AI Rank
中文
← Open Source
vostride

agent-qa

Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.

AI EngineeringGive agent toolsBuild agent workflow (SDK)TypeScript
Open on GitHub
Momentum
+1stars in 24 hours+0.1%
907
Stars
20
Forks
+4
This week
3
Contributors
Created 2026-05-07 · Updated 2026-10-16 · #6057 today
Top developers
trad024pranshuchittora

vostride/agent-qa is ranked 6,057 with 907 stars.

Same-category comparison

vostride/agent-qa is ranked 6,057 among these 8 peers; jeremychone/rust-genai is ranked 6,056.

Same-category comparison
NameRankMetrics
anthropics/buffa6,045
Language:
Rust
Stars:
915
Forks:
112
Description:
Rust implementation of protobuf with editions support, JSON serialization, and zero-copy views.
LibreChat-AI/rag-api6,047
Language:
Python
Stars:
914
Forks:
409
Description:
ID-based RAG FastAPI: Integration with Langchain and PostgreSQL/pgvector.
alikon-art/DeterminFlow6,048
Language:
Python
Stars:
913
Forks:
139
Description:
A production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services.
jeremychone/rust-genai6,056
Language:
Rust
Stars:
908
Forks:
191
jasonjmcghee/WebMCP6,059
Language:
JavaScript
Stars:
905
Forks:
56
Description:
Early WebMCP proposal / implementation - since evolved and worked on by much more capable folks that develop the web: https://github.com/webmachinelearning/webmcp.
janwilmake/openapi-mcp-server6,061
Language:
TypeScript
Stars:
904
Forks:
95
Description:
Allow AI to wade through complex OpenAPIs using Simple Language.
phuryn/pm-brain6,064
Language:
Python
Stars:
902
Forks:
178
Description:
PM Brain OS: The Second Brain for Product Managers, Made of Markdown.
Jakedismo/codegraph-rust6,067
Language:
Rust
Stars:
898
Forks:
96
Description:
100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced agentic code analysis tools through MCP for efficient code agent context management.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguageTypeScript
CategoryAI Engineering
SubcategoryGive agent tools, Build agent workflow (SDK)
KeywordsAgent-ready APIs, Automated testing, MCP, Memory management
Stars907
Forks20
Contributors3
Created date2026-05-07
Updated date2026-10-16
Stars in 1 day1
Stars in 7 days4
Rank6,057
Previous rank3,268
Rank change-2,789
7-day stars rank6,293
Previous 7-day stars rank6,298
7-day stars rank change5
Total stars rank11,996
Previous total stars rank11,988
Total stars rank change-8
README summary

agent-qa The self-improving Agentic QA harness with Memory Write tests in natural language for web and mobile. agent-qa learns from past runs, adapts to UI changes, and catches regressions before you ship. Docs | Quickstart Features **Write tests in natural language for web and mobile**: Define actions and assertions in human language while agents work from visible roles, labels, and screen state. **Self-healing test execution**: When any sub-action, such as click, fill, or select, fails, agent

-qa re-observes the UI and tries a different path in the same run. Tests recover from UI drift and flaky interactions instead of failing on the first broken action. **Self-improves with Memory**: With every test run, agent-qa builds execution memory from product, suite, and test observations, then adds that context to future runs. agent-qa also curates memory from steps that were healed during execution, helping future runs avoid the same mistake. **Built for humans and machines

**: A polished dashboard and CLI for developers, plus MCP and skills for coding agents. **Accelerate runs with smart Cache**: The action cache reuses validated plans across similar subsequent test runs, reducing planner work, token usage, and runtime overhead. **Run sandboxed hooks during tests**: Run Node, Bun, Python, or Bash hooks in isolated Docker containers to set up environments, call APIs, seed fixtures, tear down state, or pass structured outputs back into the active test run. **Open source, reviewable QA**: The

harness is open source, and tests, configs, hooks, memory, and suite logic all live as version-controlled code, so every change can be diffed, reviewed, reused, and shared across teams. **Bring your own LLM**: Run tests with the model of your choice via OpenAI- and Anthropic-compatible endpoints, Gemini, local or open-source models, and subscriptions like Codex and Claude Code. Quickstart Install the package: For Codex or Claude Code subscription auth, also install: Install Docker before using hooks. agent

-qa runs hooks in a sandboxed runtime, and Docker is required for the Node, Bun, Python, and Bash hook containers. Initialize agent-qa and install the runtime support you need: Start the dashboard, complete auth, and run tests from the UI: For the full setup flow, use the quickstart. CLI Run tests from the CLI: Docs Full docs Quickstart CLI reference Dashboard Configuration License Notice

Frequently asked questions

How many stars and forks are recorded?

vostride/agent-qa has 907 stars and 20 forks.

What is the repository rank?

vostride/agent-qa is ranked 6,057.

What language and category are recorded?

vostride/agent-qa has 907 stars, uses TypeScript and belongs to AI Engineering.

Which repository is closest in rank?

vostride/agent-qa is compared with jeremychone/rust-genai, ranked 6,056 with 908 stars.

README

[Docs](https://vostride.com/docs/agent-qa)
·
[Demo](https://github.com/vostride/agent-qa/tree/main/demo-project)
·
[Issues](https://github.com/vostride/agent-qa/issues)

agent-qa

The self-improving Agentic QA harness with Memory

Write tests in natural language for web and mobile. agent-qa learns from past runs, adapts to UI changes, and catches regressions before you ship.

Docs | Quickstart

Features

  • Write tests in natural language for web and mobile: Define actions and assertions in human language while agents work from visible roles, labels, and screen state.
  • Self-healing test execution: When any sub-action, such as click, fill, or select, fails, agent-qa re-observes the UI and tries a different path in the same run. Tests recover from UI drift and flaky interactions instead of failing on the first broken action.
  • Self-improves with Memory: With every test run, agent-qa builds execution memory from product, suite, and test observations, then adds that context to future runs. agent-qa also curates memory from steps that were healed during execution, helping future runs avoid the same mistake.
  • Built for humans and machines: A polished dashboard and CLI for developers, plus MCP and skills for coding agents.
  • Accelerate runs with smart Cache: The action cache reuses validated plans across similar subsequent test runs, reducing planner work, token usage, and runtime overhead.
  • Run sandboxed hooks during tests: Run Node, Bun, Python, or Bash hooks in isolated Docker containers to set up environments, call APIs, seed fixtures, tear down state, or pass structured outputs back into the active test run.
  • Open source, reviewable QA: The harness is open source, and tests, configs, hooks, memory, and suite logic all live as version-controlled code, so every change can be diffed, reviewed, reused, and shared across teams.
  • Bring your own LLM: Run tests with the model of your choice via OpenAI- and Anthropic-compatible endpoints, Gemini, local or open-source models, and subscriptions like Codex and Claude Code.

Quickstart

Install the package:

npm install -D agent-qa

For Codex or Claude Code subscription auth, also install:

npm install -D @vostride/agent-qa-subscription-auth

Install Docker before using hooks. agent-qa runs hooks in a sandboxed runtime, and Docker is required for the Node, Bun, Python, and Bash hook containers.

Initialize agent-qa and install the runtime support you need:

npx agent-qa init
npx agent-qa install-browsers --chromium
# Mobile projects:
npx agent-qa install-mobile-drivers --all

Start the dashboard, complete auth, and run tests from the UI:

npx agent-qa dashboard --open

For the full setup flow, use the quickstart.

CLI

Run tests from the CLI:

npx agent-qa run tests/hacker-news-top-story.yaml

Docs

Nearby in the ranking
Similar items