Instrukt runs in a terminal and lets users build, test, and direct AI agents.
agent-qa
The agent-qa repository describes a self improving test agent for web and mobile software teams.

About agent-qa
agent-qa is a self-improving QA harness with memory for software teams testing web and mobile. It learns from past runs, adapts to UI changes, and stores tests, configs, hooks, memory and suite logic as version-controlled code. Setup uses npm with browser or mobile driver installs.
Pricing is not clearly stated.
Key features
- Write web and mobile tests in natural language
- Self-healing execution retries failed actions via alternate UI paths
- Builds execution memory from past runs for future runs
- Action cache reuses validated plans across runs
- Run Node, Bun, Python, or Bash hooks in Docker containers
- Bring your own LLM via compatible endpoints and subscriptions
agent-qa at a glance
- Website
- github.com/vostride/agent-qa
- Category
- AI & Machine Learning › AI Agents & Automation
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Details verified
- Oct 22, 2026 · Official source
- Open source
- Not stated
- Language
- English
- Good for
- Developers
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
agent-qa alternatives
Tools and sites you could use instead, ranked by how closely they match.
Actionbook helps an AI agent access sources located behind logins and paywalls.
Taxy uses GPT-4 in a browser extension to automate repetitive browser actions from user instructions.
Microagents provides self-improving AI agents for automated task execution.
The Ouroboros project describes a self-creating AI agent created in 2026.
Agent Teams AI coordinates agents that work on tasks, message each other, and review work through a kanban board.
Popular in AI Agents & Automation
Well-known listings from the same topic.
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












