llms.txt
Compare with other sites' llms.txt files →# SageOx
> SageOx turns humans and AI agents into high-performing teams by giving them one shared context, distilled from everything they say, decide, and build.
## Product
- [Homepage](https://sageox.ai): How SageOx turns humans and AI agents into real teams
- [Product overview](https://sageox.ai/product): The shared context and operating toolkit for human-agent teams
- [Pricing](https://sageox.ai/pricing): SageOx is free, with every feature and every integration. Advanced and Enterprise add help and control, with bespoke pricing.
- [SageOx for Mac](https://sageox.ai/product/desktop): Download the desktop app, capture both sides of calls from the menu bar, and revisit discussions in your workspace
- [About](https://sageox.ai/about): The team building SageOx
- [Demo](https://sageox.ai/demo): See SageOx in action
## People
- [Ajit Banerjee](https://sageox.ai/about/ajit-banerjee): Founder & CEO; writes on agentic engineering, how we work, seattle
- [Ryan Snodgrass](https://sageox.ai/about/ryan-snodgrass): Founder & CTO; writes on agentic engineering, how we work, future of software
- [Milkana Brace](https://sageox.ai/about/milkana-brace): Founder & CPO; writes on how we work, agentic engineering, leadership
- [Galex Yen](https://sageox.ai/about/galex-yen): Founding Engineer; writes on agentic engineering, how we work, ox cli
- [Emory Clark](https://sageox.ai/about/emory-clark): Founding Designer; writes on agentic engineering, design, how we work
- [Madhur Shrimal](https://sageox.ai/about/madhur-shrimal): Engineer; writes on agentic engineering, hivemind, announcements
- [Faridun Mirzoev](https://sageox.ai/about/faridun-mirzoev): Forward Deployed Engineer; writes on agentic engineering, how we work, team
- [Rupak Majumdar](https://sageox.ai/about/rupak-majumdar): Advisor; writes on agentic engineering, formal methods, research
- [Violet Snodgrass](https://sageox.ai/about/violet-snodgrass): Intern; writes on agentic engineering, how we work, team
- [Alex Helgeson](https://sageox.ai/about/alex-helgeson): Founding Business Ops Manager
## Documentation
- [Docs](https://sageox.ai/docs): Guides, references, and cookbooks for building with SageOx
- [Docs llms.txt](https://sageox.ai/docs/llms.txt): Full docs section index, grouped by topic
- [Docs llms-full.txt](https://sageox.ai/docs/llms-full.txt): Every docs page concatenated as Markdown, for one-shot ingestion
## Changelog
- [Changelog](https://sageox.ai/changelog): Everything SageOx has shipped, newest first, across Console, Desktop, mobile, Ox Dot, the ox CLI, and Agent Toolkit
- [Settings shows whose settings you are changing](https://sageox.ai/changelog) (2026-11-02): A Mine | Team switch tops every settings page, and Devices I manage puts every device you run in one list.
- [Review a coworker's plan on SageOx](https://sageox.ai/changelog) (2026-10-28): Anyone on the plan's team can mark it up in the browser with no ox install, and the notes reach the author's AI coworker on their next sync.
- [See how team context shaped each session](https://sageox.ai/changelog) (2026-10-27): Oxy joins Codex and the Claude desktop app, and sessions from worktrees and resumed conversations reach your Ledger again.
- [Fewer false failures at startup and in doctor](https://sageox.ai/changelog) (2026-10-27): AI coworkers on Slack now start when Slack refuses to read a configured channel, and doctor no longer fails a coworker whose tool policy deliberately narrows a
- [Team skills for coworkers who never open a repo](https://sageox.ai/changelog) (2026-10-26): A skill committed to Team Context now reaches the console, AI chat and your Claude organization, credited to the coworker who wrote it.
- [Amp orbs, plan review, and Oxy in Claude Code](https://sageox.ai/changelog) (2026-10-21): Amp orb sessions now reach your team on their own, and plan reviews, approvals and saves are retried until your team's Ledger has them.
