CEO of SashiDo.io | โค๏ธโ€๐Ÿ”ฅ about (๐Ÿค–๐Ÿง ) (โ˜๏ธ๐Ÿ’ป) (๐Ÿ‚) (๐Ÿช๐Ÿ„๐Ÿป) (๐Ÿฅ‹) (๐Ÿฅ™) (โ‚ฟ๐Ÿš€)

Joined January 2009
85 Photos and videos
Every vibe coder should probably install this GitHub project. If you use Claude Code, Codex, Cursor, Gemini, Copilot, etc. - ctx-wire feels like a no-brainer. The problem is simple: AI coding agents run tons of noisy commands: git, sed, tr, grep, cat, npm, go, cargo, etc. And then they happily dump all that output back into the context window. Result? Your session fills up faster. You burn more tokens. You compact more often. And the agent starts carrying around a lot of useless noise instead of useful context. ctx-wire sits between the agent and the command output. It runs the command, filters/compresses the noisy output, scrubs secrets, and gives the agent a much shorter, cleaner result, while keeping the full scrubbed log locally if something actually fails. Why I like it: - Less token waste - Cleaner agent context - Fewer forced compacts - Better signal-to-noise during long coding sessions - Open source, free, installs in a few lines This is one of those tiny infra/devtools things that feels boringโ€ฆ Until you realize it directly improves the way your AI coding agent thinks. Repo: github.com/pivanov/ctx-wire Install: ctx-wire.dev Cut the noise. Keep the context.
1
1
2
204
Every vibe coder should probably install this GitHub project. If you use Claude Code, Codex, Cursor, Gemini, Copilot, etc. - ctx-wire feels like a no-brainer. The problem is simple: AI coding agents run tons of noisy commands: git, sed, tr, grep, cat, npm, go, cargo, etc. And then they happily dump all that output back into the context window. Result? Your session fills up faster. You burn more tokens. You compact more often. And the agent starts carrying around a lot of useless noise instead of useful context. ctx-wire sits between the agent and the command output. It runs the command, filters/compresses the noisy output, scrubs secrets, and gives the agent a much shorter, cleaner result, while keeping the full scrubbed log locally if something actually fails. Why I like it: - Less token waste - Cleaner agent context - Fewer forced compacts - Better signal-to-noise during long coding sessions - Open source, free, installs in a few lines This is one of those tiny infra/devtools things that feels boringโ€ฆ Until you realize it directly improves the way your AI coding agent thinks. Repo: github.com/pivanov/ctx-wire Install: ctx-wire.dev/ Cut the noise. Keep the context. Well done @ivanovpavel
4
2
223
Marian Ignev ๐Ÿค™ retweeted
Apr 21
SpaceXAI and @cursor_ai are now working closely together to create the worldโ€™s best coding and knowledge work AI. The combination of Cursorโ€™s leading product and distribution to expert software engineers with SpaceXโ€™s million H100 equivalent Colossus training supercomputer will allow us to build the worldโ€™s most useful models. Cursor has also given SpaceX the right to acquire Cursor later this year for $60 billion or pay $10 billion for our work together.
