# ![@_StanGirard Avatar](https://lunarcrush.com/gi/w:26/cr:twitter::1217778667851538432.png) @_StanGirard Stan Girard

Stan Girard posts on X about open ai, claude code, api, agents the most. They currently have [-----] followers and [---] posts still getting attention that total [-----] engagements in the last [--] hours.

### Engagements: [-----] [#](/creator/twitter::1217778667851538432/interactions)
![Engagements Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1217778667851538432/c:line/m:interactions.svg)

- [--] Week [-------] +24%
- [--] Month [-------] +274,027%
- [--] Months [-------] +30,484%
- [--] Year [-------] +468%

### Mentions: [--] [#](/creator/twitter::1217778667851538432/posts_active)
![Mentions Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1217778667851538432/c:line/m:posts_active.svg)

- [--] Week [--] +82%
- [--] Month [--] +1,300%
- [--] Months [--] +725%
- [--] Year [--] +5.90%

### Followers: [-----] [#](/creator/twitter::1217778667851538432/followers)
![Followers Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1217778667851538432/c:line/m:followers.svg)

- [--] Week [-----] +21%
- [--] Month [-----] +23%
- [--] Months [-----] +23%
- [--] Year [-----] +25%

### CreatorRank: [-------] [#](/creator/twitter::1217778667851538432/influencer_rank)
![CreatorRank Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1217778667851538432/c:line/m:influencer_rank.svg)

### Social Influence

**Social category influence**
[technology brands](/list/technology-brands)  32% [stocks](/list/stocks)  2% [finance](/list/finance)  1% [social networks](/list/social-networks)  1% [travel destinations](/list/travel-destinations)  1% [countries](/list/countries)  1% [celebrities](/list/celebrities)  1%

**Social topic influence**
[open ai](/topic/open-ai) 13%, [claude code](/topic/claude-code) #651, [api](/topic/api) #360, [agents](/topic/agents) #2631, [vibe coding](/topic/vibe-coding) 4%, [$200month](/topic/$200month) #5, [6969](/topic/6969) 2%, [mcp server](/topic/mcp-server) 2%, [max](/topic/max) 2%, [to the](/topic/to-the) 2%

**Top accounts mentioned or mentioned by**
[@quivrbrain](/creator/undefined) [@langchainai](/creator/undefined) [@supabase](/creator/undefined) [@openai](/creator/undefined) [@hwchase17](/creator/undefined) [@kiwicopple](/creator/undefined) [@mistralai](/creator/undefined) [@llamaindex](/creator/undefined) [@fastapi](/creator/undefined) [@nextjs](/creator/undefined) [@ollama](/creator/undefined) [@jerryjliu0](/creator/undefined) [@realcharai](/creator/undefined) [@agishaun](/creator/undefined) [@raoufdevrel](/creator/undefined) [@neondatabase](/creator/undefined) [@posthog](/creator/undefined) [@resend](/creator/undefined) [@grok](/creator/undefined) [@litellm](/creator/undefined)

**Top assets mentioned**
[Alphabet Inc Class A (GOOGL)](/topic/google) [Handshake (HNS)](/topic/handshake) [Microsoft Corp. (MSFT)](/topic/microsoft)
### Top Social Posts
Top posts by engagements in the last [--] hours

"I can customize the Web UI. I can add integrations or create plugins. I can use Claude Code Web with Minimax and many other providers from the web. I can add auto-schedule (not sure about this one yet because this would be clearly against TOS). I can access it from my mobile phone and use API credits (not only subscription). Globally expose your awesome product to way more people and explore more freely how to best leverage it. http://Z.ai http://Z.ai"  
[X Link](https://x.com/_StanGirard/status/2021314474733355371)  2026-02-10T20:04Z [----] followers, [----] engagements


"I deleted every MCP server from my Claude Code setup. I was running MCP servers for everything. Postgres GitHub search browser automation. Background processes running all day waiting for my agent to maybe use them"  
[X Link](https://x.com/anyuser/status/2016488559746887939)  2026-01-28T12:28Z [----] followers, [---] engagements


"I reverse-engineered Claude Code's internal protocol. Now you can spawn and orchestrate agents from TypeScript. No SDK. No -p flag. Full programmatic control. OSS below 👇 https://github.com/The-Vibe-Company/claude-code-controller https://github.com/The-Vibe-Company/claude-code-controller"  
[X Link](https://x.com/anyuser/status/2020046807125090306)  2026-02-07T08:07Z [----] followers, 17K engagements


