https://www.muralichowdhary.com AI product engineer. Writing about cost-optimized LLM infrastructure, multi-provider routing, and shipping AI products end to end. Available for freelance and consulting. en-us https://www.muralichowdhary.com/blog/opencode-go-model-routing-guide OpenCode Go limits are dollar-denominated, not request-based. That changes everything about routing. Complete opencode.json + .omc/config.json setup to run 10 agents across 8 models for $10/month. Fri, 22 May 2026 18:30:00 GMT https://www.muralichowdhary.com/blog/opencode-go-model-routing-guide https://www.muralichowdhary.com/blog/nyasa-bot-detection-sdk CAPTCHA and fingerprinting were built for clumsy bots. In 2026, LLM agents fill forms with realistic typing cadence, patch out webdriver flags, and solve CAPTCHA for $0.50. Nyasa adds a third actor to the model: AuthorizedAgent. One SDK, 24 signals, six detection rules. Thu, 21 May 2026 18:30:00 GMT https://www.muralichowdhary.com/blog/nyasa-bot-detection-sdk https://www.muralichowdhary.com/blog/view-counter-nextjs-portfolio-free How to track blog post views in a Next.js portfolio without paying anything. AWS DynamoDB, two API routes, and a five-second delay so bounces do not count. Mon, 11 May 2026 18:30:00 GMT https://www.muralichowdhary.com/blog/view-counter-nextjs-portfolio-free https://www.muralichowdhary.com/blog/2025 The hardest year of my life. A startup failed. I ran out of map. And somehow, I came out the other side a little more real. Sun, 10 May 2026 18:30:00 GMT https://www.muralichowdhary.com/blog/2025 https://www.muralichowdhary.com/blog/sheetforge-google-sheets-backend-data-loss The Google Sheets API drops rows under concurrent writes. It's a documented bug and every wrapper (SheetDB, Sheety, SheetBest) inherits it. I ran the test against all of them. Fifty parallel writes, somewhere between 35 and 47 rows. Every run different. Here is the bug, why a lock doesn't fix it, and what I built instead. Tue, 21 Apr 2026 18:30:00 GMT https://www.muralichowdhary.com/blog/sheetforge-google-sheets-backend-data-loss https://www.muralichowdhary.com/blog/gemini-2-5-flash-37-tokens-debugging I set max_tokens=1000 on a Gemini 2.5 Flash call. Got back 37 tokens. No error, no warning. The real cause was reasoning tokens eating the output budget, a bug documented in 15+ open GitHub issues but missing from every tutorial. Here is the full debugging trail, the three-tier fix with tradeoffs, and a diagnostic script. Sun, 19 Apr 2026 18:30:00 GMT https://www.muralichowdhary.com/blog/gemini-2-5-flash-37-tokens-debugging https://www.muralichowdhary.com/blog/litellm-got-hacked-freellm-alternative The most popular LLM routing library got compromised in a supply chain attack. 95 million monthly downloads. Credential harvester, Kubernetes backdoor, persistent RCE. I built FreeLLM as a narrower, auditable alternative: 6 providers, 262 tests, one job. Mon, 13 Apr 2026 18:30:00 GMT https://www.muralichowdhary.com/blog/litellm-got-hacked-freellm-alternative https://www.muralichowdhary.com/blog/freellm-one-endpoint-five-providers Every LLM provider has a free tier. Combined, they give you ~80 requests per minute. FreeLLM routes your requests across Groq, Gemini, Mistral, Cerebras, and Ollama with automatic failover. One endpoint. Zero cost. Mon, 06 Apr 2026 18:30:00 GMT https://www.muralichowdhary.com/blog/freellm-one-endpoint-five-providers https://www.muralichowdhary.com/blog/how-i-validated-metis-before-writing-code 91% of Indian retail traders lose money. I surveyed 70+ traders and did deep interviews before writing a single line of code. Here is exactly how I validated Metis, what I cut, and the one interview quote that killed 4 features. Sun, 22 Mar 2026 18:30:00 GMT https://www.muralichowdhary.com/blog/how-i-validated-metis-before-writing-code https://medium.com/@muralisudireddy0/ai-rise-86ee02ae0eec?source=rss-1d007ba7ee2c------2 The Rise of AI: How Artificial Intelligence is Taking Over the WorldIn recent years, artificial intelligence (AI) has gone from being a niche field in comput... Wed, 05 Mar 2025 04:47:42 GMT https://medium.com/@muralisudireddy0/ai-rise-86ee02ae0eec?source=rss-1d007ba7ee2c------2