CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.
C-Rank Grade: A (Welcoming) - 62/100
External PR Merge Rate: 64%
Response Time: 3d
First Timer Success: 53%
cuga-project/cuga-agent has a recorded first-timer success rate of 52.6%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in cuga-project/cuga-agent respond to incoming external pull requests in approximately 64.1 hours on average. Keeping PRs focused on single tasks and ensuring tests pass helps maintainers review faster.
The C-Rank™ system evaluates GitHub projects on a 0–100 scale using real data: PR merge rates, review turnaround time, active maintainer presence, and first-time contributor success. A score of 61.8 places cuga-project/cuga-agent in the A tier.
The external contributor pull request merge rate for cuga-project/cuga-agent is 64.3%, based on public PR activity from non-core contributors.
cuga-project/cuga-agent currently has 53 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Balanced & professional review environment in cuga-project/cuga-agent. Maintains strict focus on technical quality and test standards.
Average Response Latency
Tracks hours until a maintainer leaves a review, comment, or PR response.
External Acceptance Rate
Percentage of community pull requests successfully merged into main.
First PR Conversion
Rate at which developers submitting their first repository PR succeed.
Show contributors that your repository actively reviews and merges external pull requests.
[](https://getmerged.abhishekco.de/cuga-project/cuga-agent?utm_source=github&utm_medium=badge)
Historical health & responsiveness evolution
External PR acceptance
First PR success rate
50% receive response in
90% receive response in
Maintainer review activity heatmap & prime window prediction
Calculating local time...
Calculating local time...
Detected: UTC
Maintainers are most responsive around 10:00 UTC (10:00 UTC in your timezone). Recommended submission window is Monday - Wednesday from 10:00 to 14:00 UTC (10:00 - 14:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~42 hours (80% approval). Large PRs (>500 lines) take ~308 hours (29% approval). Keep your diff compact for rapid review.
What happened Should break into multiple issues: Followed quickstart guide, noted multiple readmes across platforms (Issue 1), which is confusing. would recommend a quickstart CLI (Issue 2) to prevent having to debug and use other coding agents to get things running . How to reproduce uv lock uv sync (dies at cryptography with current toml file x86-64 changes) Environment macOS x86_64 Logs, screenshots, or config No response Checklist I searched existing issues and this doesn’t look like a duplicate
Time: ~1.5–2 h, including a one-time install · AI API key: not needed to build and check it; to see real answers, use an API key or free local Ollama Background in 30 seconds A CUGA app is a small website with an AI assistant inside. Each app in cuga-apps is one folder with four files: File What it is What you'll do main.py A small web server (FastAPI) that creates the AI agent, gives it tools, and passes on the user's questions Change the tool list, the instructions and the name ui.py The web page (HTML in a Python string) Change the title and the example buttons README.md How to run it Rewrite for your app requirements.txt Python packages Remove two lines The agent's tools are functions it can call, and they already exist on shared MCP servers (tool bundles). You don't write any tools. Most of the work is writing clear instructions (the "system prompt") that tell the agent how to use them. You'll copy the smallest existing app, webpage_summarizer, and change about
Time: ~1.5–2 h, including a one-time install · AI API key: not needed to build and check it; to see real answers, use an API key or free local Ollama Background in 30 seconds A CUGA app is a small website with an AI assistant inside. Each app in cuga-apps is one folder with four files: File What it is What you'll do main.py A small web server (FastAPI) that creates the AI agent, gives it tools, and passes on the user's questions Change the tool list, the instructions and the name ui.py The web page (HTML in a Python string) Change the title and the example buttons README.md How to run it Rewrite for your app requirements.txt Python packages Remove two lines The agent's tools are functions it can call, and they already exist on shared MCP servers (tool bundles). You don't write any tools. Most of the work is writing clear instructions (the "system prompt") that tell the agent how to use them. You'll copy the smallest existing app, webpage_summarizer, and change about
Time: ~1.5–2 h, including a one-time install · AI API key: not needed to build and check it; to see real answers, use an API key or free local Ollama Background in 30 seconds A CUGA app is a small website with an AI assistant inside. Each app in cuga-apps is one folder with four files: File What it is What you'll do main.py A small web server (FastAPI) that creates the AI agent, gives it tools, and passes on the user's questions Change the tool list, the instructions and the name ui.py The web page (HTML in a Python string) Change the title and the example buttons README.md How to run it Rewrite for your app requirements.txt Python packages Remove two lines The agent's tools are functions it can call, and they already exist on shared MCP servers (tool bundles). You don't write any tools. Most of the work is writing clear instructions (the "system prompt") that tell the agent how to use them. You'll copy the smallest existing app, webpage_summarizer, and change about
Time: ~1.5–2 h, including a one-time install · AI API key: not needed to build and check it; to see real answers, use an API key or free local Ollama Background in 30 seconds A CUGA app is a small website with an AI assistant inside. Each app in cuga-apps is one folder with four files: File What it is What you'll do main.py A small web server (FastAPI) that creates the AI agent, gives it tools, and passes on the user's questions Change the tool list, the instructions and the name ui.py The web page (HTML in a Python string) Change the title and the example buttons README.md How to run it Rewrite for your app requirements.txt Python packages Remove two lines The agent's tools are functions it can call, and they already exist on shared MCP servers (tool bundles). You don't write any tools. Most of the work is writing clear instructions (the "system prompt") that tell the agent how to use them. You'll copy the smallest existing app, webpage_summarizer, and change about
Rate what actually matters after opening a pull request here.
Rate your first-hand PR experience (review speed, maintainer responsiveness, and onboarding ease) to help other contributors.
When evaluating whether to contribute to cuga-project/cuga-agent, response velocity and maintainer engagement are crucial. GetMerged continuously tracks pull request trajectories, first-comment latency, and code review rounds to help developers avoid submitting pull requests to backlogged repositories.
Currently, maintainers of cuga-project/cuga-agent acknowledge new external contributions in approximately 2 days+. Out of all submitted pull requests from non-core authors in the last 180-day window, 64.3% were successfully merged into the primary branch.
cuga-project/cuga-agent has a recorded first-timer success rate of 52.6%. Repositories ranked Welcoming typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~2 days+. Keeping PRs scoped to single concerns and ensuring CI checks succeed will optimize review turnaround.
The C-Rank™ index scores repositories on a 0 to 100 scale using an objective formula: external PR merge rates, initial response speed, active maintainer count, and first-time contributor retention. A score of 61.8 places cuga-project/cuga-agent in the Welcoming tier.
The external pull request merge rate is 64.3%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, cuga-project/cuga-agent currently has 53 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for cuga-project/cuga-agent are automatically retrieved via the public GitHub API and recalculated daily. Insider pull requests submitted by repository owners or organization members are excluded from merge rate calculations to preserve objective external contributor statistics.