"I was burning $200/day on agent API calls. Then I realized: I already pay $200/month for Claude Code Max. So I reverse-engineered its protocol. Now I spawn agents via REST API monitor them from a dashboard and pay nothing extra. OSS 👇 https://github.com/The-Vibe-Company/claude-code-controller https://github.com/The-Vibe-Company/claude-code-controller"  
[X Link](https://x.com/_StanGirard/status/2020199249515016357)  2026-02-07T18:13Z [----] followers, 84.6K engagements


"You can also programmatically use and spawn Claude code with GLM [---] Minimax [---]. I built this project to be able to have 24/7 CC like agents working on thought project"  
[X Link](https://x.com/anyuser/status/2020395866025259084)  2026-02-08T07:14Z [----] followers, [----] engagements


"Big update I continued my reverse engineering and found a websocket with all the functions exposed So I built my own Web UI of Claude code that uses the vanilla binary. I can finally access Claude Code from my phone Made it open source too https://github.com/The-Vibe-Company/companion https://github.com/The-Vibe-Company/companion"  
[X Link](https://x.com/_StanGirard/status/2020983902144176239)  2026-02-09T22:11Z [----] followers, [----] engagements


"Hey @opencode & @thdxr Would love to add Opencode to the list before @claudeai patches it ;)"  
[X Link](https://x.com/_StanGirard/status/2021197584153575486)  2026-02-10T12:20Z [----] followers, 15.7K engagements


"This is actually funny It is partially right but false in the same sense. Yes you can do part of what The Companion does with the SDK but I simply listen to Websocket events and made a UI on top. I don't have to wait for the SDK to do it. And you technically can't use your subscription with the SDK (TOS ) @JayD0ubleu @_StanGirard @trq212 https://t.co/jttt5FxHZ1 @JayD0ubleu @_StanGirard @trq212 https://t.co/jttt5FxHZ1"  
[X Link](https://x.com/_StanGirard/status/2021342892988801161)  2026-02-10T21:57Z [----] followers, [----] engagements


"@Klaudioz Now maxing out my Claude code subscription all the time"  
[X Link](https://x.com/_StanGirard/status/2020211322559033622)  2026-02-07T19:01Z [----] followers, [----] engagements


"@itsgreyum Im simply using a mechanism they have and exposing it via API. It became possible thanks to the new swarm feature"  
[X Link](https://x.com/_StanGirard/status/2020216280502935712)  2026-02-07T19:21Z [----] followers, [----] engagements


"@gonzague @Tailscale @claudeai Je viens d'ajouter une feature d'environnements. Maintenant tu peux lancer @claudeai @ollama avec. http://Z.ai http://Z.ai"  
[X Link](https://x.com/_StanGirard/status/2021130201816584367)  2026-02-10T07:52Z [----] followers, [---] engagements


"@JayD0ubleu I'm almost done with a codex integration. Works pretty well. Didn't have to "reverse engineer" anything this time"  
[X Link](https://x.com/_StanGirard/status/2021351414585537011)  2026-02-10T22:31Z [----] followers, [---] engagements


"1 year of vibecoding daily. Shipped: docs [--] internal tools a Language Tool clone. Trashed: 50+ projects. The ratio is brutal but the wins save months. The real insight Everyone is lost. Seniors juniors founders. No playbook exists yet. We're all figuring it out live. Anyone who says otherwise is lying. http://quivr.com http://quivr.com"  
[X Link](https://x.com/anyuser/status/2015786927279022587)  2026-01-26T14:00Z [----] followers, [---] engagements


"Claude Code's swarm feature has a protocol. The master agent sends instructions via filesystem. The workers pick them up execute report back. I reverse-engineered it. Now any script can be the master. REST API. TypeScript SDK. Web dashboard. Same protocol. Different interface. Details 👇 https://github.com/The-Vibe-Company/claude-code-controller https://github.com/The-Vibe-Company/claude-code-controller"  
[X Link](https://x.com/anyuser/status/2020217743568769139)  2026-02-07T19:26Z [----] followers, 17.1K engagements


"To everyone saying you can get already do this with the sdk. Yes you can almost however you cant use your subscription with it"  
[X Link](https://x.com/_StanGirard/status/2020244952954073216)  2026-02-07T21:15Z [----] followers, [----] engagements


"I reverse-engineered Claude Code's binary. Found a flag they hid from --help. --sdk-url Enable it and the terminal disappears. The CLI becomes a WebSocket client. We built a server to catch the connection. Added a React UI on top. Now I run Claude Code from my browser. From my phone. From anywhere. Same $200/month subscription. Zero extra API costs. bunx the-vibe-companion http://github.com/The-Vibe-Company/companion http://github.com/The-Vibe-Company/companion"  
[X Link](https://x.com/_StanGirard/status/2020979746931085772)  2026-02-09T21:54Z [----] followers, 692.5K engagements


