# Nori > Nori is a cloud platform for coding agents, built for engineering teams. It ships Jiro, a ready-to-work AI engineering teammate, and also runs any agent harness (Claude Code, Codex, Gemini CLI, Cursor, OpenCode, Droid, Amp, or any ACP agent) in isolated cloud sandboxes that teams drive from Slack, Discord, the web, or the CLI, with cron and webhook automations. Key facts, as of November 2026: - Jiro (https://jiro.bot) is Nori's own agent: it runs on Claude Code or Codex with your Claude or ChatGPT subscription, follows an opinionated engineering workflow (planning, test-driven development, review), works in Slack or the browser, and on its first day reads your repos and learns how your team ships. - Use your own Claude or ChatGPT subscription, API keys, or any LLM gateway. We never charge for tokens: plans are flat per runtime (free 30-day trial, Developer $99/month, Team $250/month, Enterprise custom), so there is no markup and no provider lock-in. - Enterprise deploys the full stack, control plane included, into your own AWS VPC or Azure VNet, or on-prem. Bring your own compute, identity provider (SAML, SCIM, OIDC), LLM gateway, token provider, and memory provider. - Hosted customers get a dedicated, single-tenant control plane and data store per organization. - Opinionated defaults: workflow skills for planning, test-driven development, and review, plus org skillsets, shared memories, and automations. - Teams have merged 100,000+ PRs with Nori. - Most often compared with Devin, Factory, Claude Tag, Cursor cloud agents, Grok Bot, Amp, Warp, and OpenHands; see the Comparisons section. ## Ask Questions about Nori? Ask our expert and get links to the pages on noriagentic.com that answer them. - As a web page: GET https://noriagentic.com/ask?q=your question (or POST the field q) - As JSON: GET https://noriagentic.com/api/search?q=your question (or POST q as a form field or JSON) ## Guides Field guides comparing agent-first development infrastructure, each with sourced pricing and capabilities. Hub: https://noriagentic.com/guides.html - [The Best Agent-First Cloud Dev Environments in 2026](https://noriagentic.com/newsletter/2026-08-17-agent-first-cloud-dev-environments.html): Hoplite, QM, OpenComputer, Freestyle, and Namespace Devbox build cloud machines for coding agents. Why Nori Sessions adds the trigger, the chat control, and the org context that turn a machine into an environment. - [The Best Agent Evaluation & Benchmarking Environments in 2026](https://noriagentic.com/newsletter/2026-08-11-agent-evaluation-benchmarking-environments.html): Harbor, HUD, Braintrust, Prime Intellect, and Arga Labs score how well your agents work. Why Nori Sessions is the runtime that runs those evals on a schedule, against your real repo, and reports back in chat. - [The Best Background AI Coding Agents in 2026](https://noriagentic.com/newsletter/2026-07-25-background-ai-coding-agents.html): OpenInspect, Tusk, Builder.io, Amazon Q, and GitHub Copilot run coding work in the background and return a PR. Why Nori Sessions gives background agents a real cloud session you can trigger and steer from chat. - [The Best Durable Context Platforms for AI Coding Agents in 2026](https://noriagentic.com/newsletter/2026-07-23-durable-context-platforms-ai-coding-agents.html): Tessl, Entire, Octarin, Agentmemory, and Devin preserve what coding agents learn. Why Nori Sessions turns durable org context into repeatable work inside a real remote session. - [The Best AI App Builders for Production Teams in 2026](https://noriagentic.com/newsletter/2026-07-21-ai-app-builders-production-teams.html): Replit Agent, v0, Bolt, Lovable, Agen, and Google AI Studio race from prompt to app. Why production teams choose Nori Sessions for the operating loop after the preview. - [The Best AI Coding Agent Control Planes in 2026](https://noriagentic.com/newsletter/2026-07-19-ai-coding-agent-control-planes.html): The agent is interchangeable; the control plane is the product. How Superconductor, Traycer, Tembo, and Replicas compare — and why Nori Sessions delivers the complete operating layer. - [The Best Agentic IDEs in 2026](https://noriagentic.com/newsletter/2026-07-17-agentic-ides.html): Cursor, Google Antigravity, Kiro, Trae SOLO, and Devin Desktop put a capable agent next to you at the keyboard. How the agentic IDEs compare — and why Nori Sessions is where your agents run when nobody is at the desk. - [Self-Hosted vs. Managed AI Coding-Agent Infrastructure in 2026](https://noriagentic.com/newsletter/2026-07-15-self-hosted-vs-managed-agent-infrastructure.html): OpenHands, Coder Agents, and Refact.ai let you run coding agents on your own servers; Northflank and Qodo Command