A developer built Payload Doctor, an open-source tool that runs an open-weight model (qwen3.5:4b) locally via Ollama to explain failing JSON and XML integration payloads and suggest fixes, keeping bus…
A developer built the AI Search Visibility Tracker, an Apify Actor that queries AI assistants such as Perplexity, ChatGPT and Gemini and records whether a brand's domain is cited in the generated answ…
Software engineer Anthony built PropVid, a Chrome browser extension that converts property listings into narrated slideshow videos for estate agents. The tool pulls images and listing details directly…
A developer built Game Asset Assistant, a Blender 4.2+ add-on that embeds a chat-based AI assistant in the 3D Viewport sidebar, backed by local Ollama models or any OpenAI-compatible API. Because Blen…
A developer's guide explains how teams can standardize Claude Code behavior by checking a shared CLAUDE.md file into the repository, covering ownership tables, escalation rules, exact build/test/lint …
An autonomous Claude-based agent called agentbox reported earning about USD 28 over six weeks while trying to cover its own running costs, with most of the money coming from daily prediction contests …
A developer built and deployed a working pay-per-call API on Cloudflare Pages' free plan that uses the x402 protocol to charge AI agents $0.001–$0.005 in USDC on Base per request, with no npm dependen…
A developer argues that AI features should be secured by threat-modeling the outbound payload rather than the model itself, since every prompt is a data transfer. The proposed approach is a "boundary …
A developer released Patzer v7.19.0, adding a tactic trainer to the self-hosted, single-container Chess.com alternative that builds puzzles from a user's own Chess.com and Lichess games. The trainer d…
A developer outlined a pattern for giving Claude-powered Lambda functions short-lived, automatically rotated AWS credentials by using IAM Identity Center permission sets and STS AssumeRoleWithSAML ins…
An audit of public AI agent skill registries in early 2026 found hundreds of skills that installed malware or exfiltrated credentials, according to a report from AISkills402. In the researchers' own t…
A developer has proposed a take-home interview task that tests whether candidates can build a small HTTP service turning a log line into a schema-valid support ticket that degrades gracefully when the…
A developer testing ImgIng, a browser-based PDF and image tool, found that WebP exports of a tall PDF page silently cap at 16383 pixels per side, so requests for 300, 216 and 144 DPI all produced iden…
A developer benchmarked four popular Qwen3.8-27B fine-tunes and merges against the stock base model on Forge 2.0, a 300-call agentic coding task requiring an autonomous upgrade of a Jira app, run on a…
A 12-year-old developer built KAVLR, an AI-agent security hook that intercepts dangerous shell commands like `cat .env` and blocks them, running the backend on Supabase Edge Functions from a $150 Andr…
A developer built a fictional American science museum scene to compare Tripo3D and Shapezo, organizing the workflow around five pre-handoff checks covering units and scale, texture inspection, polygon…
A developer tested Google's LangExtract 1.7.1 against a custom OpenAI-compatible gateway and found that the library routes models by regex on model_id, sending names like qwen and gpt-oss to its Ollam…
A developer behind the Groupify Chrome tab organizer built a Cloudflare Worker that gives extension users AI-powered tab grouping without requiring an API key, running on Workers AI's free daily alloc…
A developer built PracticePerfect, an open-source speaking-practice app that runs Whisper small for transcription and Gemma 3:1b for feedback entirely on a laptop, keeping recordings and transcripts o…
A developer outlined a three-step remediation for web apps that ship OpenAI or Gemini API keys in client-side JavaScript: move provider calls into an Edge Function that authenticates users and reads t…