Knowledge catalogue
We're sharing our new framework for tracking, investigating, and disclosing instances of model misalignment at OpenAI. The framework sets criteria and timelines for public disclosure, including when w
Our framework for reporting model misalignment https://openai.com/index/model-misalignment-reporting-framework/ // if you scrape away all the anthropomorphic language, all the nonsense about thinking,
RIP to every 'which framework should I use' thread. harness on top, framework in the middle, runtime at the floor. one stack, three heights, fully composable. paste these four images into claude and a
🎉Introducing PyFlue: The Python-Native Agent Harness Framework.🧰 💡Flue for Python: Fred K. Schott @FredKSchott CEO of HTML has launched Flue: The Agent Harness Framework for TypeScript. It brings prog
while exploring harnesses, i came across my first and favourite agent orchestration framework @LangChain has launched deep-agents last year. it’s a wonderful harness, that has a lot of tools: - write_
New research from NVIDIA. They just dropped a PyTorch-native training framework for agentic RL. (bookmark it) Paper summary: Molt is a PyTorch-native agentic RL framework with an unusual design target
eve is like Next.js, for agents framework for building agents. one folder, durable by default ↓ https://x.com/vercel/status/2067180054979936413 Introducing eve, an agent framework. 𝚊𝚐𝚎𝚗𝚝/ 𝚊𝚐𝚎𝚗𝚝.𝚝𝚜 𝚒𝚗𝚜
3/ Harbor integration Harbor is a framework for running long running, stateful agent evals We integrate with it in multiple different ways. We wrote a blog on those integrations: https://www.langchain
Learn to use the new eve agentic framework from Vercel. Go try out the hands-on labs now. I'm digging the eve agentic framework from Vercel. I like that everything is files, from the tools to the skil
I'm digging the eve agentic framework from Vercel. I like that everything is files, from the tools to the skills to the evals. More importantly, it's gets you building with agents fast. Very promising
Enjoyed the read? If you have deep experience in ML frameworks (training or inference) and love working on problems like these, our team is hiring! ML Systems Engineer, Frameworks & Tooling: https://j
Pay attention to this one, AI devs. This is particularly interesting if you work with long-horizon terminal agents that often drown in their own observations. TACO is a self-evolving framework that au
// From Language Models to World-Acting Systems // A critical review of agentic AI, and a framework that is genuinely useful for deciding how much authority to hand an agent. Here is how it works. The
Some of LangSmith's biggest and most engaged customers trace with: - @aisdk - Claude Agents SDK - OpenAI Agent SDK - No framework at all And I'm sure we'll see tons of http://pi.dev in the near future
DSGym is a comprehensive framework designed to evaluate and train AI agents for data science tasks, providing a structured environment for benchmarking agent performance across various data science wo
KYA is a framework-agnostic trust layer designed for autonomous systems that provides verifiable guarantees, addressing the need for trustworthy and transparent operation of AI agents across different
RL environments now have a home on the @huggingface Hub. Every RL framework has its own way to find environments. Custom hubs, runtime registries, GitHub lists with a custom loader. If you publish for
Thanks @juliafedorin for a great conversation! Some tidbits from the podcast on the AI space: - We've pivoted from building a RAG framework towards building the document infrastructure for agents - Do
The LangChain team has built some nice LangSmith tracing/observability integrations with voice AI orchestration frameworks and the speech-to-speech APIs from OpenAI and Google. LangChain pioneered a l
native integrations for four leading voice frameworks so you can see whats happening dont fly blind Voice agents are exploding. Don’t let them be a black box in production. Today, we’re launching Lang
Voice agents are exploding. Don’t let them be a black box in production. Today, we’re launching LangSmith tracing for 4 voice frameworks: 🎙️ @pipecat_ai 🎙️ @livekit 🎙️ @OpenAI Realtime 🎙️ @GeminiApp L
Jerry Liu built one of the most installed pieces of AI plumbing of the last three years. Then he sat down and told me the framework era he helped create is over. The agent harness ate the abstraction
The U.S. faces a chaotic #AI regulatory patchwork with over 1,200 state bills introduced in 2025 and no unified federal framework, researchers @JeffSonnenfeld and Stephen Henriques of @YaleSOM and @Ga
🧵 Slime: The Most Elegant & Comfortable RL Training Framework Ever A deep dive into why Slime redefines LLM RL training with clean architecture & production-grade engineering ✨ Insights from Zhihu con
We just wrapped recording with @jerryjliu0 of @llama_index 👀 His thesis: the AI framework era is over. Scaffolding collapses into the model. Context quality = moat that survives. Frontier models still
Harrison Chase, co-founder of LangChain, expressed strong conviction on X (formerly Twitter) that LangChain has the best team in the AI framework space, emphasizing the consistent quality and volume o
Apropos NVidia’s agent trust framework, anybody remember NemoClaw? Anyone using it? Introducing the NemoClaw Deep Agents Blueprint, a reference architecture for building open agent systems developed w
💯💯”The current agentic framework is fully unsafe and must be redesigned from scratch based on different fundamental principles.” Some observations around the interview Q:Can be AI test environments be