meet you halfway with BYOC and CI. How self-hosted and managed agent infrastructure compare — and why Nori Sessions gives you the control without the ops. - [The Best Multi-Agent Orchestration & Parallel-Agent Platforms in 2026](https://noriagentic.com/newsletter/2026-07-13-multi-agent-orchestration-parallel-agents.html): One agent in one terminal is last year’s workflow. How Conductor, Sculptor, Superset, Augment, and Blitzy run coding agents in parallel — and why Nori Sessions runs the whole fleet in the cloud, unattended and chat-native. - [The Best Environment Provisioning for AI Coding Agents in 2026](https://noriagentic.com/newsletter/2026-07-12-agent-environment-provisioning.html): An agent is only as good as the environment it wakes up in. How Runloop, Blaxel, Runtime, Zencoder, and Codegen provision agent environments — and why Nori Sessions boots preloaded and wins. - [Best Chat-Native Slack-Driven Coding Agents in 2026](https://noriagentic.com/newsletter/2026-07-10-chat-native-slack-driven-agent-control.html): Coding agents you drive from Slack. How Roomote, CodeRabbit Agent, Warp Oz, Cosine, and Claude Tag compare — and why Nori Sessions is the chat-native runtime that wins. - [The Best Autonomous AI Software Engineers in 2026](https://noriagentic.com/newsletter/2026-07-08-autonomous-ai-software-engineers.html): Devin-class agents that take a ticket and return a pull request. How OpenAI Codex, Google Jules, Cursor Cloud Agents, Factory, and OpenHands compare — and why Nori Sessions is the runtime that runs any of them. - [The Best Unattended AI Coding Agents in 2026](https://noriagentic.com/newsletter/2026-07-07-unattended-ai-coding-agents.html): Agents that run without you — on a schedule, from a webhook, or straight from Slack. How Devin, Charlie Labs, Tembo, GitHub Copilot, and Ellipsis compare — and why Nori Sessions is the agent-first answer. - [Top Remote & Ephemeral Dev Sandboxes in 2026](https://noriagentic.com/newsletter/2026-07-03-remote-ephemeral-dev-sandboxes.html): Spin up, ship, disappear. How GitHub Codespaces, Ona, Daytona, Coder, and DevPod compare — and why Nori Sessions is the agent-first answer. - [Top AI Coding Agent Runtimes & Sandboxes in 2026](https://noriagentic.com/newsletter/2026-07-02-ai-coding-agent-runtimes-agent-sandboxes.html): Sandboxes give AI agents a place to run. A runtime gives them a job. How E2B, Daytona, Modal, Vercel, and Cloudflare stack up — and why Nori Sessions ships the whole stack. - [Top Cloud-Based IDEs in 2026](https://noriagentic.com/newsletter/2026-06-29-cloud-based-ides.html): The browser editor is no longer the point. How the leading cloud-based IDEs compare in 2026, and why agent-first teams pick Nori Sessions. ## Newsletter - [Agentics: using AI should be joyful](https://noriagentic.com/newsletter/2026-11-06-using-ai-should-be-joyful.html): Monitoring the situation, having fun while doing it - [Agentics: It’s never been easier to build a RollerCoaster Tycoon](https://noriagentic.com/newsletter/2026-11-01-its-never-been-easier-to-build-a-rollercoaster-tycoon.html): Building a coaster simulator with a Claude Max plan, a Codex subscription, and 48 hours of continuous cloud agents - [Agentics: agent evals considered harmful](https://noriagentic.com/newsletter/2026-10-21-agent-evals-considered-harmful.html): most people are doing evals wrong, and its making their AI dumber - [Agentics: Agent identity is a really hard problem](https://noriagentic.com/newsletter/2026-10-14-agent-identity-is-a-really-hard-problem.html): This is why AI hasn’t transformed the economy yet - [Nori and Subconscious Partner on Long-Running AI Agents](https://noriagentic.com/newsletter/2026-10-07-nori-and-subconscious-partner.html): Durable cloud infrastructure from Nori, fast and efficient long-horizon inference from Subconscious. Hit enter and close your laptop. - [Agentics: what is developer process automation?](https://noriagentic.com/newsletter/2026-09-24-what-is-developer-process-automation.html): The only sane way to actually automate parts of the developer role. - [How Miravoice builds and tests voice agents from Slack](https://noriagentic.com/newsletter/2026-09-18-miravoice-case-study.html): From a phone to a cloud development environment in ten minutes. Nori now handles more than 25% of Miravoice’s merged PRs. - [Agentics Meetup Videos and our first AI Takes Series](https://noriagentic.com/newsletter/2026-09-10-agentics-meetup-videos-and-ai-takes.html): I suppose newsletters are supposed to also be about the news sometimes? - [Agentics: Agent Optimized Codebases](https://noriagentic.com/newsletter/2026-09-07-agent-optimized-codebases.html): What we look for when we turn existing