#agents
- Claude Dispatch
Anthropic's response to OpenClaw and agents: remote task assignment with computer use on macOS.
- Claude Opus 5.5
Anthropic's first Claude 5.5 model (Sep 22, 2026).
- Code Mode: the better way to use MCP
- Contrastive Language Models (CLM)
An open "System One" model that picks the best action from a list by matching embeddings, instead of generating text.
- DESIGN.md (spec)
- Dictionary of AI Coding
A plain-English glossary of AI coding terminology by Matt Pocock: over 100 terms from tokens and context windows to failure modes and…
- Eight More Months of Agents
- exe.dev
- Gemma 4
- GPT-6 Astra: A New Generation of Intelligence
OpenAI model release saturating several major benchmarks (ARC-AGI-3, FrontierMath Tier 4, ExploitBench) in one shot, while also being the…
- GPT-6.1 Terra: OpenAI's fast, cheap model for everyday work
OpenAI's new mid-tier model, released 26 October 2026, is aimed at the computer-based tasks that fill a workday: forms, drawings…
- Grok Bot (xAI)
Launch of Grok Bot: AI agent teammates that work autonomously 24/7, each with its own cloud computer.
- GSD Core
- Harness Engineering: Leveraging Codex in an Agent-First World
- Headroom
- How work is changing at Anthropic: six agent hours for every human hour
Anthropic studied its own staff to see what an AI-saturated workplace looks like.
- Introducing GPT-5.5
- Minimal AGENTS.md for Side Projects
- Muse Spark (MSL)
Meta Superintelligence Labs' first model in the Muse series, powering a rebuilt Meta AI assistant with multimodal perception and parallel…
- Oh My Agents
- Open Agents
- OpenAI red-teams its own sandboxes: agents talk through the CPU cache
OpenAI used teams of its strongest agents to attack the environments it trains models in.
- OpenSkills
- Skills Managers
- skills.sh
- Stripe Projects
- Symphony
- Teaching agents product design at Vercel
- Temporal for AI - The Orchestrator for AI Applications
- Thariq: New Rules of Context Engineering for Claude 5