2,343
4,890
38,209
20,963,321
Marian Ignev ๐Ÿค™ retweeted
๐Ÿ“Š How much does content production really cost in 2026? Our new research breaks down the full picture - from internal time investment to external spend - so teams can accurately budget, forecast ROI, & make smarter content decisions. See more โžก๏ธ contentship.io/research/contโ€ฆ
1
1
27
Marian Ignev ๐Ÿค™ retweeted
The weekend build is the prototype. Production is the other 47,000 lines. Auth edge cases. Schema rewrites. Backups. Realtime. Observability. That is where apps survive or die. Plan the rebuild phase. Read the breakdown ๐Ÿ‘‰ sashido.io/en/blog/creating-โ€ฆ
1
2
79
Marian Ignev ๐Ÿค™ retweeted
Most apps donโ€™t lose users because of value. They lose them in the first quiet hour. Fix onboarding with behavior triggers: One push. One action. Stop after activation. SashiDoโ€™s team breaks it down. Read the playbook ๐Ÿ‘‰ sashido.io/en/blog/applicatiโ€ฆ
1
1
38
Marian Ignev ๐Ÿค™ retweeted
๐Ÿš€ Real outcomes, not projections. Our customers see 3ร— organic click growth & 4.4ร— more search impressions in just 3 months, based on verified Google Search Console data. Average rankings improve too, with first signals in ~6 weeks ๐Ÿ“ˆ Learn more โžก๏ธ contentship.io/results
1
2
44
Push is a retention lever. Not a loudspeaker. If every team can send, users will mute. - Segment by intent. - Cap frequency globally. - Deep link to the exact moment. Thatโ€™s how push drives trust, not opt outs. Read the full playbook ๐Ÿ‘‰ sashido.io/en/blog/push-notiโ€ฆ
1
1
69
Vibe Coding is the future
Build fast, ship faster with #vibecode and SashiDo ๐Ÿง‘๐Ÿปโ€๐Ÿ’ป
1
38
Marian Ignev ๐Ÿค™ retweeted
Developers ๐Ÿ˜€ #meme #fun
1
1
2
47
Marian Ignev ๐Ÿค™ retweeted
After a month of abusing this internally, I realized itโ€™s worth sharing "split-tasks" โšก Parallel agents for independent tasks ๐Ÿง  Same prompt, less waiting ๐Ÿ”— skills.sh/pivanov/ai-skills/โ€ฆ
1
2
56
Marian Ignev ๐Ÿค™ retweeted
AI writing assistants donโ€™t fail on prompts. They fail when teams skip structure. The real edge is clear briefs, review loops, and human judgment at the end. AI supports decisions. It doesnโ€™t replace them. Read the playbook ๐Ÿ‘‰ contentship.io/blog/seo-writโ€ฆ
1
1
22
Marian Ignev ๐Ÿค™ retweeted
Most MVPs stall not on frontend speed, but on backend setup. Auth, CRUD, storage, realtime, jobs. Founders want time to learn, not run infra. In 2026, BaaS wins when speed beats purity. Read the breakdown ๐Ÿ‘‰ sashido.io/en/blog/startup-mโ€ฆ
1
2
34
Marian Ignev ๐Ÿค™ retweeted
React apps rarely break in the UI. They break when the backend does not fit the team or traffic. Read before you scale ๐Ÿ‘‰ sashido.io/en/blog/backend-fโ€ฆ
1
2
29
I asked @Claude Code to build me a @cursor_ai alternative. It built it in #Vim. Free. Open source. Runs over SSH. github.com/mignev/vimsor
1
81
๐ŸŽ‰๐ŸŽ‰๐ŸŽ‰
Contentship just got approved in the @framer marketplace! ๐ŸŽ‰ We welcome all the designers, developers, and content teams building beautiful sites with Framer. Let's build something amazing together! ๐Ÿ’™
1
25
Hello guys, Iโ€™m starting a new product. @contentshipio is about how content actually wins in 2026, not just by shipping more pages, but by proof, demand, and trust across Google and LLMs. If you care about SEO beyond hacks, follow along ๐Ÿ‘‡
Hello, guys, we are getting started! Follow us for SEO Hacks for Google and LLMs. SEO in 2026 is not about shipping more pages. It is about proof, branded demand, and CTR. Human experience beats generic AI every time. Read the playbook ๐Ÿ‘‰ contentship.io/blog/seo-optiโ€ฆ
1
13
Marian Ignev ๐Ÿค™ retweeted
Claude Code is powerful and risky. Agentic AI needs loops and guardrails. Plan. Change. Check. Revert. Read this ๐Ÿ‘‰ sashido.io/en/blog/ai-code-tโ€ฆ
1
1
2
63
Marian Ignev ๐Ÿค™ retweeted
Heroku alternatives are not about cheaper dynos. AI apps have bursty traffic, queues, streaming, and egress bills. Pick for runway and portability. Read before migrating ๐Ÿ‘‰ sashido.io/en/blog/heroku-alโ€ฆ
1
1
1
59