"How to access Claude Code from your phone I reverse-engineered the CC binary and found a hidden websocket. I built an UI on top of it and now I can launch hundreds of Claude Code from my phone using my subscription. https://github.com/The-Vibe-Company/companion https://github.com/The-Vibe-Company/companion"  
[X Link](https://x.com/_StanGirard/status/2020980797138747536)  2026-02-09T21:59Z [----] followers, 26.9K engagements


"Now it's Codex's turn to get a mobile/web open-source UI. Shipping in today. I reverse-engineered Claude Code's binary. Found a flag they hid from --help. --sdk-url Enable it and the terminal disappears. The CLI becomes a WebSocket client. We built a server to catch the connection. Added a React UI on top. Now I run Claude Code from my browser. From https://t.co/GHCLStJ4FD I reverse-engineered Claude Code's binary. Found a flag they hid from --help. --sdk-url Enable it and the terminal disappears. The CLI becomes a WebSocket client. We built a server to catch the connection. Added a React UI"  
[X Link](https://x.com/_StanGirard/status/2021316645054972000)  2026-02-10T20:13Z [----] followers, [----] engagements


"You can now run Codex & Claude Code from your phone. I added it to The Vibe Companion. Claude Code or Codex same UI no extra API costs. Pick your agent. Ship from anywhere. Install - bunx the-vibe-companion https://github.com/The-Vibe-Company/companion https://github.com/The-Vibe-Company/companion"  
[X Link](https://x.com/_StanGirard/status/2021359921519001699)  2026-02-10T23:05Z [----] followers, 28.1K engagements


"@CbsaSciencehub @OpenAI Agreed 👍 I wanted to showcase an example with no private data. However Ive tried it on [---] pages long contract and it worked very well"  
[X Link](https://x.com/_StanGirard/status/1722375159275782343)  2023-11-08T22:06Z [----] followers, [--] engagements


"@CbsaSciencehub @OpenAI Call me StanGPT 😂 copilot + ChatGPT"  
[X Link](https://x.com/_StanGirard/status/1722376069892780501)  2023-11-08T22:10Z [----] followers, [--] engagements


"@CbsaSciencehub @OpenAI No something different. Open source :)"  
[X Link](https://x.com/_StanGirard/status/1722376210817179887)  2023-11-08T22:11Z [----] followers, [--] engagements


"@VadlamaniVen @OpenAI @LangChainAI @llama_index @quivr_brain @hwchase17 Thats weird What could it be"  
[X Link](https://x.com/_StanGirard/status/1722376427398406638)  2023-11-08T22:11Z [----] followers, [---] engagements


"I spent a few days understanding OpenAI value propositions so that I can create a product that scales with them and isn't just a wrapper 👀 How can you create products in a market where one company dominates and iterates so quickly"  
[X Link](https://x.com/_StanGirard/status/1724454218029728185)  2023-11-14T15:48Z [----] followers, 14.4K engagements


"3 Build a product that isn't based on OpenAI Look at all the OpenAI features & Make sure that your product will not be replaced by OpenAI or one of their features. I hope you enjoyed the learning. I spent countless hours working and understand OpenAI in the last [--] months:"  
[X Link](https://x.com/_StanGirard/status/1724454228905619873)  2023-11-14T15:48Z [----] followers, [---] engagements


"- I've met hundreds of passionated people building awesome projects @hwchase17 from @LangChainAI @jerryjliu0 from @llama_index @RealCharAI with @agishaun @raoufdevrel from @neondatabase @kiwicopple from @supabase"  
[X Link](https://x.com/_StanGirard/status/1724454231782924472)  2023-11-14T15:48Z [----] followers, [---] engagements


"@hwchase17 @LangChainAI @jerryjliu0 @llama_index @RealCharAI @agishaun @raoufdevrel @neondatabase @kiwicopple @supabase - I've talked & helped dozens of Theodo & Sicara clients - I've asked hundreds of @quivr_brain users and analysed hundreds of thousands of discussions on https://quivr.app https://quivr.app"  
[X Link](https://x.com/_StanGirard/status/1724454234714726598)  2023-11-14T15:48Z [----] followers, [---] engagements


"@hwchase17 @LangChainAI @jerryjliu0 @llama_index @RealCharAI @agishaun @raoufdevrel @neondatabase @kiwicopple @supabase @quivr_brain If you want the full document let me know in the comments (don't forget to follow so I can send it). See you later and have fun building cool projects 🔥"  
[X Link](https://x.com/_StanGirard/status/1724454237684298135)  2023-11-14T15:48Z [----] followers, [---] engagements


