Developer Builds CheckForge, an Uptime Monitoring SaaS Using Fastify and Cloudflare

·1 views

A developer has built CheckForge, an uptime monitoring platform designed to track websites, APIs, and SSL certificates in real time. The platform was created over several months as a hands-on exercise in building a production-ready SaaS beyond typical portfolio projects. CheckForge uses Cloudflare Workers to execute health checks, Supabase to store results, and supports alerts via Email, Slack, Discord, and Webhooks. When a failure is detected, the system automatically creates an incident and dispatches notifications through the user's configured channels. The project is live at checkforge.in, with multi-location monitoring among the features planned for future development.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Developer Builds Fully Local AI Voice Assistant Using Hermes Agent and Kokoro TTS

A developer experimented over the weekend with combining Hermes Agent, an open-source AI framework by Nous Research, and Kokoro TTS to build a fully local, voice-enabled AI assistant. The setup processes user queries through a locally running large language model, converts responses into natural speech via Kokoro TTS, and can deliver output through Telegram as text, voice, or both. Because all inference and speech synthesis run on the user's own machine, no data is sent to external providers and there are no per-request API costs. The stack is compatible with popular local model servers such as Ollama, LM Studio, and llama.cpp through OpenAI-compatible endpoints. Key trade-offs include the need for adequate CPU or GPU hardware, large initial model downloads, and potentially slower response times compared to cloud-based alternatives.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Dev Team Builds AI Agent Observability Tool AXRAY Using SigNoz and OpenTelemetry

A development team building an autonomous AI coding agent called AXRAY found they had no visibility into why agent runs varied wildly between 8 and 45 seconds. To solve this, they integrated SigNoz as an observability backbone, using OpenTelemetry and official GenAI Semantic Conventions to instrument every agent action, from LLM calls to Docker command execution. Each agent turn is tagged by phase, allowing the team to separately measure time spent on LLM reasoning versus actual code execution in the sandbox. Analysis of real sessions revealed that roughly 78% of latency originated inside the LLM due to large context windows, not slow infrastructure. SigNoz's ClickHouse-backed trace storage also enabled custom SQL queries, giving the team granular, sub-turn latency breakdowns that standard dashboards could not provide.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Six Security Checks to Evaluate Before Trusting Any AI Agent Skill

AI agent skills, stored as reusable instruction files like SKILL.md, are growing in popularity for automating coding and deployment tasks across sessions. However, a well-formatted skill can still be unsafe, vague, or unverifiable, raising concerns for both third-party and internally written workflows. Experts recommend checking that a skill performs real discovery before acting, defines inspectable outputs as evidence of success, and sets explicit hard boundaries around destructive actions like deleting data or force-pushing to production. Strong skills also order operations by risk level, preferring reversible steps first, and must distinguish between local validation and live-target verification. A skill that cannot cleanly recover from a wrong hypothesis or fails to confirm changes on the actual production environment should not be trusted without revision.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Anthropic Launches Claude Opus 5 at Same Price as Predecessor with Major Upgrades

Anthropic released Claude Opus 5 on July 24, 2026, priced at $5 per million input tokens and $25 per million output tokens, matching its predecessor Opus 4.8 and undercutting rival Fable 5 by half. The model features a 1-million-token context window and 128K max output, and now enables extended thinking by default rather than requiring explicit activation. A key migration consideration is that developers must increase max_tokens to accommodate both the internal thinking and visible response output. Benchmark results from Anthropic show Opus 5 performing comparably or better than Fable 5 on several tests including OSWorld 2.0 and CursorBench 3.2, though it lags behind in exploit development tasks. The model is currently available only via the Claude API and is not accessible on Amazon Bedrock, Google Cloud, or Microsoft Foundry.

0 comments Read more at DEV Community