Next Generation Agentic Proxy for AI Agents and MCP servers
C-Rank Grade: A (Welcoming) - 67/100
External PR Merge Rate: 75%
Response Time: 19h
First Timer Success: 65%
agentgateway/agentgateway has a recorded first-timer success rate of 65.3%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in agentgateway/agentgateway respond to incoming external pull requests in approximately 19.1 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 67.3 places agentgateway/agentgateway in the A tier.
The external contributor pull request merge rate for agentgateway/agentgateway is 74.7%, based on public PR activity from non-core contributors.
agentgateway/agentgateway currently has 2 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Highly welcoming maintainers in agentgateway/agentgateway. Prompt code reviews with positive guidance for new contributors.
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/agentgateway/agentgateway?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 19:00 UTC (19:00 UTC in your timezone). Recommended submission window is Wednesday - Friday from 19:00 to 23:00 UTC (19:00 - 23:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~12 hours (93% approval). Large PRs (>500 lines) take ~92 hours (34% approval). Keep your diff compact for rapid review.
agentgateway should document how to export telemetry to each observability platform below. For every platform, add integration guides for both standalone and Kubernetes deployments. Each guide should cover prerequisites, configuration, and verification, and should be linked from the documentation navigation. A checkbox is complete when both deployment guides are merged. Arize AX Arize Phoenix Axiom Braintrust Coralogix Dash0 Datadog ClickStack CoreWeave Dynatrace Elastic Honeycomb HoneyHive Langfuse LangWatch Laminar LangSmith Last9 Lunary Middleware New Relic OpenLIT PromptLayer Pydantic Logfire SigNoz Splunk Traceloop Others? (comment down below)
Context #2533 and #2605 establish the extensible standalone agentgateway import command and the initial LiteLLM proxy adapter. The initial implementation intentionally focuses on common file-based model, provider, alias, deployment, weighted-routing, and ordinary-fallback configuration. This issue tracks the remaining migration capabilities. Each checkbox is intended to be independently deliverable through one or more focused PRs. Implementations should extend the source-neutral import plan and shared emitter when a capability can be reused by future source adapters, while keeping LiteLLM parsing isolated in its adapter. Follow-on work Add centralized credential support for LiteLLM credential_list and litellm_credential_name, emitting reusable agentgateway providers when possible. Add secret-manager reference handling and preserve supported environment-backed values without materializing secrets. Add wildcard model conversion, including model_name: "*" and provider wildcards such a
When using extAuth for external authentication/authorization, the OTEL context is not propagated to the external system. This would be useful for tracking the calls through all the layers that the requests is forwarded to. I have not tested with extProc, but I guess that the headers are not set there either.
Currently our AI guardrail policy is configured by inlining the provider-specific config under promptGuard. This leads to repeated configuration for response/request, and if reusing the same guardrail across multiple routes or backends : kind: AgentgatewayPolicy metadata: name: openai-prompt-guard namespace: agentgateway-system spec: targetRefs: - group: gateway.networking.k8s.io kind: HTTPRoute name: openai backend: ai: promptGuard: request: - bedrockGuardrails: identifier: <guardrail-ID> version: "<version>" region: <region>> policies: auth: aws: secretRef: name: aws-secret response: - bedrockGuardrails: identifier: <guardrail-ID> version: "<version>" region: <region>> policies: auth: aws: secretRef:
agw shows multiple listeners on the same port. This should be flagged/handled as a conflict. xref kgateway-dev/kgateway#13309
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 agentgateway/agentgateway, 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 agentgateway/agentgateway acknowledge new external contributions in approximately 19 hours. Out of all submitted pull requests from non-core authors in the last 180-day window, 74.7% were successfully merged into the primary branch.
agentgateway/agentgateway has a recorded first-timer success rate of 65.3%. Repositories ranked Welcoming typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~19 hours. 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 67.3 places agentgateway/agentgateway in the Welcoming tier.
The external pull request merge rate is 74.7%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, agentgateway/agentgateway currently has 2 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for agentgateway/agentgateway 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.