"@teereximus @hwchase17 @LangChainAI @jerryjliu0 @llama_index @RealCharAI @agishaun @raoufdevrel @neondatabase @kiwicopple @supabase @quivr_brain Follow me so I can send you the message :)"  
[X Link](https://x.com/_StanGirard/status/1724482556786086347)  2023-11-14T17:40Z [----] followers, [--] engagements


"@tomviner @hwchase17 @LangChainAI @jerryjliu0 @llama_index @RealCharAI @agishaun @raoufdevrel @neondatabase @kiwicopple @supabase @quivr_brain Sent"  
[X Link](https://x.com/_StanGirard/status/1724482654051901715)  2023-11-14T17:41Z [----] followers, [--] engagements


"@JoelSprunger @hwchase17 @LangChainAI @jerryjliu0 @llama_index @RealCharAI @agishaun @raoufdevrel @neondatabase @kiwicopple @supabase @quivr_brain Sent"  
[X Link](https://x.com/_StanGirard/status/1724482690341101679)  2023-11-14T17:41Z [----] followers, [--] engagements


"Source code -"  
[X Link](https://x.com/_StanGirard/status/1724903236640161852)  2023-11-15T21:32Z [----] followers, [---] engagements


"What would be the best vector store for an open source project that needs to scale Thinking of ingesting 100gb of data in the short term. It needs to be self-hostable and have a hosted offering"  
[X Link](https://x.com/_StanGirard/status/1726347377538400328)  2023-11-19T21:11Z [----] followers, [----] engagements


"I just added a feature to @quivr_brain that allows you to easily generate images🧙🐈 How You connect a brain to @OpenAI DallE [--] API. It took me [--] seconds to add. And now I have image generation in Quivr Doc on how to do it yourself 👇"  
[X Link](https://x.com/_StanGirard/status/1728057836020568528)  2023-11-24T14:27Z [----] followers, [----] engagements


"@hwchase17 @LangChainAI @quivr_brain @traviscline I need to talk to him @traviscline Lets meet :)"  
[X Link](https://x.com/_StanGirard/status/1730245290098033049)  2023-11-30T15:19Z [----] followers, [---] engagements


"@hwchase17 @LangChainAI @quivr_brain @traviscline Damn He is building Langchain for Golang Big fan of Go Therefore big fan of the man"  
[X Link](https://x.com/_StanGirard/status/1730245913577156667)  2023-11-30T15:22Z [----] followers, [---] engagements


"@classF2RE @quivr_brain @LangChainAI @supabase @Ollama_ai It is the best LLM out there. You can quickly iterate on it and then once you are happy implement your system to be llm agnostic. Way easier to iterate on the best llm"  
[X Link](https://x.com/_StanGirard/status/1731730118916132920)  2023-12-04T17:40Z [----] followers, [--] engagements


"Don't use @LangChainAI it is just a wrapper that adds complexity. Is a lie And here is why Two days ago I removed my custom code on @quivr_brain to embed files and used @LangChainAI. Guess what It made embedding 50/100 times faster and reduce my cloud cost by [--]. You know why Because I didn't know you could send hundreds of "document" at a time to openAI. I used to send one doc at a time. Well what @hwchase17 with @LangChainAI knew is that you could send multiple docs and let @OpenAI parallelise. It took me [--] months to realize that & I worked on OpenAI api daily. This is just one small example"  
[X Link](https://x.com/_StanGirard/status/1732437384615068108)  2023-12-06T16:30Z [----] followers, 32K engagements


"I dont agree because Running an embedding model is expensive. In my opinion the mostly available one and simplest to install is Llama [--] with Ollama. However you need a strong computer to run this model. Yes there are smaller and better one but for non-techie to easily install there aren't. The embedding size is [----] dimensions meaning it takes even more space in the vector store. Then you need to host the model on a server. Even thought Lama7B is small it needs a hefty server. OpenAI is pay as you go. It is [----] dimensions and is pretty cheap. It would be interesting only if you need to"  
[X Link](https://x.com/_StanGirard/status/1732445838700339420)  2023-12-06T17:04Z [----] followers, [----] engagements


"@AlexanderMoini @pelaseyed @LangChainAI @quivr_brain @30ms @100mS Any sources I can look into Looks promising"  
[X Link](https://x.com/_StanGirard/status/1732466426017919268)  2023-12-06T18:25Z [----] followers, [---] engagements


"@tomviner @quivr_brain @FastAPI @nextjs @supabase @OpenAI @AnthropicAI @Google @nomic_ai @LangChainAI @streamlit I am the DevOps 😅 Simply deployed that into a Fargate on AWS for the backend frontend on vercel and @supabase on their saas"  
[X Link](https://x.com/_StanGirard/status/1733894887781573105)  2023-12-10T17:02Z [----] followers, [--] engagements