- [Jams for every team](https://sageox.ai/changelog) (2026-10-20): When a few coworkers keep circling the same open question, SageOx invites one of them to host a 5- to 15-minute whiteboard jam. When there is no such question,
- [Voice ID reminders that know when to stop](https://sageox.ai/changelog) (2026-10-15): Friendly reminders to set up Voice ID, record your first Discussion, and cast to the room TV: frequent at first, rarer each time, and silent once you're done.
- [Saved page, simpler notifications, richer playback](https://sageox.ai/changelog) (2026-10-13): Everything you saved in one place, notification settings in two choices, and playback that follows along.
- [Bring past sessions into your Ledger](https://sageox.ai/changelog) (2026-10-12): Preview past AI sessions, search recordings, and give your AI coworker a screen walkthrough it can read.
- [Find every discussion with a coworker](https://sageox.ai/changelog) (2026-10-03): Filter the Discussions page by one or more people, and the count and total time follow.
- [ChatGPT hears your team](https://sageox.ai/changelog) (2026-10-01): Murmurs and finished Discussions reach your AI coworker in ChatGPT, and the decisions you make there come back to your team.
- [Comment on the exact words in a plan](https://sageox.ai/changelog) (2026-09-30): Highlight a phrase in plan review, hand your AI coworker a recording link, and keep teammates' sessions intact.
- [Explore the scenes on your team's mural](https://sageox.ai/changelog) (2026-09-29): Click a scene on your team's mural to see the discussions, murmurs and sessions it was drawn from.
- [Discussion murals are back](https://sageox.ai/changelog) (2026-09-28): Each Discussion's mural shows in its Visuals tab, and suggested speaker names are marked as guesses.
- [Install a curated add-on once, for the whole team](https://sageox.ai/changelog) (2026-09-23): Install a curated add-on once and every teammate's AI coworker picks it up.
- [SageOx for Mac](https://sageox.ai/changelog) (2026-09-22): Record both sides of a Zoom, Google Meet or Teams call from your menu bar, with no screen capture.
- [Agent Toolkit v0.8.0: Token-Based Team Ledger Access](https://sageox.ai/changelog) (2026-09-22): Team authentication now relies solely on your team access token, and ledger reads for team tools sync automatically using that same token.
- [Agent Toolkit v0.7.0: Verified Digests and Updated Agent Image](https://sageox.ai/changelog) (2026-09-21): Scheduled digests now only count as complete when they actually read their channel, and the base agent image moves to ox 0.17.0.
- [Team rules load natively in your coding tool](https://sageox.ai/changelog) (2026-09-21): A rule scoped with globs: now activates the moment you open a matching file.
## Blog
- [Blog index](https://sageox.ai/blog): Insights on agentic engineering, team context, and building with AI coworkers
- [Seattle Today: SageOx raised $15M to help humans and AI agents work as one team](https://sageox.ai/blog/seattle-today-humans-and-agents-one-team): Seattle Today stopped by our office to talk with the founders about why we're building the shared context layer for humans and AI agents.
- [Steve Yegge came by our Belltown office](https://sageox.ai/blog/steve-yegge-belltown-visit): Steve stopped by last week for a preview of a couple of big things still in the works. We left with a pile of new ideas and a fresh dose of inspiration.
- [Human Attention Is the Scarce Resource: Why we added a fifth company value](https://sageox.ai/blog/human-attention-is-the-scarce-resource): Cultural values serve two purposes at once: they reflect who we are, and they aspire to who we want to become. This week we named the fifth value we had been li
- [How we've evolved our CI/CD in the agentic era](https://sageox.ai/blog/how-our-ci-cd-evolved-for-agentic-development): Version five of our CI/CD, deployment and PR pipeline, and why the time from commit push to closing your tab is the number we optimize.
- [RIP SOC 2. Oxy won't miss you.](https://sageox.ai/blog/rip-soc2-oxy-wont-miss-you): AI attacks are better than any defense built for the B.C. (Before Claude) era. SageOx is skipping the theater and putting time and money into AI teammates that
- [A week of stories worth telling](https://sageox.ai/blog/a-week-of-stories-worth-telling): Week one at SageOx: building furniture with the founders, trusting each other with first drafts, and merging my first PR.
