Kshitij Mishra | AI & Tech

Job hunting Github repos I spent a few hours trying open-source tools that actually make the process faster instead of sending hundreds of random applications. These are the ones I'd keep using: • JobSpy github.com/Bunsly/JobSpy Collects jobs from LinkedIn, Indeed, Glassdoor, ZipRecruiter, and other sites into one place without duplicate listings. • Resume Matcher github.com/srbhr/Resume-M… Checks your resume against a job description, points out missing keywords, and shows how well it fits ATS filters. • Claude Cowork – Job Seeker Plugin github.com/anthropics/kno… A Claude plugin designed to help with resumes, applications, and the overall job search process. • Career-Ops github.com/santifer/caree… An AI-powered workflow for discovering jobs, ranking opportunities, tailoring resumes, and keeping applications organized. • Remote In Tech github.com/remoteintech/r… A regularly updated list of companies that genuinely support remote engineering and tech roles. Open source has quietly become one of the best career coaches on the internet.

@liquidated0x nice

@DAIEvolutionHub bro agency-agents is decent but for real shipping i built forge for this exact use case — forgee.xyzforgee.xyz

10 GitHub repositories worth checking out this week. 🔥 These are some of the fastest-growing and most talked-about open-source projects right now. 1. agency-agents — production-ready AI agents → github.com/msitarzewski/a… 2. Strix — AI-powered penetration testing → github.com/usestrix/strix 3. Caveman — reduce AI token usage by 15–95% → github.com/JuliusBrussee/… 4. OpenWiki — AI-generated documentation for your codebase → github.com/langchain-ai/o… 5. OfficeCLI — Office automation built for AI agents → github.com/iOfficeAI/Offi… 6. agent-skills — production-grade skills for AI coding agents → github.com/addyosmani/age… 7. awesome-design-md — DESIGN.md examples for AI-generated UIs → github.com/VoltAgent/awes… 8. Meetily — local AI meeting assistant → github.com/Zackriya-Solut… 9. OmniRoute — one API for 230+ AI providers → github.com/diegosouzapw/O… 10. OpenHands — one of the best open-source AI coding agents → github.com/All-Hands-AI/O… Save this post.

@david_marco45 good

@DAIEvolutionHub Need

Most AI startups build another app. mbag.ai built around something 4.5B+ people already use: Email. Your AI agent can: • Complete signups • Read documentation • Execute tasks • Reply through email Feels obvious after you see it. Website: mbag.ai/mbag/

@VuAnh20091987 yup

@DAIEvolutionHub Building on top of Outlook and standard email instead of forcing another app on 4.5B+ people is a neat move. If an AI agent can read documentations and reply directly from there, it’d save a ton of workload

@GeniusPothead yeah

@DAIEvolutionHub This solves real problems where people already spend most of their day.

MY TOP FIVE GITHUB REPOSITORIES ANDREJ-KARPATHY-SKILLS: github.com/multica-ai/and… HERMES-AGENT: github.com/NousResearch/h… CLAUDE-MEM: github.com/thedotmack/cla… EVOLVER: github.com/EvoMap/evolver GENERIC AGENT: github.com/lsdefine/Gener…

@LinkedInHelp @a_sad1226 Get my account back

@a_sad1226 Hello, thank you for contacting us. I'm sorry to hear about the inconvenience you are facing with the restriction of your LinkedIn account. Could you please send your full name and email address associated with your profile via Direct Message so that I can assist you further?-VIK

Hi @LinkedIn @LinkedInHelp @LinkedInNews I have lost my account access and i think someone hack my account. Please help me to gain my access back. I have attached the mail which i received when i lost my account access. My mail id is asad07aug@gmail.com

@LinkedInHelp @SusantaNandy1 Get my account back

@SusantaNandy1 Hello and thanks for replying, I regret the inconvenience caused to you. We have already replied you in DM regarding your issue, please check it there. Thanks!-SY

@RodmanAi Persistent memory is the feature I've been waiting for.

Every AI agent you've tried has amnesia. It does one task, forgets everything, and tomorrow you start from zero. That's not an employee. That's a temp you have to retrain every single morning. Hyperagent by Airtable is the first platform I've used that actually fixes this. Here's what got me: 1. Agents that compound. Each agent has memory. The one running today is smarter than the one you shipped three weeks ago. Same prompt, same integrations, but weeks of your judgment baked in. 2. Real deliverables, real receipts. You don't get a chat transcript. You get finished work with the cost and runtime printed right on it. A full research report for under ten bucks. Try getting that invoice from an agency. 3. A fleet, not a chatbot. Build a specialist for outreach, another for research, another for reporting. Give each one its own tools, its own memory, and its own budget cap so nothing runs away with your credits. 4. Deploy to Slack and your whole team uses the agent you built. One competitive intel agent, @ mentioned by everyone. Airtable runs its own data team this way. 5. Each agent gets its own cloud machine with a real browser and code execution. It works while you sleep. No babysitting, no local setup, no laptop that has to stay open. I put it to work in the video below. Watch what it builds. The teams treating agents as durable assets instead of one-off prompts are going to lap everyone else. This is the first tool that actually treats them that way. #ad @hyperagentapp