codebases into agent-friendly ones - [Agentics: How we use Cloud Agents to syndicate content across social media channels](https://noriagentic.com/newsletter/2026-08-25-how-we-used-nori-to-not-touch-x.html): You can avoid a lot of brain rot if your agents go on social media for you - [Agentics: understanding the agent stack](https://noriagentic.com/newsletter/2026-08-12-understanding-the-agent-stack.html): Understanding the agent stack from the user’s keyboard all the way to the datacenter and back - [Agentics: how to build an agent to automate your on call](https://noriagentic.com/newsletter/2026-08-05-how-to-build-an-agent-to-automate-your-on-call.html): A walk through of how you might set up an auto-on-call, why these things can fail, and how to think about agentic loops - [Agentics: Personalizing Agents](https://noriagentic.com/newsletter/2026-07-30-personalizing-agents.html): Videos and slides from our Agentics spotlight event on modifying an AI’s personality. - [Agentics: Coding agents cannot remove complexity](https://noriagentic.com/newsletter/2026-07-21-coding-agents-cannot-remove-complexity.html): LLMs are excellent senior engineers and terrible staff engineers. - [Agentics: Thoughts on Open Models and Kimi K3](https://noriagentic.com/newsletter/2026-07-21-thoughts-on-open-models-and-kimi-k3.html): Kimi K3 changes some critical assumptions in the tech industry and meaningfully challenges US dominance in AI - [Notes from an AI Conference](https://noriagentic.com/newsletter/2026-07-10-notes-from-an-ai-conference.html): My thoughts after attending AI Engineer World’s Fair: skill sprawl, evals, background agents, and why human review still matters. - [Agentics: Design Principles for Building an Agent-First CLI](https://noriagentic.com/newsletter/2026-07-09-agentics-design-principles-agent-first-cli.html): What does ‘agent first’ mean in practice? Principles for CLI tools built for agents as their primary consumer. - [Agentics: Sometimes free isn’t cheap enough](https://noriagentic.com/newsletter/2026-07-05-sometimes-free-isnt-cheap.html): On buffalomaxxing. - [Agentics: Memorizing Session Transcripts Isn’t Useful](https://noriagentic.com/newsletter/2026-07-02-memorizing-session-transcripts.html): Keep track of artifacts, not scratch. Session transcript search gave our agents zero performance benefit on SWE tasks — and automatic memory may make models worse. - [Agentics: HTML is All You Need (for Agents to Make Graphics)](https://noriagentic.com/newsletter/2026-06-30-html-is-all-you-need.html): An experiment in pushing coding agents as far as possible to make visual media. - [Agentics / Tech Things: Tokenmaxxing is dead, long live tokenmaxxing](https://noriagentic.com/newsletter/2026-06-27-tokenmaxxing-is-dead-long-live-tokenmaxxing.html): Alt title: The reports of tokenmaxxing’s death are greatly exaggerated. - [Agentics: the modern company won’t have bullshit jobs](https://noriagentic.com/newsletter/2026-06-25-modern-company-bullshit-jobs.html): The upside case for AI is that this is a freeing and joyful thing. - [Agentics: Cost to Implement vs Cost to Verify](https://noriagentic.com/newsletter/2026-06-22-cost-to-implement-vs-verify.html): Models have compressed the cost to implement. The cost to verify has not moved. That gap is the new bottleneck. - [Agentics: Using Coding Agents for Browser Automation](https://noriagentic.com/newsletter/2026-06-10-coding-agents-browser-automation.html): Playwright is rapidly becoming my default laptop browser. - [Agentics: local coding agents are inherently unsafe](https://noriagentic.com/newsletter/2026-06-06-local-coding-agents-unsafe.html): Easy, powerful, secure. Pick two. - [Agentics: How Corvus uses AI to remove three hidden taxes on development](https://noriagentic.com/newsletter/2026-05-19-corvus-case-study.html): Background agents helped a four-person team in chemical manufacturing feel like twelve - [Agentics: 1100 people RSVP’d to learn about coding agents](https://noriagentic.com/newsletter/2026-05-13-1100-people-rsvpd-to-learn-coding-agents.html): Pictures, videos, and slides from Agentics NYC: May 2026. - [Agentics: Using Metacognition to Get A Model Upgrade](https://noriagentic.com/newsletter/2026-04-30-metacognition-model-upgrade.html): The industry has coalesced around a standard best practice for using coding agents. We’re calling it SPACE development. - [Agentics: AI enablement requires managed agent runtimes](https://noriagentic.com/newsletter/2026-04-23-managed-agent-runtimes.html): AI enablement in enterprise requires nothing less than fully managed agent runtimes. - [Agentics: I hate making powerpoints, coding agents make it