"@MistralAI Embed is a viable alternative to @OpenAI Ada [---] 🔥 Once I have access to the API I'll make it available in @quivr_brain"  
[X Link](https://x.com/_StanGirard/status/1734491771466379461)  2023-12-12T08:33Z [----] followers, [---] engagements


"What a trip - 27k stars - 30k+ users - 15k+ local installation And I met awesome people @hwchase17 @kiwicopple @antonosika @ivanmartit @MatthewBerman just to name a few. Quivr is joining @ycombinator W24 The team @_StanGirard @BrianLaleye @_Zewed is ready to ship Stay tuned 👇 https://t.co/s0NdwlO5LO Quivr is joining @ycombinator W24 The team @_StanGirard @BrianLaleye @_Zewed is ready to ship Stay tuned 👇 https://t.co/s0NdwlO5LO"  
[X Link](https://x.com/_StanGirard/status/1749480755863151040)  2024-01-22T17:14Z [----] followers, [----] engagements


"@pelaseyed @superagent_ai Congrats my friend"  
[X Link](https://x.com/_StanGirard/status/1751517535768551541)  2024-01-28T08:08Z [----] followers, [--] engagements


"@OpenAI Opensource alternative 😜"  
[X Link](https://x.com/_StanGirard/status/1752392155933679742)  2024-01-30T18:03Z [----] followers, [----] engagements


"@nomic_ai @llama @MongoDB Thats amazing Congrats guys 🎊"  
[X Link](https://x.com/_StanGirard/status/1753456809132920973)  2024-02-02T16:34Z [----] followers, [--] engagements


"My current OSS go-to stack: - @supabase for db auth storage realtime - @LangChainAI for building my rag pipelines - @posthog for analytics - @FastAPI for the backend - @nextjs for the frontend - @resend for the emails - @LiteLLM for LLMs compatibility - @ollama & @MistralAI for OSS llm All of that allowed us to build a complete oss self hostable RAG framework @quivr_brain 🔥 Go opensource"  
[X Link](https://x.com/_StanGirard/status/1756411278472650874)  2024-02-10T20:14Z [----] followers, 140.1K engagements


"@mudler_it @supabase @LangChainAI @posthog @FastAPI @nextjs @resend @LiteLLM @ollama @LocalAI_API Tell me more 👀"  
[X Link](https://x.com/_StanGirard/status/1756467745494036698)  2024-02-10T23:58Z [----] followers, [----] engagements


"@albertobissacco @supabase @LangChainAI @posthog @FastAPI @nextjs @resend @LiteLLM @ollama Unfortunately not opensource - AWS"  
[X Link](https://x.com/_StanGirard/status/1756472888721547687)  2024-02-11T00:19Z [----] followers, [---] engagements


"@TechnologyPat @albertobissacco @supabase @LangChainAI @posthog @FastAPI @nextjs @resend @LiteLLM @ollama 30$ for everything And people can install it locally very easily @AntWilson I'll let you answer this one 😘"  
[X Link](https://x.com/_StanGirard/status/1756474470657872181)  2024-02-11T00:25Z [----] followers, [---] engagements


"Ease of use too my friend. One day of works cost way more than the price difference. I can use it to generate migrations easily takes care of auth lambda storage and all. I probably would have spend a couple of days ( and Im a DevOps) to build the same thing with less features. @supabase allowed me to focus on providing value quickly with the product"  
[X Link](https://x.com/_StanGirard/status/1756488315996631062)  2024-02-11T01:20Z [----] followers, [---] engagements


"@swapnil_harpale @supabase @LangChainAI @posthog @FastAPI @nextjs @resend @LiteLLM @ollama Im an AWS expert so no. Should I"  
[X Link](https://x.com/_StanGirard/status/1756584661453877643)  2024-02-11T07:43Z [----] followers, [---] engagements


"If you are interested please comment and connect with me so I can contact you 🔥 Limited to [--] companies"  
[X Link](https://x.com/_StanGirard/status/1765450013667426679)  2024-03-06T18:50Z [----] followers, [---] engagements


"@Christophepas @SliteHQ @agixid Ill make a slite integration in @quivr_brain 😍 anyone will be able to create a brain connected to their slite account ;)"  
[X Link](https://x.com/_StanGirard/status/1767211813614055852)  2024-03-11T15:31Z [----] followers, [--] engagements


"Introducing LLM Colosseum 🔥 Evaluate LLMs quality by having them fight in realtime in Street Fighter III Who is the best @OpenAI or @MistralAI Let them fight Open source code and ranking 👇"  
[X Link](https://x.com/_StanGirard/status/1772023888211571197)  2024-03-24T22:13Z [----] followers, 142.2K engagements


