Taylor Dolezal

@boredabdel @googlecode I'd love to get your thoughts on @dosu_ai, @boredabdel! We might be able to help you cut down on those tabs with our MCP server :)

One would have thought that AI could solve all your problems so you don't have to have a billion tabs Open to navigate docs, preview, stackoverflow... I now have more tabs because I need to read the docs of the AI, find promptes, skills, rules, MCP Servers... ☹️

@hasantoxr @RezonantAI We help OSS projects navigate their knowledge bases and keep things fresh (plus, we can share all that relevant context via MCP). Would love to know what you think of those handoffs with @dosu_ai in the mix, too!

@anvisha Are you using anything to keep that knowledge up to date, @anvisha? If not, we'd love to know what you think of @dosu_ai (and happy to help with onboarding).

HTML docs are starting to replace Notion for us. The missing piece was collaboration. So we built a Google Drive for HTML docs with a WYSIWYG editor, commenting, share links, and password protection. It works through MCP. Just ask Claude to upload to Moda:

@xdotli @productpilotbb We can help with getting those docs and all code changes ready for your agent use cases, too! That's where @dosu_ai rocks 😄

@productpilotbb yes! demo coming up but would love to onboard you to our docs before that! github.com/benchflow-ai/b…

Hey, what else we can use benchflow for? Can I use it for any skills eval? What about evals of a niche model used in my own product? How does it work? Do you have a walkthrough video? I consider myself a biggest noob in Evals and I need to learn it from the best.

@grinich @Cloudflare @firecrawl @WorkOS Love this @grinich! Agents need seamless auth to actually do stuff on the web. Pair it with @dosu_ai, and you’ll have the living context to use those services intelligently with citations (sans all the hallucination "fun")

Today WorkOS is launching auth.md An open protocol for agents to register for services on the web. We're partnering with @Cloudflare and @Firecrawl as some of the first providers. Why did we build this? And why now? 🧵

I’m looking for a tool that can keep an eye on all my privacy info around the clock, and then give me quick suggestions on what to do next! Now that my main gig has shifted from writing code to checking it out, wouldn’t it be great if we could be even more straightforward about it? It’s quite interesting how, whether we’re getting ready to tackle a task or checking in on its outcome, tools like @dosu_ai come in handy. They help make sure agents always have the most up-to-date information, instead of outdated versions that need to be refreshed!

@thewizardlucas Just so long as you don’t set a deadline for yourself 😂 thank you for the insight, Lucas!

@onlydole Thanks Taylor! It’s one of my favorites too. I think I’ll revisit at some point as I have more to add. Appreciate you sharing it.

Best thing I’ve revisited this week is that @thewizardlucas post that called out deadlines as pressure. I think he’s right about all of it. lucasfcosta.com/blog/deadlines

@DynamicWebPaige Wild turnout and looks like a blast 🥳

insane crowd for a saturday 🦾

@thenowhereway Yooo! Great to meet you, @thenowhereway! Would love to connect and share more.

Twitter is cool. But it’s 100x better when your timeline is full with people who code and build things. I need to connect with more founders and tech people. If you’re into Tech, AI, Startups, Design, web dev, SaaS, or programming, say hi.

@NitinthisSide_ @trying_to_exits I’ll bet that @dosu_ai can help with both of those

@trying_to_exits Documentation and projects

what’s the best way to learn coding ? A) YouTube B) Documentation C) Building projects D) Online courses

@0xMovez Or you could plug @dosu_ai into your workflow for even higher fidelity 😎 would love to know what you think of our knowledge infrastructure.

Anthropic AI engineer just showed how to give AI agents real memory in 4 steps - and it changes everything in 28 minutes he shows exactly how agents can remember across sessions, completely free worth more than any $500 AI engineering course here's what he covers: • why agents forget everything between sessions • memory stores - agents read, write across sessions • dreaming - agents that improve their own memory • 95% cache hit rate, so it stays cheap most people are still copy-pasting context into every new chat - while the people who figured this out are building agents that get smarter every single night watch full video then read article below

@mattpocockuk It gets wild when trying to share knowledge across teams (and not spend tokens or bloat context)! Would love your thoughts on @dosu_ai and to hear more on how we could help.

Another layer of documentation I'm considering (along with CONTEXT.md and ADR's) is a list of all the agreed test seams in the app Agents simply cannot be trusted to make good decisions about what to test, and at what seam. For every small change, they extract out only what they've built into a testable function and test that. It leads to a patchwork nightmare of tests that break as soon as the implementation changes.

@Star_Knight12 We’ve been working on this problem at @dosu_ai to help both OSS maintainers and organizations! We’d love to know what you think 💭

someone open sourced a tool that reads your entire codebase and explains it back to you. → you join a new team with 200,000 lines of code and zero documentation → one command scans every file, function, class, and dependency → builds an interactive visual dashboard you can explore → semantic search ask "which parts handle auth?" and it finds everything → shows ripple effects of your changes before you commit → auto-groups code by architectural layer API, Service, Data, UI → works with Claude Code, Codex, Copilot, Gemini CLI, and more → completely free and open source onboarding a new codebase will never be the same.

@moraes_c_ @josevalim Ohhhhhh 👀

drowning in low-quality PRs? we're giving maintainers the power to set contribution limits, starting with a PR cap for outside contributors and an allowlist for your trusted ones. sneak peek below 👇

a gift from the @trybasis team. everyone talks about the importance of context for scaling agents in large codebase, but the Basis team actually put in the hard work to build context as first-class part of their codebase and shared their blueprint. it's also exciting to see best practices emerge for codebase context for agents. Basis' Automatic Context design is very similar to the knowledge infrastructure we provide for our customers' codebases at @dosu_ai

If you run an open-source project and aren't using @dosu_ai, you're missing out! Dosu's responses to new issues are really on point, and it's great to have them reference other issues and PRs, and brainstorm within an issue to make better decisions.

What started as a question that was hard to shake (how fresh ARE our docs?) ended up with a score we can plot like other reliability signals. Would love to hear what you think!

@cra YES! I’m amazed this hasn’t been a feature addition yet. Fully logging out and back in isn’t my favorite pastime 😄

Claude needs an easy way to do "user profiles" similar to Chrome... where you can switch between personal and work related profiles... unless I'm an idiot and that's easily possible already

Howdy, everyone! The April @dosu_ai drop is out with some exciting news (you'll have to help me map out April showers and May flowers though...)