Metrician
Score 88 out of 100 — Strongmetrician.io
Metrician is a Chrome extension that displays AI usage limits, usage pace, and reset times for ChatGPT, Claude, Grok, OpenCode Go, and Ollama inside a customizable floating browser widget.
Monitoring & observability
Metrics, logs, traces, and alerting
qsa.sh — External security scan of your own IP, in your terminal
Score 86 out of 100 — Strongqsa.sh
A terminal-based service that performs an external port and vulnerability scan of the user's own public IP address using open-source tools (naabu, nmap, nuclei), offering a free live-streaming tier and paid async/deep scan tiers.
CodeBurn — See where your AI coding spend actually goes
Score 84 out of 100 — Strongcodeburn.app
CodeBurn is a free, open-source, local-first tool that tracks AI coding token usage and cost across dozens of developer tools. It breaks down spend by model, project, and task using session files already on the user's disk, with no data uploaded.
Fixvibe
Score 83 out of 100 — Strongfixvibe.app
Security scanner for AI-generated web apps, including DAST, BaaS misconfiguration checks, leaked-secret detection, and AI-ready remediation prompts.
Replay QA for Teams — Autonomous QA for teams who ship faster than they can verify
Score 83 out of 100 — Strongreplay.io
Replay QA autonomously explores every new build, reproduces the failures it finds, and sends your team evidence they can fix before users discover the bug.
Hopsworks
Score 81 out of 100 — Stronghopsworks.ai
Build, deploy, and scale production ML systems with Hopsworks. The Feature Store and MLOps platform for real-time AI.
Media Sharing — Let AI agents put screenshots and videos on pull requests
Score 80 out of 100 — Strongargos-ci.com
Visual and snapshot testing platform that reviews pull request changes across pixels, Markdown, JSON, and other files to catch regressions before merge.
Coarena by Coasty — The arena where agents battle on real-world work
Score 80 out of 100 — Strongcoarena.ai
Platform for live computer-use agent evaluations where users post browser tasks, watch two AI agents race, and judge outputs blind to update a public leaderboard.
localskills.sh — AI Skill & MCP server management for teams & enterprises
Score 79 out of 100 — Stronglocalskills.sh
Create, share, and install reusable AI agent skills and rules across multiple coding tools, with team management, SSO/SCIM, and audit capabilities.
Xirp — The agentic development environment built by Spotify
Score 78 out of 100 — Strongspotify.com
Xirp is an agentic development environment that indexes services, documentation, and architectural decisions to provide institutional context for AI coding sessions.
Progress AI Observability — Trace, evaluate, and improve AI agents in production
Score 75 out of 100 — Strongtelerik.com
The Progress Agent Engineering Platform captures trace-level data from AI agents and LLM applications, including prompts, responses, model calls, retrieval steps, tool use, latency, token usage, and cost signals. It enables teams to debug failures, monitor production costs, evaluate output quality, and optimize workflows across .NET, Python, and JavaScript.
TraceLLM — OpenTelemetry for production AI applications
Score 72 out of 100 — Fairtracellm.in
TraceLLM connects prompts, retrieval, tool calls, model spans, token usage, errors, and exports into one inspectable workflow for production AI applications.
Show HN: GlassBox – what the browser reveals, and how identifiable you are
Score 72 out of 100 — Faircodecanary.org
Client-side browser fingerprinting diagnostic tool that runs live measurements in the browser and displays collected signals for identifiability assessment.
Gauge — Agent Led Growth: Get written into every customer's codebase
Score 70 out of 100 — Fairwithgauge.com
AI visibility platform that tracks brand mentions across LLMs (ChatGPT, Gemini, Perplexity), analyzes citation gaps, and generates/publishes content to improve AI search presence. Also offers Agent Led Growth to track how coding agents select tools.
Clears — Move beyond AI coding to agentic software delivery
Score 68 out of 100 — Fairclears.ai
Clears is an agentic execution platform that autonomously executes software delivery from requirements to reviewed pull requests, coordinating engineering workflows across the SDLC.
HookLens — Real-time webhook triage & AI root-cause analysis
Score 66 out of 100 — Fairusehooklens.com
HookLens intercepts failed webhooks across Stripe, PayPal, WooCommerce, Shopify, GitHub and custom APIs, diagnoses the root cause in seconds with AI, and notifies your team directly in Slack & Discord.
Decawork — Control your company's internal AI agents and tools
Score 51 out of 100 — Below the bardecawork.ai
Decawork gives IT one place to approve internal agents built in any tool, control what they can access and do, and see every action.