Coding agents are writing code faster than ever, but Git infrastructure is becoming a bottleneck. GitHub just introduced Project Rubicon, a new Git storage architecture built to handle this growing load. In internal tests, it supported 5,000 agents working on the same repository and handled 7,200 pushes per second. It separates compute from storage, so GitHub can scale without changing how developers use Git. OpenAI and Anthropic have also built their own systems, Pando and Scion, to tackle similar problems. AI is changing how fast we write code. Now the infrastructure needs to catch up.

Coding, 3D creation, and financial research with open weights. Kimi K3.1 Pro is Moonshot AI's multimodal MoE with 2.8T total parameters, 104B active, and a 1M-token context. 🤖 💻 Stronger coding execution: Scores 65.7 on Terminal-Bench 4.0. On the internal Kimi Code Bench 3.0 Long-horizon, it improves from K3's 55.95 to 61.2. 🔎 Research with tools: Reaches 70.0 on HLE-Full with tools and 92.1 on BrowseComp in the published evaluations. 🧊 Build and refine 3D assets: Writes and runs Blender and CAD scripts, scoring 92.7 Voxel IoU on BenchCAD with tools. 🏆 Financial document analysis: Achieves SOTA on OfficeQA Pro v2 at 64.4, covering retrieval, cross-document verification, and multi-step numerical reasoning. ✅ Fewer unsupported claims: Claim-level hallucinations fall from K3's 23.4% to 8.3% on the internal Kimi Hallu Bench Hard with tools, a stress test rather than a measure of everyday error rates. 📜 Kimi K3.1-Pro License; commercial-use and attribution conditions apply.

Coding agents broke OpenAI's Git. Codex sped up their engineers so much that by the end of last year the monorepo couldn't keep up. Slow pushes, failed merges, and reliability at times below 90%. The work multiplies. One engineer now has several changes heading to CI at once, and every push sets off more jobs fetching the same code. So they built a new Git backend called Pando. It went from kick-off to production in 10 weeks, designed by one engineer and written by teams of agents. Median push latency is down nearly 80%, and it now serves close to a petabyte of Git data a day. This is what agents do to infrastructure. Every agent is another worker pushing code, running tests and pulling data, and all of that lands on storage, networks and CPUs as well as GPUs. OpenAI hit the wall first because they use agents more than almost anyone, so at least the rest of us know what's coming. Every company that rolls out agents at scale is going to need a lot more infrastructure under them than it planned for

Coding agents can work in parallel. Their databases should too. Lakebase branches an entire Postgres database in under a second, giving each agent an isolated environment for migrations and testing without copying the parent database. How it works:

Coding drives innovation & fuels creativity. Yet the lack of diversity in programming can perpetuate biases & deepen inequalities in the digital world. On Thursday’s #WorldCodingDay#, @UNESCO is calling for a more inclusive digital future.

Coding Agent Index v2.0 scores are lower than v1.5 for almost every configuration measured on both. Across the 21 configurations evaluated on both Index versions, the mean Index score moves from 54.8 to 47.4, with 20 of 21 moving down. The shift comes from FrontierCode v1.1, where the same configurations average 45.1% against 65.6% on DeepSWE v1.1, with a smaller contribution from stricter SWE-Atlas-QnA-AA grading. Terminal-Bench 4.0 is unchanged. Scores on the two Index versions reflect different evaluation setups.

coding has exploded in 2026 which is a big reason openai and anthropic have pulled so far ahead after going all-in on it but once robotics starts taking off i think google's broader approach will really pay off unless better coding models end up accelerating robotics even faster though it's still too early to say

Coding CLIs keep getting more complicated. Daemons, 3 layers of TUIs, client-server architectures. The whole point of a CLI is to deliver intelligence with zero friction, and be unix-like. 💾 Try It's 6mb, starts in milliseconds, model-agnostic. It's tastefully minimal: MCP, Skills, Subagents and ACP built-in.

Coding tasks aren’t equally difficult, so why send every one to the same model? Smart Routing evaluates each task separately and selects the lowest-cost model capable of doing the job, helping balance model quality, latency and cost. In this demo, Omnigent splits an app build across planning, backend and frontend work, routes each task to a different model, and runs some of them in parallel. Learn more: GitHub repo for this series: