Sri Santh

just fucking do it...!🫡

@garrytan hey, also check this out: x.com/srisanth2004/s…

Just launched GBrain v0.8.0 If you have it installed, you can just ask your Claw/Hermes to upgrade to the latest GBrain and we'll automatically ask if you want to install your Voice WebRTC endpoint and Twilio number It's a true mega brain-trip to talk to your agent directly.

@rxhit05 Both

As a founder, where are you marketing??

@MicroLaunchHQ I am building this knowleadge graph: x.com/srisanth2004/s…

What are you building this weekend?

@GithubProjects x.com/srisanth2004/s…

What are you building this weekend?

See this is how my graph evoles over time instead of being flat like obsidian... Imagine in obsidian or any other tools... You will create a graph only once spending so much tokens on it. Instead, you can use this which will generate initial graph without LLM needed and evolves over the time based on the question you can to it... Imagine having a Librarian inside the DB who help to identify and arrange things in a optimized manner... Thats what stixDB has... github.com/Pr0fe5s0r/Stix…

@heyblake I am building self-evolving graph system for AI agents instead of flat graph and RAG systems... github.com/Pr0fe5s0r/Stix…

Drop your project URL Let’s drive some traffic

@steipete @FanaHOVA @AlexReibman @KernelLabs_ai when you have money, and doesnt know how to spend them...

@FanaHOVA @AlexReibman @KernelLabs_ai but why. it runs on a raspberry pi.

.@AlexReibman is building a claw colony at @KernelLabs_ai 🦞

@contextkingceo sure, will ping you in the DM...

@srisanth2004 Tried DM-ing. Chat this week?

ok, i got a idea to work on a agentic memory system... Accidentally, created a version of a $6.5 Million dollar idea and made it Open Source - lol😀 github.com/Pr0fe5s0r/Stix… i failed at competitor analysis... my budget is $20 claude subscription anyways 🚶

@AliAbdaal @karpathy hey i have made something similar check this as well: github.com/Pr0fe5s0r/Stix…

building out the llm second brain inspired by all the @karpathy shenanigans over the past few days

@Tech_girlll HTML

first time you wrote hello world - what language did you use?

@kritikakodes mo one willing to buy things...

Why is everything getting Open Source?😂

@beyoumf insta reels

without drugs and alcohol. what’s the best way to escape reality?

@draft_ofkritika data

can I ask a dumb question… if everyone uses AI… what makes someone better than others

@Dearme2_ ChatGPT🤪

at your lowest, who do you talk to?

@SakshiSugandhi x.com/srisanth2004/s… see this and it aligns with the quote perfectly

"AI makes everyone a developer" is true the same way "cameras makes everyone a photographer"

@1Umairshaikh x.com/srisanth2004/s…

What are you building this weekend? Drop your project URL Let’s drive some traffic

@mikefutia hey can you also check this? x.com/srisanth2004/s…

Self-improving Claude Code skills are f*cking ridiculous 🤯 One loop → 10 test runs, scored against an eval, prompt rewritten, retested, winner kept. All inside Claude Code. Perfect for DTC brands and agencies who have built Claude Code skills but the output is still a coin flip: great sometimes, completely unusable the rest. If you've been editing your skill prompts based on vibes, re-reading every single output, adjusting one line at a time, running it again, and hoping this version is finally the one that sticks... This loop eliminates the entire cycle: → You define 3-5 binary eval criteria for your skill → Claude runs the skill 10 times with varied inputs → A separate evaluator scores every output against your criteria → It identifies the most common failure patterns across all runs → Rewrites the skill prompt to fix exactly what's failing → Retests and keeps the winner → Repeats until the score plateaus No manual prompt tweaking. No reviewing every output by hand. No "it worked that one time but I can't reproduce it." What you get: → A skill prompt that's been pressure-tested across 50+ automated runs → A scored improvement log showing exactly what changed and why → Eval criteria you can reuse every time you update the skill → A method that works on any skill: hooks, briefs, ad copy, scripts, reports Same loop AI labs use to improve their own models, applied to your creative workflow. I put together a full playbook showing how to set up the eval, the exact Claude Code prompt for the improvement loop, and starter eval criteria for the 5 most common DTC creative skills. Want the playbook for free? > Like this post > Comment "SKILL" And I'll send it over (must be following so I can DM)

@shivi1026 Git: local and Github: cloud - that the main difference

Git and GitHub are not the same. What's the difference?