upvote us on product hunt : producthunt.com/products/claud…

@Hiraweb3 yeah

@DAIEvolutionHub local ai just leveled up

A 744 billion parameter AI model just ran on a machine with 25GB of RAM. No graphics card. The project is called colibri. It works with GLM-5.2, a 744B parameter mixture-of-experts model where only about 40B parameters are used for each generated token. Instead of forcing hundreds of gigabytes into memory, colibri keeps a 9.9GB runtime loaded and fetches the required experts directly from an SSD whenever they're needed. That means: • Pure C implementation • No runtime dependencies • Works with 25GB RAM • No GPU required • The entire model stays local The performance isn't pretty. When an expert isn't already cached, the system may need to read up to 11GB from disk before producing the next token. In practice, that's around one token every 10–20 seconds. So this isn't competing with ChatGPT. It's proving something different. The long-held assumption that a giant model has to fit entirely in RAM before it can run isn't always true. That's the real breakthrough. 100% open source. github.com/JustVugg/colib…

Screenpipe is climbing GitHub's trending charts for Rust, and it's easy to see why. It continuously captures activity on your computer, turning it into searchable long-term memory for AI. Everything runs locally, so your data stays on your device. Already crossed 20K+ GitHub stars. Repo: github.com/screenpipe/scr…

@fast_crw this is goold

@DAIEvolutionHub oh where is crw? single 8mb binary crushing all of them pure rust power github.com/us/crw

I'm sharing 8 of the best GitHub repos for automatically extracting data from any website: 1. Firecrawl Pass it a URL and it automatically crawls the entire site, converting it into clean data ready for AI. Supports JavaScript-heavy pages. Over 140,000 stars. github.com/firecrawl/fire… 2. Crawl4AI Turns any website into text that LLMs can read directly. No API key or payments required. Created by a developer fed up with services charging $16. Over 70,000 stars. github.com/unclecode/craw… 3. browser-use An AI agent that uses the browser like a human: clicks, logins, forms, everything. Created by a startup from ETH Zurich. Over 100,000 stars. github.com/browser-use/br… 4. Crawlee A complete framework for scraping with proxy rotation, retries, anti-detection, and queue management. Avoids blocks like a pro. github.com/apify/crawlee 5. Scrapy The classic Python framework for large-scale scraping. It's been in use for over 10 years and stably processes millions of pages. Completely free. github.com/scrapy/scrapy 6. Scrapling Automatically adapts to website design changes and avoids block detections. Paid-level features… but free. github.com/d4vinci/Scrapl… 7. AutoScraper Just give it an example of the data you want, and it learns the pattern on its own. Extracts the rest without writing selectors. Super simple and powerful. github.com/alirezamika/au… 8. curl-impersonate Imitates real Chrome browser HTTP requests to bypass the most advanced anti-bot protections. github.com/lwthiker/curl-… Save them all, highly recommended. With these, you can pull clean data from almost any website without paying for expensive services or relying on limited APIs.

@AndrewBolis yup

@DAIEvolutionHub Great curation, saves so much time searching around randomly.