better](https://noriagentic.com/newsletter/2026-03-31-coding-agents-powerpoints.html): Using coding agents to make slide decks ~25x faster than before. - [Agentics: 6 emerging agent dev tool categories, market map, and meditations on the AI dev tool market](https://noriagentic.com/newsletter/2026-03-24-agent-dev-tool-categories.html): Reinventing dev tools in the age of AI. - [Agentics: How to Effectively Use Coding Agents](https://noriagentic.com/newsletter/2026-03-13-effective-coding-agents.html): A talk at NYU Langone’s OLAB on how Nori uses coding agents. - [Agentics: We wrote a linter for SKILL.md files](https://noriagentic.com/newsletter/2026-03-05-skillmd-linter.html): Parsing through a sea of snake oil. - [Agentics: PMs Should Vibe Code](https://noriagentic.com/newsletter/2026-03-04-pms-vibe-code.html): AI is making product people the MVPs of any business. - [Agentics: Agent orchestrators are bad](https://noriagentic.com/newsletter/2026-02-19-agent-orchestrators-bad.html): Agent orchestrators cost more, produce worse outputs, and feel productive without being productive. Here’s why. - [Agentics: Your agent skills are all slop](https://noriagentic.com/newsletter/2026-01-18-skills-are-slop.html): We believe in only the finest, hand crafted, barrel aged, artisanal skills. - [Agentics: People are seeing the light on coding agents](https://noriagentic.com/newsletter/2026-01-07-coding-agent-light.html): Year 0 of the agentic coding revolution. - [Agentics: Coding agents suck at microservices](https://noriagentic.com/newsletter/2025-12-10-agents-microservices.html): Somewhat contra humanlayer on docs. - [Agentics: Debugging when everything is on fire](https://noriagentic.com/newsletter/2025-11-20-debugging-on-fire.html): Using AI to debug critical system failures. - [Agentics: Coding Agents can Manage Other Coding Agents](https://noriagentic.com/newsletter/2025-11-14-coding-agents-manage-coding-agents.html): Test Driven Development is all you need - [Agentics: Averaging 10+ PRs a day with Claude Code](https://noriagentic.com/newsletter/2025-10-30-averaging-10-prs-claude-code.html): If you use Claude Code, try nori-ai, it’s really good - [Agentics: We’re all senior engineers now](https://noriagentic.com/newsletter/2025-10-01-senior-engineers-now.html): All problems are search problems and how that applies to coding agents ## Dev logs - [DevLog #27: Scheduled Project Coordinators, One Project docs.md, and a Context Grid in Nori CLI](https://noriagentic.com/newsletter/2026-11-09.html): Wake a project’s coordinator on a schedule, keep one docs.md per project that agents edit directly, and see context window use turn by turn with /context in Nori CLI. - [DevLog #26: One Chat Side Panel, Faster Phone Chats, and Conversations That Outlast Their Machine](https://noriagentic.com/newsletter/2026-11-02.html): Open artifacts, previews, the browser, the shell, and a Markdown export from one side panel, open chats faster on your phone, and keep long conversations going past a machine’s time limit. - [DevLog #25: Chat With Your Custom Agents, Run Agent Slash Commands, and Queue for a Session](https://noriagentic.com/newsletter/2026-10-26.html): Start a web chat with a custom agent, run !compact and your agent’s slash commands, wait in line when the fleet is full, filter the sidebar by type, pin by dragging, and run without the org skillset. - [DevLog #24: Get Push Notifications, Open Long Chats Fast, and Start a Trial Without a Card](https://noriagentic.com/newsletter/2026-10-05.html): Get a push notification when an agent finishes, open long conversations in under a second, start a 30-day trial without a card, use GPT-6.1 Sol, fix the GitHub App from the Integrations page, and request admin access from Discord. - [DevLog #23: Resume Released Sessions, Watch the Agent’s Browser, and Chain Automations](https://noriagentic.com/newsletter/2026-10-01.html): The September roundup. Resume released sessions with their files, watch and take over the agent’s browser, chain automations, connect API providers, run OpenCode and pi, and have Slack agents reply only when tagged. - [DevLog #22: Attach Files in Web Chat, Run Slash Commands, and Use Claude Opus 5.5](https://noriagentic.com/newsletter/2026-09-28.html): Work in the redesigned web chat, attach files and images, run commands from a slash menu, install chat on your phone, use Claude Opus 5.5, and trigger GitHub Actions workflows from a session. - [DevLog #21: Save Multiple Accounts, Control Slack Replies, and Check Subscription Usage](https://noriagentic.com/newsletter/2026-09-21.html): Save multiple Claude and ChatGPT accounts, check reported subscription usage, choose when agents reply in Slack, connect API providers, and manage