Bisla

Local coding agents can't do end-to-end work at your company. @proliferateai is the open-source platform for company-specific agents that can. Provision secure access to your tools, set up automations, and let agents work in the background. Congrats on the launch, @thepablohansen! ycombinator.com/launches/PVw-p…

@ycombinator @proliferateai Wow. Agents that run in cloud sandboxes, access your internal tools, trigger on Sentry alerts and cron jobs, and your team can watch and steer it live? And it's open source? This is solid. Congrats on the launch @thepablohansen🚀

@taranjeetio @mem0ai Congrats @taranjeetio @deshrajdry, super excited and proud of what you guys are building.

Memory is what makes us human. It's also what makes AI truly intelligent. @mem0ai has raised $24M to build the universal memory layer for AI. Thousands of teams in production. 14M downloads. 41K GitHub stars. Intelligence needs memory & we're building it for everyone. More👇

@mem0ai nice

🚀 We’re trending on GitHub (Python) again! mem0: State-of-the-art memory for AI agents - now beating OpenAI Memory by 26% in accuracy Big thanks to our amazing community!💚

@jspujji GrowthAssistant

A 21 y/o marketer is generating 1M+ social impressions for me. He’s using a fine-tuned AI to turn my daily meetings into viral posts. I asked him to make me a 5 min Loom to show how he does it. RT + Comment "GrowthAssistant" to get the video in your DMs.

@nurijanian @threadreaderapp unroll

Engineers-turned-PMs keep making the same fatal mistake in stakeholder meetings: They think logic will save them. After mentoring a few folks, I've noticed a pattern no one talks about:

@shreyshahi @mayankag @shreyshahi interesting, what are you guys cooking? 🤔

Interesting thing @mayankag and I observed today. If O1 ever starts answering "A succinct way to see..." you are screwed, the model always hallucinates after this.

@shreyas Product Sense course on Maven: eye-opening, no fluff. Shows new ways to think about products. Highly recommend.

@virattt super cool @virattt, curious why do you think Haiku performed better than Sonnet?

Which LLMs to use for my AI hedge fund? I ran some evals using FinanceBench: • 100 questions • 4 LLMs • LangSmith for evals Main metric was answer correctness. Surprisingly, Haiku 3.5 was best with 87% of questions answered correctly. GPT-4o was a close second with 85%. Let me know which models to test next.

@blader Can’t say or do anything to make things better. Wish and pray a speedy recovery. Big hug to you and family. ❤️

pain is learning your 4 year old has a brain tumor in the morning. and watching her 10 year old sister play with her, trying so hard to hold back her tears so she doesn’t scare her little sister. all you can do is turn around and scream silently into your fist until it bleeds.

@samraaj This is a game-changer, Samraaj! simplifies the process. Congrats!

What if frontend and design was as easy as writing a tweet? Enter ion. Describe a component, get react code that’s tailor-made to your use case ⚡ ion understands your codebase and design system, so everything meshes instantly. Just describe, integrate, and ship 🚢

@virattt Incredible work! You're onto something big here. Keep going - this could be huge!

I added evals to our Warren Buffett financial agent. LangSmith made evaluations extremely easy to set up. Implementation steps: 1 • create question + answer dataset 2 • use correctness as eval metric 3 • query the agent 4 • visualize evaluations in LangSmith I started with 15 questions and already see growth areas for the agent. All thanks to evaluations. Quick growth areas: • improve agent system prompt • improve tool descriptions • use better LLMs

@taranjeetio @mem0ai Impressive! The graph feature is incredibly powerful. Thrilled to see you implementing this. Looking forward to exploring its capabilities. 👏🏽

Open sourcing Dynamic Graph Memory by @mem0ai. Memory is fundamental to human reasoning, shaping how we approach tasks and make decisions. At Mem0, we believe that AI agents & apps should reflect this principle. Our Dynamic Graph Memory emulates human memory, advancing AI agents toward more intelligent, human-like reasoning. This is a significant step forward in building AI that truly understands and interacts with the world like we do. All credit to @khant_dev @deshrajdry @pckraftwerk for their countless nights spent on bringing this to life. Link: git.new/mem0

@virattt Great stuff. Curious about your choice for Django. Can you elaborate ?

I always do things that don’t scale. Example: a data ingestion job that keeps my stock market API updated. I manually run this job every evening. Daily time cost: ~60 minutes As a solo builder, this is now a drag: • 7 hours per week • 30 hours per month • 365 hours per year So I automated the ingestion to run every night while I sleep 😴 Daily time cost: 0 minutes. I had skipped the automation in the past to focus on top priority features. Now those are implemented: • fundamentals data • sec filings • stripe billing, etc. So I’m tackling tasks that free up my time. The diagram shows my architecture. s/o to @paulg for the inspiration.

@ankurnagpal Wow, that's very generous of you! Thanks for making it free, excited to learn some new strategies!

Want to learn how high earners pay less in taxes? I recorded a 3-hour course breaking down 25 different strategies We sold the course for $299 last year, but have made it free for the next 24 hours only RT or comment 💰 and I'll DM you a link

@joindimension Nice! Can't wait to try it out. Seamless action without switching sounds like a game-changer. 🚀

Action Bar The fastest way to action from anywhere - without context-switching. Coming soon. Get early access at dimension.dev.

@theneelpopat @theneelpopat You're a rare breed of a founder. Your recent update confirms my initial impression. Thank you for prioritizing your customers. Many talk about customer empathy; you're walking the walk. 🙇

1/ Hey all 👋 I’m *super* thrilled to announce that every Donut user will receive 100% of their funds back from Genesis. We’ve been testing withdrawals over the past days and will gradually increase the pace soon. So, how did we get here?

@virattt @_buildspace Impressive work! Setting goals and achieving them is the real deal. Keep pushing it forward, and your API sounds like a game-changer! 🚀

I built a stock market API in 42 days. All during @_buildspace s5. What is the API? Today, it lets you pull financials for 16,000 tickers going back 30+ years. Why did I build the API? Because the big providers have: • poor API design • poor documentation • expensive sales contracts • strict data retention policies How did I build it? I started building the API from scratch at the start of s5 in early June. I got deep into the SEC Edgar API and cracked how to scrape at scale. Sonnet 3.5 from @AnthropicAI was a godsend for this. I hacked early mornings, late nights, and weekends, with a full-time job. Day by day. Code by code. I set weekly goals and hit each one. End result: financialdatasets.ai I’m excited to see where this API goes. It may go nowhere, but I’ll always know that I can set goals and crush them.

@taranjeetio @mem0ai Congrats! 🚀

❤️ @mem0ai trending #1 on GitHub worldwide. 🙏🏻 thanks everyone. 🚀 more features coming soon.

@virattt Congrats Virat!

It's going live. My stock market API now has coverage for all S&P 500 tickers. • income statements • balance sheets • cash flow statements 30+ years of data. No API limits. You can connect your AI financial agents to this data. This open beta will run for ~1 week. Main goal is to load test the system prior to a full launch. Full launch includes coverage for 15,000+ stocks. Three things: • create an account 🙏 • send API requests 💻 • come hang in the discord ❤️ cc @_buildspace @FarzaTV