OpenAI opens its Codex agent harness to every developer with the Agents API

Two days after the full-duplex voice model hit the API and a day after ChatGPT went free for 23 million US public servants, OpenAI is handing developers its agent machinery. The company introduced the Agents API in public beta: a managed service that exposes the same harness and infrastructure behind Codex — context management, tool use, multi-agent orchestration — through a single API call. OpenAI operates the harness and the sandbox; developers bring the tools and workflows.

The mechanics are straightforward: you specify a task, a model, tools, and an environment, and OpenAI runs the rest. A session spins up the Codex harness, fans work out to parallel subagents that each keep their own context, automatically compacts memory as a session nears its context limit, and loads only the tool definitions the agent actually needs to cut token spend. Environments are swappable — an OpenAI-hosted sandbox, your own VPC, or integrations with nine partners including Cloudflare, Modal, E2B, Vercel, Oracle and DigitalOcean — and the harness itself stays open source and inspectable. There are no extra API fees; you pay for tokens and tools as usual.

Why it matters: harness engineering is the quiet reason agent quality varies so wildly, and OpenAI is now productizing its own. Early customers report material gains — fintech compliance firm SafetyKit says cost per case fell 60% after migrating its case-review workflow, and Ciridae's CTO says evaluation scores rose from 0.71 to 0.85 with a 4x latency reduction on subagent flows. The deeper play is lock-in-by-quality: if OpenAI keeps improving the harness alongside each model release, developers who build on it inherit those upgrades without rewriting orchestration code — a moat that's harder to leave than any pricing scheme. Rivals aren't standing still; Anthropic has its own agent SDK, and a rich ecosystem of open-source harnesses is one fork away. But today, the company that proved agents can do days of work is renting out the machinery that makes it possible.

What to watch: adoption among logistics and compliance shops running long-lived production agents, and whether partner-hosted sandboxes fragment the experience or genuinely match the OpenAI-hosted one.

Agents that used to take a weekend of orchestration code now take one API call — would you hand your agent's plumbing to OpenAI? Tell us in the comments.

Kling 4.0 goes live with 30-second native video at 10-bit HDR

Kuaishou's Kling AI has spent two years becoming the video model people actually finish projects with. Its new flagship, Kling 4.0, went fully live on October 15 — and this round is less about prettier frames than about the two things that make a generated shot usable in a real edit: length and control. Kling 4.0 generates up to 30 seconds in a single native pass, outputs 10-bit HDR at 4K, 1080p and 21:9, and takes up to 15 reference assets in one task. That budget splits across ten images, fi

Brain organoids classified Braille at 83% — in a trio, not alone

Two stories today: human brain tissue on a chip decoded a tactile signal, and the data-centre company behind some of the largest AI contracts in Europe turns out to be six months behind on its flagship site. Human forebrain organoids grown on a microelectrode array classified Braille letters with 61 percent accuracy on their own and 83 percent when the responses of three organoids were combined, in a peer-reviewed study from the University of Bristol. The team took event-based tactile readings

Suleyman says Microsoft's base model beat OpenAI's on a quarter compute

Microsoft finished pre-training its biggest in-house model yet — then used it to make a point about the company it bankrolls. Microsoft AI completed pre-training of MAI-Base-2, a mixture-of-experts foundation model with 80 billion active and 2.8 trillion total parameters, and says the recipe is 4.2–12.3x more pre-training FLOPs-efficient than DeepSeek-V4-Pro-Base. The run itself is the number worth keeping: 16,000 Nvidia GB200 GPUs for 38 days across August and September, at 21% average model

Amazon's new Bee devices listen all day — for $11.99 a month

Amazon turned its always-listening Bee line into a two-device family on Thursday, and NVIDIA opened a 2.8-trillion-token Indic corpus recipe. The connecting thread: both are bets that the next AI money is in memory — yours, or your model's. Amazon put two new always-listening devices on sale, and both now lead to a subscription. Bee Frontier, the next-generation wristband that also clips to clothing, ships now at $74.99 in Onyx, Lavender and Sage — up from the $50 predecessor — with seven-day

Read more

Kling 4.0 goes live with 30-second native video at 10-bit HDR

Brain organoids classified Braille at 83% — in a trio, not alone

Suleyman says Microsoft's base model beat OpenAI's on a quarter compute

Amazon's new Bee devices listen all day — for $11.99 a month