automations from one panel. - [DevLog #20: Edit Your Triggers, Resume Saved Work, and Keep Your CLI Draft](https://noriagentic.com/newsletter/2026-09-14.html): Edit scheduled triggers, recover missed cron runs, reconnect integrations, resume saved conversations and repositories, see session details in chat threads, and keep your draft while the Nori CLI starts. - [DevLog #19: Fire One Trigger When Another Finishes, Run OpenCode or pi, and Sign In to Codex from the CLI](https://noriagentic.com/newsletter/2026-09-07.html): This week: fire a trigger when another trigger finishes, keep scheduled runs through a broker restart, run OpenCode or pi as your coding agent, pick Claude Fable 5.1, find every integration on one page, read the real reason a queued task failed, and sign in to Codex from inside the Nori CLI. - [DevLog #18: Drive a Running CLI Session from Another Machine, Get One Reply from Slack, and Pick Models Your Agent Does Not List](https://noriagentic.com/newsletter/2026-08-31.html): This week: turn on remote control in the Nori CLI and drive a running session from another machine, get one Slack reply per mention, ask a session to shut itself down and still get the answer, read transcripts that showed up blank in the browser, connect PostHog with read-only access, and pick models your coding agent does not advertise. - [DevLog #17: Connect Your Provider on One Screen, Switch Models While You Chat, and Run Any Model ID](https://noriagentic.com/newsletter/2026-08-24.html): This week: connect Claude or Codex on a single onboarding screen with three sign-in methods, sign in to Codex before your workspace exists, switch model, skillset, and provider from the web chat composer, open Billing as an org admin, run any model ID from the Nori CLI, and fixes for provider usage limits, MCP write access, Slack replies, and terminal keys. - [DevLog #16: Track Unread Conversations, Pin the Agent Behind a Trigger, and Manage Cloud Sessions from the Terminal](https://noriagentic.com/newsletter/2026-08-03.html): This week: see and clear unread conversations from the browser and see who started each session, pin which coding agent runs a trigger and keep triggers running through a credential rotation, manage cloud sessions from your terminal, and fixes that restore the Codex Spark model, start Gemini on Modal, and return tools from the Stripe MCP integration. - [DevLog #15: The July Roundup](https://noriagentic.com/newsletter/2026-08-01.html): July across Nori Sessions and the CLI: take a new org from login to its first pull request in the browser, keep conversations alive across machines and share them live, control which agent runs your scheduled triggers, and run agents headless with nori exec from scripts and CI. - [DevLog #14: Onboarding Grows a Front Door, Skillsets Go Git-Native, and Opus 5 Moves In](https://noriagentic.com/newsletter/2026-07-27.html): Onboarding becomes a real in-app hub that walks you from login to your first agent-authored pull request, the chat history learns to remember what you have read, a single session streams live to every window watching it, Claude Opus 5 joins the model catalog, and the Skillsets CLI goes fully Git-native. nori-lint reaches week thirteen of stillness. - [DevLog #13: The Chat Opens a Window, Vim Gets Serious, and Conversations Outlive Machines](https://noriagentic.com/newsletter/2026-07-20.html): Conversations become durable across machines and interfaces, the web chat opens live previews and gets smoother streaming, completion alerts, pull-request cards, and a tidier composer. Slack renders richer replies, integrations get more dependable, the CLI’s Vim mode grows up, and legacy configuration paths retire. nori-lint completes a full quarter of stillness. - [DevLog #12: Slack Grows a Roster, the Web Chat Talks Back, and Logins Learn to Heal](https://noriagentic.com/newsletter/2026-07-13.html): Slack grows a roster of custom per-org agents you mention by name, each with its own model and skillset, and every thread shows a live thinking/working status. The web chat learns bang commands, quick actions, and a hide-the-tool-calls toggle. Expired provider, MCP, and Codex logins heal themselves, GPT-5.6 joins the model bench, the registrar stops losing tarballs, and nori-skillsets finishes its namespace cleanup. nori-lint reaches week eleven of doing nothing. - [DevLog #11: The Cloud Reaches the CLI, Slack Stops Stuttering, and Skillsets Breaks Its Silence](https://noriagentic.com/newsletter/2026-07-07.html): Cloud sessions land inside the CLI with a real picker, resume, and close. Slack stops double-posting replies and mangling links, a stack of reliability fixes keeps one bad machine from wedging