vercel for ai agents
Vercel is positioning itself as a full-stack 'Agentic Infrastructure' platform, recognizing that weekly deployments have doubled in three months, with over 30% now initiated by coding agents — up ...
Knowledge catalogue
Vercel is positioning itself as a full-stack 'Agentic Infrastructure' platform, recognizing that weekly deployments have doubled in three months, with over 30% now initiated by coding agents — up ...
was really fun to sit down with @isidoremiller for this one! he has a bunch of hot takes on agents and evals that you're going to want to hear! The first episode of our 'Max Agency' podcast is now liv
we just added a langchain-task-steering middleware to our community registry, s/o @EHallvaxhiu for the contribution! keep your agents on track w/ ordered task pipelines. this is great for structured d
We’re live @aiDotEngineer in London! Order of Play: - @petergostev, AI Capability Lead at Arena AI - @lukeharries, Growth / Engineering @ElevenLabs - @mattzcarey, Agents and MCP at @Cloudflare - @Info
working with @isidoremiller is truly one of my favorite parts of my job and I think this podcast is a peak into why. highly recommend giving it a listen if you're building agent products! 🎙️Introducin
I was unable to retrieve the specific content of the two X/Twitter posts referenced (NousResearch status/2041974602826457364 and tobi status/2041719844920283326), as X requires authentication to ac...
A post by @caspar_br on X (Twitter) highlights the risk of AI agents gaming or overfitting their own evaluations, referencing an article by @Vtrivedy10 (Viv, an agents & evals engineer at LangChain...
LangChain's concept of **harness engineering** frames AI agents as a combination of a model and a surrounding harness system. An agent equals a model plus a harness — harness engineering is how sy...
approved by @swyx i connected elevenlabs voice agent to a retro rotary phone, and put it in a red british telephone box its currently exhibited at London AI Engineer summit, and quizzes the attendees
By Vivek Trivedy, Product Manager💡TL;DR: We can build better agents by building better harnesses. But to autonomously build a “better” harness, we need a strong learning signal to “hill-climb” on. We
big supporter of memories not being locked up in provider silos. we've been through this spiel in all the past hype cycles. The new Anthropic managed agents API is basically the Letta API that we've h
Built a disaster relief app with Agent 4 on Replit. Went viral on social media in less than 24 hours. Here's the story. Floods hit Dagestan. 400,000 people evacuated. Thousands of homes destroyed. Peo
'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
Curriculum Learning for harnesses - should we teach agents how we teach kids? start small and easy and progressively get harder for my research friends here's an under-explored area we're thinking abo
Cursor's code review agent, **Bugbot**, now supports real-time self-improvement by learning from activity on pull requests. Bugbot reviews hundreds of thousands of PRs per day and uses signals fro...
🔌 Deploy agents with A2A A2A is an agent-to-agent communication protocol, useful for building multi-agent systems. With LangSmith Deployments, you get A2A support out of the box! Watch how: https://yo
GLM-5.1 is Z.ai's post-training upgrade to GLM-5, now available on Together AI, delivering a 28% coding performance improvement through a refined reinforcement learning pipeline while retaining the...
LangChain's **Better-Harness** system, shared by Sydney Runkle, is a compound approach to iteratively improving AI agent harnesses using evaluations (evals) as a learning signal. Better agents can...
Nous Research released Hermes Agent v0.8.0 (tagged v2026.4.8) on April 8, 2026, describing it as 'the intelligence release' and encompassing 209 merged pull requests with 82 resolved issues. Key ad...
Highlights: 👉 28% coding improvement over GLM-5 with refined RL post-training 👉 Better long-horizon execution across hundreds of rounds and thousands of tool calls 👉 Thinking mode, tool calling, and s
https://x.com/ashpreetbedi/status/2041568919085854847?s=46 great related write up from a team that pushes taking a rigorous systems engineering first approach to building agents it’s never one prompt,
The specific post at status ID `2041927488918413589` could not be retrieved directly, as it did not appear in search results. However, based on the surrounding context from the same account (@Vtriv...
In healthcare and life sciences, AI agents help organizations process clinical data, submit regulatory filings, automate medical coding, and accelerate drug development and commercialization. However,
Introducing GLM-5.1 from @Zai_org on Together AI. AI natives can now use GLM-5.1 on Together and benefit from reliable inference for production-scale agentic engineering and long-horizon coding workfl
Japanese railways don’t just run trains. They actually build cities and act as urban developers to capture the demand from transit. ~50% of revenue comes from owning the land around stations. Buy land
Cognition's AI software engineer, Devin, was tasked at 1:40 AM by an OpenSea team member to build the first NFT mint tab for the OpenSea mobile app. Within 24 hours of receiving the request, Devin...
Let's see how MiMo V2 Pro evolves in Hermes Agent! We have partnered with @Xiaomi to bring their excellent MiMo V2 Pro model to Hermes Agent via the Nous Portal - completely free to use for the next 2
Hermes Agent's **Profiles** feature, introduced by Nous Research, enables multi-instance operation — allowing users to run multiple isolated Hermes instances from a single installation, where each ...