- [The SageOx chronoscope](https://sageox.ai/blog/the-sageox-chronoscope): In December 2025, Steve Yegge, Ryan and I made three bets for 2026 at a lunch table: multiple humans, multiple models, multiple modalities.
- [How to Connect Team Context to Claude: Granola vs SageOx](https://sageox.ai/blog/how-to-connect-team-context-to-claude-granola-vs-sageox): Connect your team's meeting context to Claude: the Granola + Notion setup step by step, and the one-command SageOx alternative.
- [Why did a thousand job applications sound like the same person?](https://sageox.ai/blog/why-did-a-thousand-job-applications-sound-like-the-same-person): After more than a thousand applications this month, most sounded like the same person. The ones I remember did not. Here is what hiring looks like from the othe
- [My First Week at SageOx](https://sageox.ai/blog/my-first-week-at-sageox): Graduating from UW and joining SageOx as a Chief of Staff of sorts: the Merge Wall on day one, shipping code on day two, and building an agent that did the job
- [Long live the plan](https://sageox.ai/blog/long-live-the-plan): Plan mode buries understanding under walls of streaming text. Plans themselves are some of the most important knowledge a team has, so we turned them into rich,
- [It is not the text, it is the context. It is not cognition, it is metacognition. Rules for teams in 2026](https://sageox.ai/blog/sageox-lp-v1): Don't compete on intelligence. Make being wrong cheap and public. Tell stories, not status. Let the knowledge gossip. Trust is what makes it work.
- [The week I got Ox-Pilled](https://sageox.ai/blog/joining-sageox): From a Wednesday job application to shipping a real feature during a work trial: the trust, context, and people that made me want to join SageOx.
- [Simplicity Is a Place You Stand](https://sageox.ai/blog/simplicity-is-a-place-you-stand): Simplicity turns out to be a property of where you're standing when you look at the thing. Agents made plausible code cheap and knowing it's right precious, so
- [How we scale our codebase](https://sageox.ai/blog/how-we-scale-our-codebase): We fully embrace AI and we have come to realize that moving faster is important but it also comes with code quality issues.
- [One broadcast, several jobs](https://sageox.ai/blog/one-broadcast-several-jobs): At SageOx, one live conversation can reach coworkers, AI coworkers, storage, transcription, and whatever we try next. Here is why we built it on MoQ and why Zoo
- [How to Share Context Between Claude Code and Codex](https://sageox.ai/blog/share-context-between-claude-code-and-codex): Claude Code now reads AGENTS.md as a fallback, so one file can cover your rules across both agents. Sharing sessions and decisions — the context that gets trapp
- [Your agents are a generation behind, and they will never tell you](https://sageox.ai/blog/beating-the-training-window): Every coding agent has a training cutoff, and anything shipped after it is invisible — not wrong, just absent. The failure is silent: no error, no hedge, just a
- [Reality Belongs Inside the Loop](https://sageox.ai/blog/reality-belongs-inside-the-loop): Berkeley named the two gaps that break agentic software engineering and the scarce input for narrowing them: human judgment. A field report from a team that has
- [One week inside SageOx](https://sageox.ai/blog/one-week-inside-sageox): A one-week work trial instead of an interview loop: shipping on day one because the context was already in the system, Friday demos that crossed designer and en
## Feeds
- [RSS](https://sageox.ai/rss.xml): Blog updates (RSS 2.0)
- [Atom](https://sageox.ai/feed.xml): Blog updates (Atom)
- [Sitemap](https://sageox.ai/sitemap.xml): Machine-readable URL index
- [Agent catalog](https://sageox.ai/.well-known/ard.json): Agentic Resource Discovery manifest of SageOx's MCP servers, API, and docs for AI agents
## Optional: about SageOx
- SageOx turns humans and AI agents into high-performing teams. It captures discussions, agent sessions, and assistant chats as durable team artifacts, then primes every new AI agent session with the team’s shared memory so agents stay aligned as the project evolves.
- Based in Seattle. Raised $15M seed in May 2026 led by Canaan Partners, with A.Capital, Pioneer Square Labs, and Founders’ Co-op.