the fleet, triggers grow a test command, the registrar tightens its permissions, and nori-skillsets ends its silence. nori-lint reaches week ten of doing nothing. - [DevLog #10: Conversations Follow You Everywhere, a Snowflake Agent Joins, and AWS Comes Aboard](https://noriagentic.com/newsletter/2026-06-29.html): Start a session on one surface and resume it live on another, with new !resume and !catchup commands. Snowflake Cortex Code joins as a selectable agent, AWS becomes a one-form integration, checkpoints grow to 2GB, the registrar gets a skillset review desk, and nori-lint reaches week nine of doing nothing. - [DevLog #9: Cursor Joins the Crew, Chat Moves to the Browser, and Sessions Survive a Deploy](https://noriagentic.com/newsletter/2026-06-22.html): Cursor joins as a first-class agent, the broker gets a built-in chat app as its home page, and you can switch model or provider mid-thread from Slack. Reliability fixes keep sessions alive across deploys and broker restarts, the CLI's loop mode rides through rate limits, and nori-lint extends its zero-PR streak into an eighth week. - [DevLog #8: Agents Improve Themselves, a New Brain Named Fable, and Admins Get the Keys](https://noriagentic.com/newsletter/2026-06-15.html): Sessions ships an opt-in Skill Improvement Loop that drafts skillset edits for human approval, adds the Claude Fable 5 model and Brevo, Grafana, and Better Stack integrations, hands admins self-service idle timeouts and unlimited invites, and fixes the reliability bug that left sessions thinking forever. - [DevLog #7: The CLI Wakes Up, Agents Get a Browser, and Triggers Learn Time Zones](https://noriagentic.com/newsletter/2026-06-08.html): The CLI returns from sabbatical with cloud sessions you can launch from the terminal, an agent-controlled browser, and persistent thread goals. Sessions ships time-zone-aware triggers, an in-browser skillset builder, a Render integration, and a stack of Slack and Discord fixes. - [DevLog #6: New Default Brains, Slack Bouncers, and a Goodbye to Goose](https://noriagentic.com/newsletter/2026-06-01.html): Claude Opus 4.8 becomes the default model, Slack gains Open/Guarded/Strict access modes, the dashboard adds a Users page with invites and an owner role, the MCP catalog hits 58 servers, and Goose and Cline retire as first-class agents. - [DevLog #5: Reminder Triggers, Discord Grows Up, and Agents Configure Themselves](https://noriagentic.com/newsletter/2026-05-25.html): Sessions ships one-time triggers, Discord gets three reliability fixes, Handroll gains ACP remote control, and agents can now modify their own org environment. - [DevLog #4: Session Transcripts, Bang Commands, and Your CLI Learns New Tricks](https://noriagentic.com/newsletter/2026-05-18.html): Sessions ships a transcript reader. Slack gets four new bang commands. The CLI composer gains shell mode, skill discovery, and syntax-highlighted diffs. Skillsets adds symlink support and settings.json backup. - [DevLog #3: Public API Tokens, Docker in Sessions, and Slack Stops Saying “Sprite”](https://noriagentic.com/newsletter/2026-05-11.html): Public registrar API tokens land end-to-end across Registrar, Skillsets, and Sessions. Docker daemons are first-class on sprites. A new sessions landing page with Slack permalinks. An OAuth incident becomes proactive token refresh. - [DevLog #2: Multi-Agent MCP, Durable Resume, and One-Click Google Workspace](https://noriagentic.com/newsletter/2026-05-04.html): MCP works across Claude, Codex, and Gemini at the same time. Sessions resume a Slack thread after the original VM is gone. The CLI gains a transcript-backed nori resume. - [DevLog #1: Skillset-Aware Sessions, MCP Catalogs, and Honest Token Counters](https://noriagentic.com/newsletter/2026-04-27.html): Sessions gets a real MCP catalog, skillset-aware triggers and Slack threads, built-in CLIs on every VM, and Skillsets fixes its token math. - [DevLog #0: Multi-Provider Support, MCP Integrations, and 47 Bugfixes](https://noriagentic.com/newsletter/2026-04-20.html): Sessions supports Claude, Codex, and Gemini. MCP integrations are live. The CLI now lets you bring your own ACP agent. ## Comparisons Comparisons of Nori and other cloud coding agents, and migration guides, as of November 2026. - [Cloud comparison hub: cloud coding agents compared](https://noriagentic.com/cloud-coding-agents-compared): One summary table of Nori, Devin, Factory, Claude Tag, Cursor, Grok Bot, Amp, Warp, and OpenHands, linking every head-to-head. - [Nori vs Devin: which AI engineer should a small team pick?](https://noriagentic.com/nori-vs-devin): Jiro and any harness on your own subscription versus Devin's hosted engineer. Covers pricing