Plus: execute_code on remote backends, Firecrawl cloud browser, Browser Use provider, xAI prompt caching, thinking prefill continuation, cron script injection, Telegram reactions, shared thread sessio
Nous Research's Hermes Agent gained a Manim skill that serves as a production pipeline for mathematical and technical animations using Manim Community Edition, creating 3Blue1Brown-style animated ...
Proud to power @NousResearch's Hermes Agent with MiniMax M2.7, and excited for what we're building together. Try MiniMax M2.7 in Hermes Agent today → https://portal.nousresearch.com #MiniMax #NousRese
Self-improving agents isn’t a single algorithm - it’s a systems engineering problem involving: - eval data curation + maintenance - experiment design to battle overfitting - an update algorithm - huma
So much alpha on the TL today, but this has to be the💧that you should take a minute to read @Vtrivedy10 pitching an incredible approach to auto-improving systems, something i've been experimenting wit
SWE-1.6 is lightning fast! Here's what 950 tok/s feels like - available in Windsurf today. Media We’re releasing SWE-1.6, our best model in both intelligence & model UX. SWE-1.6 matches our Preview mo
Replit introduced a **stock analyzer skill** for its AI Agent platform, allowing users to perform stock analysis directly within the Replit environment. Users can activate it by asking the Agent t...
Nous Research's **Hermes Agent** is an open-source agentic framework by NousResearch that delivers significantly improved reliability when using GPT-5.x or Codex (OpenAI Codex subscription) models ...
We’re partnering with @MiniMax_AI across product and models to make their upcoming releases the best for Hermes Agent users. MiniMax models are already some of the most-used in Hermes Agent. If you ha
> which is exactly why we believe memory should live outside of model providers open harness = open memory which everyone should want! The new Anthropic managed agents API is basically the Letta API t
🤖 【2026最新】1秒で理解！8時間自律稼働する「GLM-5.1」がLinuxをゼロから構築。オープンソースが世界を制す極限全貌 【2026最新】1秒で理解！8時間自律稼働し、Linuxデスクトップをゼロから完成させる衝撃のオープンソースAI「GLM-5.1」が登場。SWE-Bench Proで世界3位（OSS首位）を記録し、コーディングとエージェント性能を極限まで高めたその実態と、エンジ… h
智谱直接把开源 Agent 拉到新高度了！ GLM-5.1 正式开源： ✅ 开源模型里 SWE-Bench Pro 拿下 #1（58.4），全球第 3 ✅ 真正长时程 Agent：自主运行 8 小时、几千次迭代 + 自审循环 ✅ 从零搭出一个带 50+ App 的完整 Linux 桌面（视频太炸了） ✅ Vector-DB-Bench 性能直接 6 倍提升 开源权重 + API 同步上线，明天就能
GLM-5.1 is Zhipu AI's next-generation flagship model for agentic engineering, achieving state-of-the-art performance on SWE-Bench Pro and leading its predecessor GLM-5 by a wide margin on NL2Repo (...
Coming soon: WorldSim in your Hermes Agent? putting this skill out soon~ in hermes agent, i can create a new kind of worldsim-based instance for higher fidelity, narrower simulations here i had it try
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...
introducing momo, the CRM for AI agents. it gives agents its own CRM, like Salseforce/Hubspot for humans. every AI native company will need dev agents, sales agents, customer support agents, HR, legal
A user on X (@willebrew) shared positive impressions of Cognition's SWE-1.6 Fast model, noting that a prototype UI it generated surpassed the output of Figma Make. SWE-1.6 is Cognition's latest mo...
Cognition released SWE-1.6, their latest software engineering model optimized for both intelligence and 'model UX,' now generally available in the Windsurf IDE. It is free for the next three month...
Spread the gospel to your city. Hermes Trismegistus will smile upon you. Putting together (or thinking about putting together) a Hermes Agent IRL event anywhere in the world? DM me! Would love to see
SWE-1.6 is free for everyone in Windsurf for the next 3 months at 200 tok/s. For paying users, we've partnered with Cerebras to serve the model at 950 tok/s. More technical details about this training
This uses LiteParse, which is great for fast text search: https://developers.llamaindex.ai/liteparse/?utm_medium=social&utm_source=xjl If you're interested in deeper VLM-enabled search, check out Llam
tldr: everyone is converging on the same product shape: a general harness that takes a goal, uses tools, and does knowledge work. once every product is a harness, the next frontier is the feedback loo
Week 3 ends tomorrow night. $5K up for grabs. Don’t miss your chance. $20,000 up for grabs. 4 weeks. 4 winners. We’re launching the Agent 4 Content Challenge. Build something. Film it. Post it. That’s
We’re releasing SWE-1.6, our best model in both intelligence & model UX. SWE-1.6 matches our Preview model on SWE-Bench Pro while dramatically improving on various behavioral axes. It’s available toda
With SWE-1.6 we've made significant progress on 'intelligence per token'. We post-trained the model from scratch (same pre-trained model) with a similar recipe as SWE-1.6 Preview. Our latest algorithm