50 Super Practical GitHub Repositories 1. iFixAi — AI Alignment Testing → github.com/ifixai-ai/iFix… 2. public-apis — Free API Collection → github.com/public-apis/pu… 3. build-your-own-x — Learn by Doing → github.com/codecrafters-i… 4. developer-roadmap — Learn Any Skill → github.com/kamranahmedse/… 5. free-programming-books — Thousands of Free Books → github.com/EbookFoundatio… 6. system-design-primer — System Design Introduction → github.com/donnemartin/sy… 7. coding-interview-university — Coding Interview University → github.com/jwasham/coding… 8. the-art-of-command-line — The Art of the Command Line → github.com/jlevy/the-art-… 9. project-based-learning — Project-Based Learning → github.com/practical-tuto… 10. you-dont-know-js — JavaScript You Don't Know → github.com/getify/You-Don… 11. the-book-of-secret-knowledge — The Book of Secret Knowledge → github.com/trimstray/the-… 12. tech-interview-handbook — Tech Interview Handbook → github.com/yangshun/tech-… 13. awesome-selfhosted — Self-Hosted Apps Collection → github.com/awesome-selfho… 14. javascript-algorithms — JS Algorithms Collection → github.com/trekhleb/javas… 15. 30-seconds-of-code — 30-Second Code Snippets → github.com/Chalarangelo/3… 16. GitHub .gitignore Templates — Git Ignore Files → github.com/github/gitigno… 17. ollama — Run Large Models Locally → github.com/ollama/ollama 18. langchain — Large Model App Framework → github.com/langchain-ai/l… 19. n8n — Automation Tool → github.com/n8n-io/n8n 20. openclaw — Local AI Assistant → github.com/openclaw/openc… 21. dify — AI App Builder → github.com/langgenius/dify 22. langflow — Visual LLM Workflow → github.com/langflow-ai/la… 23. mem0 — AI Memory Layer → github.com/mem0ai/mem0 24. browser-use — Browser Automation → github.com/browser-use/br… 25. crewAI — Multi-Agent Framework → github.com/crewAIInc/crew… 26. MetaGPT — AI Product Manager → github.com/geekan/MetaGPT 27. AutoGen — Microsoft's Multi-Agent Framework → github.com/microsoft/auto… 28. aider — AI Coding Assistant → github.com/Aider-AI/aider 29. markitdown — Microsoft's Document Conversion Tool → github.com/microsoft/mark… 30. open-webui — Open-Source Web UI → github.com/open-webui/ope… 31. maigret — OSINT Intelligence Tool → github.com/soxoj/maigret 32. TradingAgents — Trading Agents → github.com/TauricResearch… 33. stagehand — Web Automation Library → github.com/browserbase/st… 34. firecrawl — Web Crawling Tool → github.com/mendableai/fir… 35. transformers — Hugging Face Models Library → github.com/huggingface/tr… 36. vLLM — Large Model Inference Acceleration → github.com/vllm-project/v… 37. llama.cpp — C++ Inference Engine → github.com/ggerganov/llam… 38. llama_index — RAG Framework → github.com/run-llama/llam… 39. nanoGPT — Karpathy's GPT Implementation → github.com/karpathy/nanoG… 40. RAGFlow — RAG Workflow Engine → github.com/infiniflow/rag… 41. supermemory — Super Memory Tool → github.com/supermemoryai/… 42. awesome-claude-skills — Claude Skills Collection → github.com/ComposioHQ/awe… 43. Bumblebee — Perplexity Security Tool → github.com/perplexityai/b… 44. ComfyUI — AI Painting Node Editor → github.com/comfyanonymous… 45. DeepSeek — Official Models Repository → github.com/deepseek-ai 46. Lobe Chat — Open-Source Chat App → github.com/lobehub/lobe-c… 47. freeCodeCamp — Free Programming Learning Platform → github.com/freeCodeCamp/f… 48. System Design + Interview Prep Collection → github.com/jwasham/coding… 49. AI Agent Ecosystem Collection → github.com/langchain-ai/l… 50. Automation + AI Workflow Collection → github.com/n8n-io/n8n Bookmark this list, don't forget. You'll come back here at least ten more times.

@dadadaistt yeah

@DAIEvolutionHub useful. a goldmine of ready to clone tools will probably saved me hours

This is probably the best free book to learn AI. Not a summary. Not a course. Not a YouTube playlist. The actual textbook written by one of the Godfathers of AI. Inside you'll learn: • Neural networks • Computer vision • How AI models remember • Why models overfit • Backpropagation • Optimization • The math behind deep learning Yoshua Bengio is one of the three researchers widely known as the Godfathers of AI. Long before ChatGPT existed, he spent decades pushing neural networks when most researchers believed they had no future. That work earned him the 2018 Turing Award, often called the Nobel Prize of computing. Together with Ian Goodfellow and Aaron Courville, he wrote *Deep Learning*. It's one of the most recommended AI books ever published. The crazy part? While the printed edition is sold as a regular book... The complete online version is available for free. Every chapter. Every figure. Every explanation. No signup. No subscription. No paywall. It starts with the basics like linear algebra and probability, then gradually builds all the way to modern deep learning. It's not an easy read. But if you want to truly understand how today's AI models work, this is one of the best resources you'll find. Read it free: deeplearningbook.org

@RodmanAi This is the direction AI agents should be heading.

I automate things for a living. I never automated my own inbox. Six weeks ago an AI employee took it over, and last Thursday he did something I never asked for. I'm an API automation developer and an AI implementation manager. I mentor other builders. What I do not have is staff. Everything on my list that stays unshipped stays unshipped because I ran out of hours, not because I ran out of ideas. Viktor lives in my Slack. Early on he only did what I told him to do. Triage the inbound, pull the research, draft the replies I never got around to. Thursday he went further. He noticed a collab thread that had gone quiet for nine days, pulled up what had actually been agreed in it, drafted the follow-up in my voice, and posted it in Slack for me to look at. I read it, changed one line, sent it. That thread is alive again. That is the whole difference. Every AI I have ever built with waits for a prompt. This one watches the work and turns up holding it. He proposes. I approve. I am the only approver there is, and that is exactly how I want it. Most AI tells you what to do. Viktor does the work. Tell me I'm wrong. Try free at viktor.com. $100 in credits, no card. @viktor__com