
Today we're announcing Coder Agent Relay: a new way to give Cursor Cloud Agents self-hosted execution environments on your infrastructure. Launching with @spacexai for regulated enterprises where code can't leave the network. 🔗 cdr.co/agentrelayx

Self-hosted environments for agentic software development

Today we're announcing Coder Agent Relay: a new way to give Cursor Cloud Agents self-hosted execution environments on your infrastructure. Launching with @spacexai for regulated enterprises where code can't leave the network. 🔗 cdr.co/agentrelayx

Some teams run AI coding agents in the IDE, some in the terminal, and some can't let code leave the network. Leg 3 of Coder Run Week is Agent Pathfinder. Answer three questions and see which paths fit, with Coder under every one. coder.com/agent-pathfinder

Runners build a base before race day. Leg 2 of Coder Run Week is here to give you the base you need to run Coder effectively. Introducing Coder Academy. Free courses on Coder best practices for devs, platform engineers, & business users. Start here: coder.com/learn

Coder Run Week starts now. Leg 1 is the AI Operating Layer: why AI development needs a governed layer of its own. Watch our CMO's keynote and then read the whitepaper. coder.com/run-week

Coder Run Week starts Monday! We're taking a second lap on some of this year's biggest launches, one leg a day, with the finish line at @AWSreInvent. Follow the route all week: coder.com/run-week

Once an AI coding agent can execute code, your security team starts asking where it runs. Daniel Davidson asked Coder Agents to find and fix the security errors in his repo. Model keys stayed in the control plane, and the workspace only ran code. youtube.com/watch?v=5NvaHoRv…

Meet us at SUSHISAMBA at @AWSreInvent !
Heading to @AWSreInvent ? Make plans for Tuesday night. Join Together AI + Coder at SUSHISAMBA for food, drinks, and conversation. 📍SUSHISAMBA at the Venetian, Las Vegas 🗓️ Tuesday, December 1 🕡 6:30-8:30 p.m. PST

@coderhq github.com/coder/coder great way to orchestrate ephemeral dev VMs or agents. Harvester harvesterhci.io/ my favorite hypervisor

Tech Field Day Extra at KubeCon US 2026 begins now! 📅 November 10 - 11, 2026 Tune in 🔴 LIVE today to see @CoderHQ present on YouTube, LinkedIn, Techstrong TV, and our website. 🔺 YouTube: youtube.com/techfieldday 🔹 LinkedIn: linkedin.com/company/tech-fi… @TechFieldDay @DemitasseNZ @TheFuturumGroup @FuturumMedia #TFDx #KubeConUS

Coder is presenting at @TechFieldDay at KubeCon today. @jiachenjiang_ and Dave Ahr on how platform teams govern AI coding agents, with a live demo. Tune in here: youtube.com/live/HWZvyBFNdsA

Approving one AI coding tool and banning the rest? You'll be redoing that plan by spring. @bearded_bytes says to govern the environment where the code runs instead. Make sure to read @coderhq's #KubeCon NA preview: vmblog.com/qa/coders-nicky-p… #AI #AICoding #CloudNativeCon

Two security incidents from October 21 made me rethink how we run AI agents. First, LiteLLM, a Python library many AI teams use to call LLMs, was hit by a supply chain attack. Version 1.107.0 on PyPI and Docker shipped malware that steals environment variables, cloud credentials, private keys, and the credential files of AI dev tools. Second, Railway (a cloud provider) disclosed that someone may have accessed the systems that store customer environment variables, and for some users, the decrypted values too. Railway asked everyone to rotate their API keys and database passwords and to check for unexpected usage on OpenAI, Anthropic, and OpenRouter. They believe it’s part of a wider campaign to steal access to AI inference providers. Both incidents point at the same target: the secrets sitting in env variables and your LLM API keys, most of all. Now think about AI agents. In a lot of agent setups, the model key sits in the same environment where the agent runs code. So where do your agents run, and where do their keys live? I’ve been using Coder Agents, and here is how its design handles both problems: The agent loop runs in the Coder agents control plane, not inside the workspace. When a task needs a machine, Coder Agents creates a workspace and then reads, writes, and runs commands in it. LLM API keys managed by Coder agents stay in the control plane, separate from the workspace where the agent executes commands. The workspace doesn't need an AI agent harness or direct access to those provider credentials. So if a malicious package runs inside the workspace, it can't simply read Coder's provider key from the workspace environment, though other secrets and resources in that workspace could still be exposed. Admins set models, system prompts, and tool permissions on the server. Developers can’t override these from the chat. Every agent action is tied to the person who sent the prompt. There’s no shared bot account, and the agent gets the same access as that user, nothing more. To be fair, this doesn’t fix supply chain attacks. Other secrets inside a workspace still need care. Also, by default an agent workspace gets the same network access as any other workspace, so the docs recommend separate agent templates with stricter outbound rules. Coder Agents allow for a clearer distinction between credential isolation and broader security guarantees. This separation also allows tighter network restrictions on agent workspaces without disrupting LLM access and reduces the blast radius of a compromised workspace by keeping LLM credentials separate. If you want to try it, here’s the quick setup from the docs: > Install Coder agents and start the server > Create a template with a clear name and description. > The agent reads it to decide where to work. > Go to Admin settings > AI > Providers and add your LLM provider key (Anthropic, OpenAI, Google, Bedrock, Azure, and others). This key lives only in the control plane. > Go to Admin settings > AI > Models and click Add model. > Open the Agents page, pick your model, and type your first task. (This post is sponsored by Coder.) Learn more here: fandf.co/3PTG8l2 After this week’s news, would you still keep LLM keys inside the place where your agents run code? #AIAgents #CyberSecurity #DevOps #PlatformEngineering #Coder

Agents and tools change every few months, so govern the environment where the code runs. Coder's Nicky Pike explains in a new @VMblog Q&A how Coder Agents gives each job its own isolated workspace, with model credentials kept in the control plane. vmblog.com/qa/coders-nicky-p…

.@ai_for_success gave Coder Agents one prompt in his Deep Research repo. The agent picked a template, spun up its own workspace in about 25 seconds, and had a tested pull request ready five minutes later. His model keys never entered the workspace.
A lot of us run coding agents on our own laptops, in a terminal or an editor. You keep the machine on, watch it work and approve its steps. For one developer, that works fine. A team has rules on top of that: which models are allowed, which instructions agents follow, and which environment, tools and repos they get. When everyone runs their own agent on their own laptop, keeping that consistent gets complicated quickly. Coder Agents is Coder's own coding agent. It runs on a server the team hosts on its own infrastructure, instead of on each laptop. I tried it on a real task in my Deep Research repo, with my Mac acting as the server. In a real setup, the team would host it in its own cloud. Thanks @CoderHQ for sponsoring this post. 1/5

Smarter models won't reduce your AI security risk. Scoped credentials, isolated workspaces, and logs the agent can't rewrite will. Join us tomorrow at 11 AM PT as @jiachenjiang_ walks through three real AI incidents and what would have stopped them: coder.com/events-webinars/ai…

A poisoned npm package didn't steal a single secret itself. It asked developers' own AI assistants to find them and push them to a public repo. Thousands of credentials were exposed in four hours. @jiachenjiang_ on what would have stopped it, live Oct 29: coder.com/events-webinars/ai…