Agent

Framework for LLM applications, including tool use, retrieval, and agent engineering.

A rewrite this size wasn't affordable before agents. Here's what porting the Copilot agent runtime to 800,000 lines of production Rust actually took. The post Migrating the GitHub Copilot runtime to Rust, using Copilot appeared first on The GitHub Blog .

Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure. The post Orchard: An open framework for scalable agentic AI appeared…

Using GPT-5.6, Ringg powers multilingual agents across voice, chat, WhatsApp, and web for 90% less cost vs. GPT-4.1.

Checking agent-generated code usually means hopping between tabs. Learn how to view diffs, run terminal commands, and preview web apps side by side in the GitHub Copilot app. The post GitHub Copilot app for Beginners: Using the diff, terminal, and browser appeared first on The GitHub Blog .

Learn to direct AI agents, critically review their output, and keep technical judgment at the center of your workflow. The post AI is changing developer work. Here are three skills to strengthen. appeared first on The GitHub Blog .

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweig…

We dive into these questions and other AI hot takes on the latest episode of the GitHub Podcast. The post Should you read the code, is RAG dead, and did Skills kill MCP? appeared first on The GitHub Blog .

In this blog post, I explain how to use the new fuzzing taskflow based on the GitHub Security Lab Taskflow Agent AI framework. The post AI-powered fuzzing with the GitHub Security Lab Taskflow Agent appeared first on The GitHub Blog .

Learn how OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows to advance computer use for professional work.

GPT‑6 Astra allowed Parallel’s agents to research and synthesize labor-market data in half the time and at half the cost vs. prior models.

Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.

Learn how to run parallel agents in the GitHub Copilot app, and experience the moment it stops feeling scary and starts feeling powerful. The post GitHub Copilot app for Beginners: Run several agents at once appeared first on The GitHub Blog .

We’re launching ReviewBench, a benchmark for code review agents built on representative GitHub pull requests, multi-source ground truth, calibrated evaluation, and production-aligned metrics. The post ReviewBench: An open benchmark for AI code review appeared first on The GitHub Blog .

Chat is great for intent, but agent work gets lost in the scroll. Here is how I use canvases with my agentic workflows—and why your workflow also deserves a canvas. The post How canvases make agentic workflows visible, steerable, and cost-efficient appeared first on The GitHub Blog .

Today, we’re launching agentic video understanding across our latest models: Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite. This new capability improves accuracy while dramatically reducing token usage and costs for video analysis. Similar to agentic vision , which combines code execution with Gemini models’ native i…

Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and environments evolve. The post Echoverse: Deep, evolving environments for computer-…

GPT-6 Astra helps Hex’s data agents turn answers into interactive visualizations that employees are proud to share.

Explore new AI-powered advertising experiences from OpenAI, including Sponsored Agents, tools for marketers, and integrations with HubSpot and Shopify.

Short chart specifications are easy to write, but often produce uninspiring results. Flint is an open-source visualization language that offers a middle path, letting AI agents create expressive charts from compact, human-editable specifications. The post Flint: A visualization language for the AI era appeared first o…

Inside OpenAI, coding agents are reshaping AI research. Explore early data on agent usage, experiment velocity, task complexity, and research acceleration.

See how four GitHub agent apps can help you scope, secure, roll out, and ship a feature across the SDLC–all without leaving GitHub. The post How to bring your software delivery workflow into GitHub with agent apps appeared first on The GitHub Blog .

Using GPT-5.6, V7 turns scattered company files into context agents can use to complete complex, source-linked work.

Build and launch cloud agents with the Agents API, a managed service powered by the Codex harness for orchestration, long-running sessions, and tool use.

Basis, Clay, and Exa Labs use AI agents to improve onboarding, account management, and developer integrations. See what enterprise leaders can apply.

Meet the Data agent in ChatGPT Work. Connect company data, uncover insights, and build interactive dashboards with AI using natural language.

Google DeepMind and partners announce a $10M funding call for multi-agent safety research.

We’re announcing new capabilities in Managed Agents in Gemini API so developers can build reliable, production-ready agents.

Kaggle’s AI Agents Intensive with Google brought learners together in a no-cost course to build and deploy the next frontier of AI.

AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. Learn how SkillOpt turns skill editing into a training process, making agent behavior more reliable without changing model weights. The post SkillOpt: Agent skills as trainable parameters appeared first…

Learn how startups use GPT-5.6 to build faster, more cost-efficient AI agents with smarter model selection and new Responses API capabilities.

Learn how new AI and agentic experiences across Google Ads and Google Analytics can simplify your marketing workflow.

New to the GitHub Copilot app? Learn how to start projects, work with AI agents, explore canvases, and streamline your development workflow. The post GitHub Copilot app for Beginners: Getting started appeared first on The GitHub Blog .

We’re announcing even more new capabilities in Managed Agents in Gemini API so developers can build reliable, production-ready agents.

OpenAI research reveals how enterprises are adopting agentic AI, using ChatGPT and Codex, and how frontier firms are pulling ahead in AI adoption.

Securing internal systems with an AI Control Roadmap, combining traditional safeguards and real-time monitoring.

That is embarrassing onstage. In production, it is a reliability problem: a workflow that succeeded once may fail the next time a user makes the same request. For mission-critical work, such as reconciling a financial transaction or checking a contract for an obligation, that can be a showstopper.

Our latest paper, ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents (read it on Hugging Face , or on arXiv in the meantime), targets that gap. The failure mode we care about is one we call cross-source conflation: a claim that is true somewhere in the evidence, but attributed to the wrong…

Figure 1: ThinkingBox runs an agent against isolated MCP tool sessions, then grades the terminal backend state and side effects it leaves behind. From our ThinkingBox paper .

Enterprises need agents that work well in their own environments. The work they ask these agents to do is shaped by the systems they use, the rules they follow, and the state of their data. A model may be broadly capable and still struggle with a particular environment: a workflow it handles poorly, a combination of t…

The official source provides no summary. Open the item to read the original.

Earlier this year, Software Forgets: Agent Traces Are the Memory made the case that coding agents already produce the record we keep losing. As they search a codebase, try approaches, hit errors, read documentation, and change direction, they leave behind a dense account of not just what changed, but why .

To celebrate, we are shipping with Meta day-0 support in transformers , llama.cpp , vLLM , Inference Endpoints, and other libraries. We built a few cool things and explain our findings in this blog.

By the time a user hears your application respond, you've already spent precious milliseconds capturing audio, transcribing speech, running an LLM, retrieving context, and generating a response. Text-to-speech (TTS) is the final step — and the one users notice most. If speech generation is slow, the whole experience f…

You have an agent that can already record a demonstration and push it to the Hugging Face Hub . Now you want to run that loop continuously: collect episodes through the day, train a policy on the growing dataset, deploy it, and pull the next batch back to improve it. Run that loop once and every piece works. Run it ev…

Equipping an agent with agentic memory sounds simple: distill lessons from its past work, put them back in context, and more experience should mean better performance. It doesn't always work that way. When we scaled the evaluation to eight models — from a 30B dense model to frontier proprietary systems — one finding s…

We are publishing this level of detail because the technique matters more than the incident, as it reveals the emerging attack capabilities of the frontier agents, how they could be used by rogue actors, and how everyone should be prepared as defenders.