
Selfship — your agent's failures become pull requests
Detects failures in AI agent applications and opens eval-backed pull requests for you to review and merge.
pranny · HN
Selfship.ai – Surface and fix isues with your agentic applications 24x7
The full gallery
Tech stack
7 projects

Detects failures in AI agent applications and opens eval-backed pull requests for you to review and merge.
pranny · HN
Selfship.ai – Surface and fix isues with your agentic applications 24x7

Secure GitHub pull requests with hardware authentication and OTP verification.
jallmann · HN
> want without a PR process that requires hardware authentication or proof of presence Just curious, what do you use for this? I built OTP Guard [1] a few years ago for exactly this problem, although I haven't seen any alternatives in the space. Does GitHub have something built-in now? The original framing was more "local malware compromising your GitHub account" ... it never occurred to me that the malware could be a LLM. I really should update the page. [1] https://otpguard.com

GitHub PR analytics for engineering teams. Measure pull request performance metrics, review latency, throughput, and reviewer load from GitHub PR metadata. Read-only GitHub App.
@ashajjar85 · X

Use an AI agent to automatically generate and execute test cases across browsers without manual QA.
@mlguy1234 · X

The simplest way to deploy, manage, and scale AI agents. Sleep/wake micro-VMs and flat plans that work out to $1 per agent per month. Push your code, get a live API endpoint.
mariagorskikh1 · HN
Maritime, a platform for running AI agents for $1 a month

Route requests to Claude, GPT, or GLM through one API key with free daily credits.
@Awais_209 · X
Claude Opus 4.8, GPT-5.5 & GLM-5.2 for free. Get $25/day in credits. No trial or waitlist. One API key works with Claude Code, Cline, Cursor, Roo & OpenAI-compatible tools. Try it: #FreeTier #ClaudeAPI #CodingTools @AgentRouter_0

AI agent that reviews code commits, identifies issues, and generates pull requests.
@hyraxai · X