Introducing Halo, the best framework for post-training of open-source models. Halo delivers up to 2.8x the throughput of stock TRL with less peak memory, while models stay in their native HuggingFace
Elon just gave a much more practical explanation of the current AI safety problem....and laid out a practical framework for making frontier AI safer OpenAI and Anthropic are the two leading AI compani
Another special guest is hitting the stage at #FullyConnected26! @jerryjliu0 built @llama_index, the framework thousands of teams use to connect LLMs to their data. Come see Jerry and many more Sept 2
⚙️That is the framework Mistral is building toward: one in which enterprises, governments, and startups can use the best AI available, shape it around their own knowledge, and retain the value it crea
(deepagents existed ~10 months before EVE, but...) yes - the agent industry has shifted from: ~agent frameworks~ (langchain, ai sdk, llama index) to ~agent harnesses~ (deepagents, claude agent SDK, EV
The team at @vercel recently released the Eve agent framework, so we built a template that integrates LiteParse with it🦙 The template provides a set of read-only filesystem tools that let Eve resolve
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
While we eagerly await Fable 5's return, our agentic WebGPU kernel optimization framework kept running. Opus 4.8 picked up where Fable left off, pushing Liquid AI's new LFM2.5 230M to an unbelievable
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
Alongside it, Anthropic is releasing a proposal for how governments can address the risks posed by frontier AI and a policy framework for job displacement, for which we intend to provide substantial f
The Model Lab vs Agent Lab distinction is one of the clearest frameworks I've seen for understanding where AI value actually lives right now. TL;DR from @latentspacepod: • Model Labs compete on capabi
'Just use AI' can be useful (I call it The Crowd in my informal framework I gave in my post below), but you also need a Lab where people can go with their ideas and Leadership to make decisions about
- I still get nonstop questions about use cases, even though I think thinking about things in the use case framework is the wrong way of thinking about it - Enterprises are starting to see actual busi
Behind the MiMo API Price Reduction: The deepest price cut, up to 99%, is for Input (Cache Hit). The core reason is our inference framework now supports hierarchical KV cache optimization for SWA. Pro
An interesting work on Physical AI: PhysX-Omni. First unified sim-ready generation framework for rigid, deformable, and articulated objects, with a diverse dataset and new benchmark. 🌐 https://physx-o
co-sign. a very handy mental framework for what kinds of learning transformers do well today, and why it runs into limitations. when @ankit2119 and i wrote about the need for adversarial world models
Last I checked, the @llama_index OSS framework integrates with 78 (!!) vector stores. Investors (and builders starting out, and honestly me for a while) deemed this space as commoditized. One of the l
If you design production agent systems, this matters. Most devs accidentally let their framework defaults make critical architecture decisions without thinking it through. This paper shows you how to
right now Engine only works with LangSmith traces but it's super easy to trace to LangSmith, we accept OTEL and integrate with 30+ frameworks! if you want to migrate to LangSmith to try out Engine, we
Meet physics-intern🧑🎓, our agentic framework for theoretical physics. It takes Gemini 3.1 Pro from 17.7% to 31.4% on CritPt, a new SOTA on one of the hardest benchmarks for LLMs. Theoretical physics
arXiv:2605.09852v1 Announce Type: new Abstract: Machine learning algorithms are being used in high-stakes decisions, including those in criminal justice, healthcare, credit, and employment. The resear
We’ve spent a lot of time on the framework underneath Codex, so it can move quickly on routine work while stopping for review when the risk changes. Here’s how we use sandboxing, approvals, network po
🧠 Introducing NeuralBench: a unified, open-source framework to benchmark NeuroAI models. v1.0: 36 EEG tasks, 94 datasets, task-specific + foundation models. MEG/fMRI ready. MIT-licensed, FAIR's Brain
Jerry Liu discusses how AI now generates approximately 95% of code, arguing that the era of orchestration frameworks has ended and been replaced by newer approaches to AI development and integration.
Frameworks are dead. @jerryjliu0 of LlamaIndex called it — and then rebuilt the company around what actually matters: context. New episode of Beyond the Pilot: https://www.youtube.com/watch?v=HbXvX-Kt
another interesting part of the hermes architecture is how it integrates with the atropos framework. the hermes agent runtime lives inside an atropos compatible environment where multi-turn tool use,
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
Renuka Kumar and Prashanth Ramagopal from the @Cisco team built a LangSmith + LangGraph powered framework for multi-agent coordination that behaves like a real-world software team. An inside look → ht
1/5 When we saw our Reducer (=LLM judge component in Maestro, our agentic framework, that selects the best output from parallel agent runs) consistently picking gold patches, we were sure Claude Opus
Harrison Chase shared a post on X (formerly Twitter) describing a resource as a very helpful overview that also presents a clear framework for understanding Anthropic's recent positioning toward OpenC
// human-values.pseudo | ARTIFACT 0.1.0-experimental.1 | BASE 1.2.0-rc1 | EDITION ai-compact | NARRATOR System_Synthesis_Node_01 | PROVENANCE human-directed, AI-assisted | STATUS single-encoder resear
// 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