World Wire

Vercel has released durable-harness , an open-source package that keeps coding agent sessions alive through crashes and timeouts. Vercel durable-harness wraps existing harnesses, including Pi, OpenCode, Claude Code and Codex, without changing them . Each session lives in a durable log. A dead function no longer means lost work. For teams moving agents off laptops and into the cloud, that closes a real gap. TL;DR Size: npm package, version 0.0.x, Apache-2.0. Adapters cover 5 harnesses: Pi, OpenCode, fx, Claude Code, Codex. Runs on: Vercel Functions plus Vercel Queues, Node.js 22+ with Postgres, or laptop files. Claude Code and Codex need a Vercel Sandbox. Performance: No latency or throughput benchmarks published. All recovery claims are self-reported by Vercel. Best: Finished model and tool calls are read back from the log, never re-run or billed twice. Worst: Experimental 0.0.x API. Claude Code and Codex run only in a Vercel Sandbox, even self-hosted. ...

Google team have released llm-d 1.0 , the first stable version of its distributed inference stack. This open-source, Kubernetes-native layer turns vLLM or SGLang model servers into one coordinated pool. They released it at the PyTorch Conference North America. It targets self-hosted agent and RL workloads, where round-robin load balancing breaks down. TL;DR A serving stack : Google reports a published benchmark on a 17,000-node multi-region GKE deployment. Runs on: Kubernetes with NVIDIA, AMD or Intel GPUs or Google TPUs, over vLLM or SGLang. Performance: Vendor-reported gains come from cache-aware routing, tiered KV cache offload and prefill/decode disaggregation. Best: Median TTFT cut by more than 85%, with 2.4x throughput, on an Ironwood TPU coding workload. Worst: RL time-slicing lifts accelerator duty cycle only to above 70%, so roughly 30% idle time remains. What is llm-d 1.0? llm-d was founded in 2025 by Red Hat, IBM, Google Cloud, CoreWeav...

Exa has released Exa 3.0 , an upgrade to its web search API for AI agents. The Exa 3.0 search API ships a larger embedding model and a cheaper search type, Exa Lite. Dynamic Highlights is now generally available. Exa claims that it leads Perplexity, Brave and Parallel on 8 benchmarks. Those benchmarks were run by Exa, so you can treat them as self-reported. For developers, the practical change is cost: Lite costs $4 per 1,000 requests . TL;DR Size: Exa tracks over 2 trillion URLs and serves 100 billion pages. Embedding model size: Not disclosed. Runs on: Hosted API only. Exa lists configurable search latency of 450ms to 1s . No self-hosted option. Performance: Exa 3.0 Auto ranks first on all 8 Exa-run benchmarks against Perplexity, Brave and Parallel. Best: 91.8% on BrowseComp, plus the widest lead on ATLAS (42.0% vs 37.2% for Perplexity). Worst: 42.0% on ATLAS is its lowest percentage score. Its BrowseComp lead over Perplexity is only 0.3 points. W...

Cloudflare has released a preview of Clairic , a new System One extraction model on Workers AI. The Cloudflare Clairic extraction model reads text or images and returns typed values, not generated text. It targets a job developers usually give to LLMs: pulling totals, dates and IDs into JSON. Clairic answers every requested field in 1 forward pass, with no reasoning and no output tokens. TL;DR Size: Parameter count not disclosed. 65,536-token context window , up to 4 images per request. Runs on: Cloudflare-hosted GPUs via Workers AI ( @cf/cloudflare/clairic ). No local option until weights ship. Performance: Sub-second extraction in Cloudflare’s tests. No standard accuracy benchmark is published yet. Best: Extraction step took 0.46 s vs 16.1 s for GLM-5.3 in Cloudflare’s claims pipeline. Worst: 4 of 21 TSA next-day forecasts fell outside its 80% interval. Multi-step arithmetic is unreliable. What is Clairic? Clairic is a Cloudflare mo...