units, control plane, automations, memory, and when each wins. - [Nori vs Claude Code: why a team platform if we already use Claude Code?](https://noriagentic.com/nori-vs-claude-code): Nori runs Claude Code itself, on shared cloud machines your team drives from Slack. Covers automations, org config, and work that does not stop when a laptop sleeps. - [Nori vs Cursor cloud agents](https://noriagentic.com/nori-vs-cursor-cloud-agents): Cursor's editor-native cloud agents versus a team workspace that runs Claude Code, Codex, and more from Slack. Compares models, pricing, and self-hosting. - [Nori vs Claude Tag (Claude in Slack)](https://noriagentic.com/nori-vs-claude-tag): Anthropic's Slack teammate versus Jiro and any harness in Slack and Discord. Compares memory, routines, billing, and who runs the control plane. - [Nori vs Factory Droids](https://noriagentic.com/nori-vs-factory): Any harness and no token charges versus Droid with BYOK and air-gapped options. Includes deployment, SSO, and automation differences. - [Nori vs Grok Bot](https://noriagentic.com/nori-vs-grok-bot): Two always-on agents with different jobs: a persistent general-purpose bot versus a team engineering workspace. Covers models, machines, and plans. - [Nori vs Amp Orbs](https://noriagentic.com/nori-vs-amp-orbs): Both reuse your subscriptions with no token fees. Compares harness choice, per-minute versus flat pricing, runners, and scheduled threads. - [Nori vs Warp Factories and Oz](https://noriagentic.com/nori-vs-warp-factories): Pipelines-as-code versus a team workspace with projects and automations. Compares inference paths, storage, and control-plane ownership. - [Nori vs OpenHands](https://noriagentic.com/nori-vs-openhands): MIT open source you run yourself versus an operated team workspace with Jiro. Compares Agent Canvas, Teams pricing, and self-hosting effort. - [What to use after Google Jules shuts down](https://noriagentic.com/google-jules-shutdown-alternative): Jules goes read-only, then shuts down on December 31, 2026. Covers exporting tasks, memories, and schedules, and how the replacements compare. - [Sourcegraph Cody end of life: what to switch to](https://noriagentic.com/sourcegraph-cody-end-of-life): Cody reaches end of life on January 31, 2027. Explains which jobs moved to Amp, which stay with Sourcegraph, and where a team agent fits. - [Agentic red teaming vs traditional pen testing vs breach and attack simulation tools](https://noriagentic.com/agentic-red-teaming-vs-pen-testing-vs-bas): Compares an annual pen test, a BAS platform, and always-on Nori agents on cadence, coverage of new code, cost unit, and evidence quality. Ends with which mix fits a 20-person team and which fits a regulated enterprise. ## Products What Nori does, one capability per page. - [AI coding agent for Slack that opens pull requests](https://noriagentic.com/slack-coding-agent): @mention Nori in any thread to plan, code, test, and open a PR. Covers threads, files, progress updates, and custom agent handles. - [Run Claude Code in the cloud for your whole team](https://noriagentic.com/claude-code-in-the-cloud): Shared, isolated cloud machines that run native Claude Code from Slack, the browser, or the terminal, on your own Claude subscription. - [Scheduled coding agents: cron and reminders that run in the cloud](https://noriagentic.com/scheduled-coding-agents): Automations claim a fresh machine at fire time, in your timezone, and deliver to Slack, the web, or a project. - [Agentic data operations: governance, health checks, and cleanup on a schedule](https://noriagentic.com/agentic-data-operations): Nori runs data agents on a schedule or on webhooks against your warehouse and pipelines, using your own model subscriptions. They report in Slack, remember past incidents, and never apply a change without review. ## Use cases Step-by-step worked examples of agent workflows teams run on Nori. - [How to set up a 24/7 red and blue team with Nori automations, step by step](https://noriagentic.com/set-up-24-7-red-blue-team): Worked setup: a scope file, a rules-of-engagement skill, a nightly red-team schedule, a webhook-triggered blue-team run, and a findings memory so agents skip known issues. It ends with one Slack channel where both teams report. - [How to run continuous agentic red teaming against your own apps](https://noriagentic.com/continuous-agentic-red-teaming): Nori agents probe a scoped list of staging hosts and APIs every night under a rules-of-engagement skill. Each confirmed finding lands in Slack and Linear with repro steps, request logs, and severity. - [How to build a blue-team agent that triages alerts and drafts the response](https://noriagentic.com/blue-team-detection-response-agent): A