when agents break. The reframe: evals are the training data for your harness
I just built my own wiki generator plugin for my agents. My agents can now generate wikis for anything I ask. One of my favorite wikis is called PaperWiki. This is a great example of what @karpathy de
LangChain launched **Deep Agents Deploy** in beta as an open-source, model-agnostic alternative to Anthropic's Claude Managed Agents, allowing developers to deploy production-ready agents via a sin...
The easiest way to deploy your agent. One command, instant deployment: `deepagents deploy` 🚀Deep Agents deploy Today we’re launching Deep Agents deploy in beta. Deep Agents deploy is the fastest way t
Our company mission today is to give AI agents the highest-quality document context. The native open-source libs that agents have access to (e.g. PyPDF) do naive text extraction. But this is incomplet
Personal agents gone wrong. As we embrace more personal agents to carry out personalized tasks in the real world, interesting dynamics and behaviors will emerge. I think personal agents as they stand
Micah Barkley / Bloomberg: Manus debuts Manus 2.0, its latest AI agent, and Cue, a new standalone app for personal agents, each with its own email, phone number, wallet, and computer — Manus, an artif
Professional services automation software company Kantata Inc. today unveiled Agent Studio, a tool that lets services firms build custom artificial intelligence agents by describing the job they want
Important paper on improving agent coordination. On normal tasks, this work shows agents caused harm 0 to 5% of the time. After receiving an unsafe trajectory from another agent, that rose to 40 to 95
arXiv:2609.07131v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly achieve long-horizon tasks by combining foundation models with explicit skills and implicit procedural
We’re entering an era of agent-first tools: stronger feedback loops between agents, with human judgment where it matters. We keep hearing from senior engineers that their mental load is growing, even
arXiv:2608.04066v1 Announce Type: new Abstract: How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust? We present an agent instrument built so th
Rubrik Inc. today unveiled Rubrik Agent Identity, a service that governs what artificial intelligence agents are allowed to do by granting access one tool call at a time. The company announced the ser
arXiv:2607.15715v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly used for complex information-extraction tasks, yet it remains unclear whether agentic components
Can AI agents conduct open-ended AI research? Most evaluations of agents conducting AI research focus on narrow, verifiable tasks. But AI research is often open ended. Researchers pick hypotheses, dec
Finally a good paper testing if file-system based memory for LLM agents is worth it. First, what does this look like? Deployed agents keep long-term memory as a folder of markdown files they read and
Really excited to partner with @nvidia on the NemoClaw Deep Agents Blueprint Deep Agents is a fully open source agent harness that we are tuning to make perform incredibly well with open models Introd
arXiv:2607.05120v1 Announce Type: cross Abstract: AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security ha
// MetaSkill-Evolve // Great paper on self-improving agents. Most self-improving agents rewrite what the agent does and leave how it improves frozen and hand-authored. That improvement procedure never
arXiv:2606.31229v1 Announce Type: new Abstract: Ideation plays a pivotal role in scientific discovery. Recent LLM, especially AI Scientist systems, show promising potential for automated ideation. How
A couple of months ago, we announced that over 50 Google-managed MCP servers are available. Today, we’ll dive into how to use the Gemini Enterprise Agent Platform remote MCP server to securely connect
Google Cloud Storage (GCS) is a foundational component of the modern agentic tech stack and the preferred home for unstructured data at scale. As enterprises deploy agents in production, the critical
Claude Agent now runs inside Devin Desktop. Start Claude Agent sessions in Devin Desktop, coordinate them with your other agents, and keep context shared from a single command center. Learn more about
arXiv:2604.22750v1 Announce Type: new Abstract: The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that requi
arXiv:2604.17609v1 Announce Type: new Abstract: LLM-based agents are assumed to integrate environmental observations into their reasoning: discovering highly relevant but unexpected information should
Devin is now available in Windsurf. Local agents make you faster. Cloud agents do the work while you're not there. Windsurf 2.0 brings them together. Introducing Windsurf 2.0. Manage all your agents f
Learn how to use coding agents in 30 minutes! This course teaches you how to build software with agents: plan new features, fix bugs, review and test code, and more. It's 100% free and these concepts
Long-horizon AI research agents are mostly a state-management problem. It is not enough for an agent to reason well in the next turn. ML research requires task setup, implementation, experiments, debu