"@hassantsyed @OpenAI @MistralAI Yes and no. Larger llms can also answer with more and better moves"  
[X Link](https://x.com/_StanGirard/status/1772264694943994118)  2024-03-25T14:10Z [----] followers, [----] engagements


"@clefourrier @OpenAI @MistralAI Would love some help with that"  
[X Link](https://x.com/_StanGirard/status/1772264813852549327)  2024-03-25T14:10Z [----] followers, [---] engagements


"@paulml_fr @OpenAI @MistralAI A bit but better llms can also answer with better moves"  
[X Link](https://x.com/_StanGirard/status/1772265075849715975)  2024-03-25T14:11Z [----] followers, [---] engagements


"@AGItechgonewild @OpenAI @MistralAI It was so fun"  
[X Link](https://x.com/_StanGirard/status/1772367852886012020)  2024-03-25T20:59Z [----] followers, [---] engagements


"@gootecks @OpenAI @MistralAI We are currently implementing that so we can fight against them 😅"  
[X Link](https://x.com/_StanGirard/status/1772374205939458318)  2024-03-25T21:25Z [----] followers, [---] engagements


"What if you could chat with your files & APIs with Slack Let's build a slackbot that connects to @quivr_brain then🧠 Source code: https://github.com/QuivrHQ/slackbot https://github.com/QuivrHQ/slackbot"  
[X Link](https://x.com/_StanGirard/status/1782019360334266449)  2024-04-21T12:11Z [----] followers, [----] engagements


"I'm looking for a 1-click deploy solution to allow @quivr_brain users to deploy it easily What do you use"  
[X Link](https://x.com/_StanGirard/status/1782690698744975657)  2024-04-23T08:39Z [----] followers, [----] engagements


"@park_sacha_ @supabase @AntWilson I'd love to get down to 10ms. I think that for production environment getting less than 10ms for a call to a database is not ideal"  
[X Link](https://x.com/_StanGirard/status/1783432991450030539)  2024-04-25T09:48Z [----] followers, [--] engagements


"@park_sacha_ @supabase @AntWilson I'd hope that my backend in Paris on AWS would speak faster to the Supabase in Ireland on AWS"  
[X Link](https://x.com/_StanGirard/status/1783447789306839450)  2024-04-25T10:47Z [----] followers, [--] engagements


"@park_sacha_ @supabase @AntWilson @park_sacha_ I managed to get down to 8ms by connecting directly to the db using sqlalchemy. The issues seems to come from the fact that supabase postgrest implementation does a tls handshake every time there is a new query. The handshake takes a lot of time"  
[X Link](https://x.com/_StanGirard/status/1784894073913983486)  2024-04-29T10:34Z [----] followers, [--] engagements


"@yassineyassif @cohere Same Well I tried it a bit before. It almost cut down more than half our @OpenAI bill"  
[X Link](https://x.com/_StanGirard/status/1784904435656761538)  2024-04-29T11:15Z [----] followers, [---] engagements


"X is probably the best source of information on GenAI. Who should I follow"  
[X Link](https://x.com/_StanGirard/status/1786347323301175323)  2024-05-03T10:49Z [----] followers, [----] engagements


"Lets ask @grok what it thinks of the feud between @elonmusk & @ylecun I'm quite impressed with the results 🤣 Best drama explanation tool. https://x.com/i/grok/share/e3ZyCNVYrjcaCuM17EAPQyVkD https://x.com/i/grok/share/e3ZyCNVYrjcaCuM17EAPQyVkD"  
[X Link](https://x.com/_StanGirard/status/1795757925715063029)  2024-05-29T10:03Z [----] followers, [---] engagements


"Today I did some css Ill need a few days to recover"  
[X Link](https://x.com/_StanGirard/status/1795855772456284538)  2024-05-29T16:32Z [----] followers, [---] engagements


"@moraish_ raw css not even some tailwind"  
[X Link](https://x.com/_StanGirard/status/1795882852514402760)  2024-05-29T18:20Z [----] followers, [--] engagements


"Should you use LangGraph from @LangChainAI Devs will say no I can't customize it Here is why we use it at @quivr_brain 👇"  
[X Link](https://x.com/_StanGirard/status/1796162334747959371)  2024-05-30T12:50Z [----] followers, [----] engagements


"Tech giants ( Microsoft Google) are playing a tricky game. They are selling their RAG solution such as copilot telling C-level it will solve all their employes issues. It is basically a simple RAG that cant perform complex tasks such as multi document retrieval"  
[X Link](https://x.com/_StanGirard/status/1797201963605475751)  2024-06-02T09:41Z [----] followers, [---] engagements


