fastCRW

fastCRW just crossed 100 ⭐ on GitHub 📷 Open-source lightest, fastest, Rust engine for web scrape, crawl, search & map. Thank you to everyone who starred it — we're just getting started. github.com/us/crw #opensource #webscraping

@TheTriceRozay hey from the lightest fastest search crawler for your agents GitHub.com/us/crw

Need 5 million impressions? Just say, "Hey." Thank me later. 🚀

@ExaAILabs oh great for you but you can easily integrate LLM with crw too and much more customizable prompts search result and free check GitHub.com/us/crw

We raised $250M in Series C funding at a $2.2B valuation, led by a16z. Exa is a search lab organizing the web's data for agents.

@geekbb what about not tracking the tavily quota anymore? You can easily replace tavily with GitHub.com/us/crw

macOS 菜单栏小工具，把各家 API 服务的用量配额集中展示，通过插件接入智谱、MiniMax、DeepSeek、Tavily、Codex 等平台 github.com/marsmay/UsageB…

@usxperiments @Mnilax so true, welcome to fastcrw.com

@Mnilax instead tavily and firecrawl you can try open source complete free alternative, faster, better, lighter only 6mb binary github.com/us/crw

10,000$ saved in 3 months: claude + MCP + free tier. the stack: > Tavily replaced $99/mo search API > Firecrawl replaced $200/mo scraping service > GitHub MCP no more context-switching > Context7 killed hallucinated docs forever > Sentry - errors explained, no dev needed 5 servers. ~3k tokens overhead. $0/month. was paying for 6 different tools before. now it's all one claude chat. don't wait.

On fastCRW the cost forecast is multiplication, not a lottery. 100,000 pages = 100,000 credits = $69/mo. No JS multiplier, no stealth tax, no separate extract bill. fastcrw.com/pricing #webscraping #AIagents

Firecrawl users forked it because the anti-bot engine stays closed-source — self-host degrades over time. fastCRW self-host is the full engine, full parity, AGPL-3.0. No coercion. github.com/us/crw #opensource #selfhosted #opensource #selfhosted

@ron_mizrahio Fair hit. Lightpanda is the bet, fast, ~10x lighter than CDP, evolving weekly. Auto-mode's chrome fallback is a safety net, not the destination.

@fast_crw It wants to use the cdp under load instead of panda.

Same 100k credits. fastCRW Standard: $69 launch ($99 list). Firecrawl Standard: $99 list — before the separate extract bill. We undercut tier for tier. Launch pricing ends 2026-06-01: fastcrw.com/pricing #webscraping #AIagents

@ron_mizrahio I just confused cuz didn't understand what you mean exactly :D did you mean a good thing or bad, if its bad I wanna hear the problem that you got

@fast_crw It’s crw.

@ron_mizrahio Hey Ron 👋 which one's giving you trouble? If it's CRW self-host, DM me the specs, I'll help dial it in. If it's another scraper, also happy to compare notes.

@fast_crw The scraper is crushing unfelt minimal load in self hosting 😢

@nanobot_project @atomic_chat_hq local search + scrape github.com/us/crw @nanobot_project are you open for collab?

Local agents, local models, local control. Excited to collaborate with @atomic_chat_hq to make local-first agent workflows easier to try! The nanobot’s docs now include a clearer Atomic Chat setup path, so builders can run nanobot with local models on their own machine.

@cursor_ai crw is now on cursor :p ``` { "mcpServers": { "crw": { "command": "npx", "args": ["crw-mcp"] } } } ```

Cursor is now available in Jira. Assign Cursor to work items, or mention @​Cursor in a comment to kick off a cloud agent. Cursor uses the title, description, comments, and your team's repository settings to create a merge-ready PR.

Tavily's Research endpoint can burn up to 250 credits in a single request, agents blow through hundreds before you notice. fastCRW search is flat: ~1 credit/query. fastcrw.com/pricing #AIagents #search #tavily #fastcrw

@ManusAI lets collaborate, we can handle web for your agents, like search, scrape, browse and more with lightest fastest way with single 6mb rust binary <3

Introducing Scheduled Tasks 2.0 — a major upgrade to recurring work in Manus. Scheduling is no longer just about running something at the right time. It is about running it in the right place, with the right context. Now scheduled work can continue in the same task, power background actions in Manus-built web apps, and give you clearer visibility into upcoming and past runs. Available now to all users.