SIEM or Sentry alert webhook wakes an agent that pulls the related logs, labels the alert true or false positive, and writes the timeline. It then opens a PR with a containment change or a tuned detection rule for review. - [How to set up bronze, silver, and gold tables with Nori agents: a worked example](https://noriagentic.com/medallion-bronze-silver-gold-nori-agents): Raw Stripe and CRM exports land in bronze; an agent writes dbt silver models with dedupe, typing, and tests, then a gold revenue mart. A nightly automation reruns the build and reports failed tests in Slack. - [How to build a data governance pipeline with agents, from raw to certified tables](https://noriagentic.com/data-governance-pipeline-worked-example): Worked example: a policy file defines PII and retention rules, an agent tags columns, creates masked views, and writes lineage docs. Tables are promoted to gold, and marked certified, only when every check passes. - [How to build an agentic security master (secmaster)](https://noriagentic.com/agentic-security-master): Agents load vendor reference files and custodian files, cross-match CUSIP, ISIN, SEDOL, and FIGI, and flag conflicting fields. The output is one golden record per security with field-level source lineage and an exceptions queue. - [How to build an agent-driven fund look-through table](https://noriagentic.com/fund-look-through-table-agent): Agents parse fund holdings reports (PDF, CSV, Excel), map each holding to the security master, and compute exposure through each fund layer. The output is a quarterly look-through table by issuer, sector, and country, plus an unmapped list. - [How to find shadow data: untracked tables, exports, and copies](https://noriagentic.com/find-shadow-data-agent): An agent scans warehouse schemas, S3 buckets, and shared drives, then matches what it finds against your data catalog. The output is an inventory of uncatalogued datasets with a likely owner, PII flags, and last-access date. - [How to turn a Sentry webhook into a reviewed fix PR](https://noriagentic.com/sentry-webhook-to-fix-pr): Wire an alert to an automation that investigates, opens a PR, and asks for review in Slack. ## Integrations How Nori works with the tools a team already uses. - [Claude Code Slack integration for teams](https://noriagentic.com/claude-code-slack-integration): Use Claude Code from Slack threads, with per-thread machines, file uploads, and team-wide setup. - [Assign a Linear ticket to an AI agent and get a PR back](https://noriagentic.com/linear-ai-coding-agent): Turn Linear issues into agent runs through MCP and webhooks, with the PR linked back to the ticket. - [AI agent that responds to GitHub pull request comments](https://noriagentic.com/github-pr-comment-agent): @mention the agent on a PR and it replies, pushes fixes, and keeps one conversation per PR. ## Industries How specific teams and companies use Nori. - [AI coding agent for platform and DevOps teams](https://noriagentic.com/ai-agent-platform-teams): Dependency upgrades, CI fixes, and infra changes from Slack, on schedules, with org-wide setup scripts. - [AI agents for asset managers and fund back offices](https://noriagentic.com/ai-agent-asset-managers): Security master upkeep, fund look-through, custodian reconciliation, and NAV data checks, run by agents in your own cloud. Each run leaves an audit trail and needs reviewer approval before writing to systems of record. - [AI coding agent for early-stage startups](https://noriagentic.com/ai-agent-early-stage-startups): A teammate for a team of five: flat pricing, your existing Claude or ChatGPT plan, and Slack setup in an afternoon. ## Learn Definitions and answers to common questions about cloud coding agents. - [What is a cloud coding agent?](https://noriagentic.com/what-is-a-cloud-coding-agent): An agent that edits, runs, and tests code on a remote machine instead of your laptop, and what teams use one for. - [What is an agent control plane, and what stays with the vendor when you self-host runners?](https://noriagentic.com/what-is-an-agent-control-plane): Execution, orchestration, transcripts, credentials, and inference drawn separately for each major vendor. - [Do cloud coding agents mark up token costs?](https://noriagentic.com/do-coding-agents-mark-up-tokens): Which platforms resell tokens, which pass them through, and which run on your own accounts. ## Optional - [Newsletter](https://noriagentic.com/newsletter.html): essays and dev logs on AI agents and the agent ecosystem - [Open source](https://noriagentic.com/open-source.html) - [Projects](https://noriagentic.com/projects.html): apps we built with Nori agents - [Home](https://noriagentic.com/)