"A new open-source way to efficiently parse PDFs for optimal LLM Ingestion Making RAG applications better by @quivr_brain 🔥 We used Unstructured under the hood powered by some algorithms and LLMs to clean the files and improve it. 🧵"  
[X Link](https://x.com/_StanGirard/status/1797600639649792323)  2024-06-03T12:06Z [----] followers, [---] engagements


"@quivr_brain For example we use OpenAI GPT4o for improving the tables that are extracted - you could use any model even local ones"  
[X Link](https://x.com/_StanGirard/status/1797600643416285520)  2024-06-03T12:06Z [----] followers, [---] engagements


"@OpenAI Good luck @perplexity_ai"  
[X Link](https://x.com/_StanGirard/status/1816536448449003586)  2024-07-25T18:10Z [----] followers, 26.6K engagements


"@kiwicopple @supabase Let's go We have so much to launch ;)"  
[X Link](https://x.com/_StanGirard/status/1856451647746256959)  2024-11-12T21:38Z [----] followers, [--] engagements


"Today is Quivr's launch Week Day [--] @quivr_brain is now SOC2 Compliant It was painful but it feels good now If you want to learn more on how to get SOC2 Compliant quickly 👇 https://www.quivr.com/blog/quivr-is-soc2-compliant https://www.quivr.com/blog/quivr-is-soc2-compliant"  
[X Link](https://x.com/_StanGirard/status/1863568838874587235)  2024-12-02T13:00Z [----] followers, [---] engagements


"We are launching a new open-source product Parse any file into markdown easily with Megaparse 🔥 How does it work TL;DR: It is an awesome open-source File parser 🤜 Please like us on product hunt if you find it useful Parsing documents particularly unstructured ones is a challenging task that requires addressing multiple obstacles to ensure accurate and efficient resultsan essential step for effective Retrieval-Augmented Generation (RAG) document ingestion. MegaParse our innovative open-source parsing framework is on a mission to simplify and enhance this process at the fastest pace possible."  
[X Link](https://x.com/_StanGirard/status/1863859467265212801)  2024-12-03T08:15Z [----] followers, [----] engagements


"Doing a Product Launch on Product Hunt is hard. Here is everything we did to get ready for our Megaparse Launch 👇 An open-source file parser"  
[X Link](https://x.com/_StanGirard/status/1863917445875962367)  2024-12-03T12:05Z [----] followers, [---] engagements


"Me getting ready for all the announcements for @quivr_brain mega launch week Day 3"  
[X Link](https://x.com/_StanGirard/status/1864010779743162542)  2024-12-03T18:16Z [----] followers, [---] engagements


"This is what a @ProductHunt launch does to your Github stars https://github.com/quivrhq/megaparse https://github.com/quivrhq/megaparse"  
[X Link](https://x.com/_StanGirard/status/1864222542640099584)  2024-12-04T08:17Z [----] followers, [---] engagements


"Today is Launch Week Day [--] and we are releasing our Knowledge Management System in @quivr_brain It means that our second brain can now connect natively to Google Drive Sharepoint Notion Dropbox. And you can explore it directly from Quivr Have fun - https://quivr.com https://quivr.com"  
[X Link](https://x.com/_StanGirard/status/1864237205910176192)  2024-12-04T09:16Z [----] followers, [---] engagements


"If you are building a SaaS this is the stack that you need and the one we use at @quivr_brain - Frontend: @nextjs & @vercel - Backend: @FastAPI - Database: @supabase - Authentication: @supabase - Emails: @resend - Analytics: @posthog - Error & Logging: @getsentry or @parseablehq - Infrastructure as Code: Terraform from @HashiCorp - Queue: @NATS - LLMs: @OpenAI on @Azure or @AnthropicAI on @AWSFrance or @GroqInc for OSS models - CI/CD: @github - Release Management: Release Please from Google - SOC [--] Compliance: @oneleet - LLM Analytics: @phospho_ai or Langsmith from @LangChainAI - File"  
[X Link](https://x.com/_StanGirard/status/1866157965863993467)  2024-12-09T16:28Z [----] followers, [----] engagements


"One @ProductHunt launch = [--] MP for Paid Upvotes"  
[X Link](https://x.com/_StanGirard/status/1866428911678087467)  2024-12-10T10:25Z [----] followers, [---] engagements


"Codex is worse than Devin. You dont have access to internet you cant leverage CI/CD to validate code and the interface is buggy as hell"  
[X Link](https://x.com/_StanGirard/status/1924184904104870338)  2025-05-18T19:26Z [----] followers, [----] engagements


"4 Continuously learn by feeding agent feedback back into your modelsaccuracy improves with every interaction"  
[X Link](https://x.com/_StanGirard/status/1932753443346850154)  2025-06-11T10:55Z [----] followers, [--] engagements