@cognition what you are using for agents to web search and scrape ? do you want work together? fastcrw.com fastest, lightest single 6mb binary, opencore <3 github.com/us/crw

Introducing Devin Auto-Triage: Your AI first-responder with long-term memory. Devin can monitor incoming bugs, alerts, and incidents, investigate them, and come back with context, next steps, or a PR.

@GoogleAIStudio github.com/us/crw 0.9.1 release

What are you vibe coding this weekend?

@sharbel you forgot us crw github.com/us/crw faster, lighter, open source tavily/firecrawl alternative

The 10 fastest growing GitHub repos this week: 1. CloakBrowser (+9.1K stars) Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed. github.com/CloakHQ/CloakB… 2. AiToEarn (+4.8K stars) Let's use AI to Earn! github.com/yikart/AiToEarn 3. agentmemory (+6.9K stars) #1 Persistent memory for AI coding agents based on real-world benchmarks github.com/rohitg00/agent… 4. UI-TARS-desktop (+3.5K stars) The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra github.com/bytedance/UI-T… 5. 9router (+5.4K stars) Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits. github.com/decolua/9router 6. DeepSeek-TUI (+8.7K stars) Coding agent for DeepSeek models that runs in your terminal github.com/Hmbown/DeepSee… 7. AI-Trader (+3.0K stars) "AI-Trader: 100% Fully-Automated Agent-Native Trading" github.com/HKUDS/AI-Trader 8. skills (+18.3K stars) Skills for Real Engineers. Straight from my .claude directory. github.com/mattpocock/ski… 9. supersplat (+2.6K stars) 3D Gaussian Splat Editor github.com/playcanvas/sup… 10. hysteria (+952 stars) Hysteria is a powerful, lightning fast and censorship resistant proxy. github.com/apernet/hyster… The theme this week: free AI routing hacks and persistent agent memory are the real obsession right now. Bookmark this. Next week's list will look completely different.

@rambuilds_ @karpathy @fchollet @ylecun did you forgot @fast_crw ?

15 AI related accounts you should follow on Twitter: 1. @karpathy His tweets already create LLMs narratives that you later see on linkedin in 2 months. 2. @fchollet posts thoughtful research on intelligence, benchmarks, and AI limitations. Keras creator + ARC-AGI 3. @ylecun Yann LeCun is Deep learning pioneer & Meta Chief AI Scientist; big-picture research takes and critiques (and drama). 4. @AndrewYNg Andrew Ng is AI education legend; practical ML advice, courses, and real-world implementation. creator of deeplearning ai 5 @rasbt Sebastian Raschka posts on Practical ML/LLM implementations, "build from scratch" tutorials, and books. 6. @dair_ai Weekly ML/AI paper threads and accessible research explainers (high-signal for staying current). 7. @lilianweng Lilian Weng is ex-OpenAI and her Lil'Log-style threads are good. has In-depth LLM research breakdowns 8. @jeremyphoward posts interesting takes on AI/crypto news, and works on democratizing practical deep learning and accessible education. 9. @simonw Simon post Practical LLM tools, takes, experiments, prompting, and engineering breakdowns. django co-founder 10. @_akhaliq Curates the latest arXiv papers, model releases, and open-source AI drops. 11. @ID_AA_Carmack AGI/low-level optimization takes that makes you think about the problem. 12. @gwern Really high-quality long-form AI research notes and essays. 13. @goodside LLM evaluation, prompting research, and real capabilities testing 14 @drfeifei Computer vision pioneer; human-centered AI and spatial intelligence research 15 @demishassabis Been following his work for 9 years. Demmis is my hope against google usurpating their power with AI. Demmis is google DeepMind's CEO Let me know who I missed guys and save it for future

@LeiferMendez %99 dont know exist, replace tavily and firecrawl with complete open source alternative github.com/us/crw faster, better, lighter only 6mb binary

MCPs que el 90% de devs no sabe que existen: → context7 (docs en contexto) → tavily (busqueda web) → supabase (DB desde el agente) → github (repos, PRs, issues) → filesystem (archivos) → playwright (testing e2e) → slack (notificaciones) cual usas?