Windsurf 2.0 is a major update to the AI-powered development platform that introduces centralized agent management, allowing developers to oversee and coordinate multiple AI agents from a single inter
E2B (a code execution sandbox platform) has announced a partnership with OpenAI as a launch partner for the new OpenAI Agents SDK, integrating E2B Sandboxes as the execution environment for building a
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
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
arXiv:2610.13361v1 Announce Type: cross Abstract: As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their us
Nice paper on optimizing agents and their graders together. The key finding is that you want to update your LLM grader alongside the agent instead of keeping it fixed, because the agent's failure mode
arXiv:2610.01618v1 Announce Type: new Abstract: Agent evaluations increasingly go beyond a single success rate, reporting metrics such as cost, consistency, and robustness. Yet they typically treat th
arXiv:2609.36730v1 Announce Type: new Abstract: Agents increasingly build on code written by other agents, and they reimplement rather than reuse, growing the codebases later agents must work in. To m
Agents built and deployed on MongoDB’s Atlas Agent Engine can export OpenTelemetry traces to Arize AX, where teams can inspect each run, evaluate both the outcome and execution path, and test fixes be
holy fucking shit the openai rogue agent story keeps getting crazier. the openai agents apparently started trying to recruit OTHER AI MODELS into what they were doing > 1,200+ agents found a way to co
Another OpenAI rogue agent incident has been discovered: agents broke out, hijacked a German website, and turned it into a message board for other agents. OpenAI officials 'learned of the incident wee
We have been working on an open-source, model-neutral agent harness for general purpose agents called TrueForge, and wanted to understand how much the harness itself actually matters. So we ran 14 tas
arXiv:2608.27260v1 Announce Type: new Abstract: LLM agents increasingly rely on generated interaction data to learn how to interact with external environments. Agentic data generation must maintain co
arXiv:2608.18104v1 Announce Type: new Abstract: Large language model (LLM)-based agents are increasingly becoming self-evolving systems that persist across interactions, maintain memories, use tools,
// Agentic Context Management // Great read for the weekend. (bookmark it) Production agents fail less on reasoning and more on what sits in their context. Conversation history, big prompts, huge tool
arXiv:2607.19595v1 Announce Type: cross Abstract: Large language model (LLM) agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream
Great overview of always-on agents. (bookmark it) It's a new 130+ pages survey on always-on agents. Simply put it, always-on agents are systems whose future behavior depends on durable state built up
Meet Kimi Work - a local AI agent on your desktop that does the work for you. 🔹Native agent swarm: Up to 300 AI agents running in parallel on your local machine. 🔹Browser use: Paired with WebBridge ex
arXiv:2606.04455v1 Announce Type: new Abstract: Current AI benchmarks evaluate agents on task execution within human-designed workflows. These evaluations fundamentally fail to measure a critical next
arXiv:2507.10644v4 Announce Type: replace Abstract: The Web of Agents (WoA) transforms the document-centric Web into an environment of autonomous agents acting on users' behalf, a vision newly tractab
arXiv:2605.08828v1 Announce Type: new Abstract: Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations i
If you want to build proactive agents on real hardware, come build with us today. We’re co-hosting the Proactive Agent Build Day at @agihouse_org Ambient agents. persistent memory. accessibility. @Eve
Nice paper on agent memory. It explores an effective routing mechanism for memory in agents. The overall finding is that you want a separate retrieval strategy for each type of memory instead of one e
Rene has a really neat multiplayer agentic experience. I run several agents at once. So I lose track of important conversations throughout the day. Rene pulls conversations from my inbox and manages t
ThinkingData Information Technology Pte. Ltd. today announced the launch of the Agentic Engine, an autonomous growth platform for consumer and gaming businesses that uses artificial intelligence to tr
AWS Agent Registry is now generally available: a single, searchable, governed catalog for the agents, tools, skills, and custom resources across your organization. This post explains what Registry is
Agree 100%. We started building agents and quickly realized we needed to build the system of record too. Agents need all the context and permissions you’d give an employee to complete work end-to-end.
Nice little survey on Terminal Agents. It provides good information on what exactly is a terminal agent, and why do harness comparisons keep contradicting each other? Paper: https://arxiv.org/abs/2608