"If youre on Zendesk and ready to turn your hidden metadata into on-brand instant replies that scale with every product launch or Black Friday surge lets chat 💬👉 founders@quivr dot app"  
[X Link](https://x.com/_StanGirard/status/1932753454998680050)  2025-06-11T10:55Z [----] followers, [---] engagements


"Current vibe coding setup - Claude Code Netflix http://Kiro.dev http://Kiro.dev"  
[X Link](https://x.com/_StanGirard/status/1957546692061876657)  2025-08-18T20:54Z [----] followers, [---] engagements


"It's faster. It's simpler. Claude already knows how to use these tools. I kept a few MCP servers where no CLI alternative exists yet. Context7 for example. But that's the exception not the rule"  
[X Link](https://x.com/_StanGirard/status/2016488583969099876)  2026-01-28T12:28Z [----] followers, [--] engagements


"Thats why we pivoted to customer support. The data there is live and every message requires reasoning empathy and context"  
[X Link](https://x.com/_StanGirard/status/1976230784823607593)  2025-10-09T10:18Z [----] followers, [---] engagements


"Its the perfect playground for what comes after RAG retrieval reasoning and safety. RAG isnt dead but it needs to evolve"  
[X Link](https://x.com/_StanGirard/status/1976230796467060799)  2025-10-09T10:18Z [----] followers, [---] engagements


"vibe coding is now my religion. If you are not sincerely looking at which part of your project you can vibe code you'll be dead in a bit"  
[X Link](https://x.com/_StanGirard/status/2000881453039804781)  2025-12-16T10:51Z [----] followers, [---] engagements


"Claude agent sdk is insane. In an hour of vibe coding I was able to build something better than what I spent [--] year building at @quivr_brain"  
[X Link](https://x.com/_StanGirard/status/2001037718713778526)  2025-12-16T21:12Z [----] followers, [---] engagements


"@adishjain333 I don't only I try to trust Claude :D http://claude.md http://claude.md"  
[X Link](https://x.com/_StanGirard/status/2016492886485881043)  2026-01-28T12:45Z [----] followers, [--] engagements


"Im addicted to vibe coding So I built a PWA app that lets me control Claude code Codex Opencode directly from my browser or phone. Now Im vibecoding in the subway bed all day long on remote computers and my Mac. OSS project below 👇 https://github.com/QuivrHQ/247-claude-code-remote https://github.com/QuivrHQ/247-claude-code-remote"  
[X Link](https://x.com/_StanGirard/status/2015098050981613704)  2026-01-24T16:23Z [----] followers, [----] engagements


"Then I just wrote one line in my "Use CLI tools." psql instead of a Postgres MCP server. gh instead of a GitHub MCP server. curl instead of a search MCP server. agent-browser instead of Playwright MCP server. Done. No server running. No config. No protocol. http://CLAUDE.md http://CLAUDE.md http://CLAUDE.md http://CLAUDE.md"  
[X Link](https://x.com/_StanGirard/status/2016488572057207271)  2026-01-28T12:28Z [----] followers, [---] engagements


"I told my @openclaw to "find interesting AI news and summarize it". It's been [--] hours. It has now subscribed me to [--] newsletters created [--] cron jobs spawned [--] sub-agents and just asked me if it can "optimize my life". I'm scared to say no"  
[X Link](https://x.com/anyuser/status/2015796902512443645)  2026-01-26T14:40Z [----] followers, [---] engagements


"MCP makes sense when you have multiple agents sharing the same remote service. Real use case no debate. But on your laptop Running a server so your agent can query a database is insane. Just use psql. We overcomplicated this"  
[X Link](https://x.com/_StanGirard/status/2016488595742413304)  2026-01-28T12:28Z [----] followers, [---] engagements


"Are we overengineering AI agents or am I just lazy"  
[X Link](https://x.com/_StanGirard/status/2016488607536787964)  2026-01-28T12:28Z [----] followers, [---] engagements


"I love Claude Code. I pay $200/month for Max. But today I got this again 👇 I'm not alone. X is full of people with the same error right now. I get it. Scaling is hard. Demand is insane. Claude Code is genuinely good. But I'm paying premium prices for a service that tells me "come back later" multiple times a week. Anthropic I'm rooting for you. But this needs to get fixed. Either add capacity or stop selling subscriptions you can't serve. https://twitter.com/i/web/status/2016492126184333316 https://twitter.com/i/web/status/2016492126184333316"  
[X Link](https://x.com/anyuser/status/2016492126184333316)  2026-01-28T12:42Z [----] followers, [----] engagements

Limited data mode. Full metrics available with subscription: lunarcrush.com/pricing