Production ready toolkit to run AI locally
C-Rank Grade: A (Welcoming) - 65/100
External PR Merge Rate: 67%
Response Time: -
First Timer Success: 45%
RunanywhereAI/runanywhere-sdks has a recorded first-timer success rate of 45.5%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in RunanywhereAI/runanywhere-sdks respond to incoming external pull requests in approximately 0.0 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 65.4 places RunanywhereAI/runanywhere-sdks in the A tier.
The external contributor pull request merge rate for RunanywhereAI/runanywhere-sdks is 67.5%, based on public PR activity from non-core contributors.
RunanywhereAI/runanywhere-sdks does not currently have active "good first issue" tags indexed, but accepts external contributions through standard GitHub issue tracking.
Highly welcoming maintainers in RunanywhereAI/runanywhere-sdks. 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/RunanywhereAI/runanywhere-sdks?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 00:00 UTC (00:00 UTC in your timezone). Recommended submission window is Wednesday - Friday from 22:00 to 02:00 UTC (22:00 - 02:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~16 hours (84% approval). Large PRs (>500 lines) take ~115 hours (30% approval). Keep your diff compact for rapid review.
Follow-up from #928 by @Sarah-Mahmoud-29 -- thanks again for that PR! What #928 corrected the LLM streaming callback docstring at core/include/rac/features/llm/rac_llm_component.h:199 from "Called for each generated token" to "Called for each UTF-8-safe text run generated by the model." The identical stale wording -- "Called for each generated token" -- is still in four sibling locations that go through the same rac::tokens::StreamFilter chunking path: core/include/rac/features/vlm/rac_vlm_component.h:177, core/include/rac/features/vlm/rac_vlm_types.h:409 (and :453), core/include/rac/features/llm/rac_llm_types.h:265, and the mirrored (real file, not a symlink) Swift-bindings copy bindings/swift/Sources/RunAnywhere/CRACommons/include/rac_vlm_component.h:166 (plus rac_vlm_types.h:373). Why it matters Callers implementing the VLM/LLM streaming callbacks read one doc that promises per-token delivery and another that promises per-run delivery for the same underlying chunking behavior across
Follow-up from #848 by @ayaangazali — thanks again for that PR! What core/include/rac/features/llm/rac_llm_component.h:199 still documents rac_llm_component_generate_stream's token_callback as "Called for each generated token" — the exact stale, one-token-per-call phrasing #848 just corrected on all four VLM streaming-callback declarations (core + Swift mirrors). The LLM decode loop already assembles UTF-8 internally (Utf8State), so this is a docs-only mismatch, not a live bug, but it leaves the public C ABI's own doc comment describing a contract the code doesn't follow. Why it matters Callers reasonably read the header doc as the contract. Leaving the LLM doc stale while VLM's was just fixed makes the split between the two confusing, and risks the same wrong "one call per token" assumption resurfacing in a future integration. Suggested approach Reword the doc comment the same way #848 reworded the VLM ones: describe delivery as UTF-8-safe text runs rather than one call per token.
Follow-up from #720 by @ayaangazali — thanks again for that PR! What RunAnywhere.models.refresh() (added in #720) forwards to refreshModelRegistry in bindings/react-native/packages/core/src/Public/Extensions/Models/RunAnywhere+ModelRegistry.ts. At lines 1063-1070 that helper awaits the throwing ensureServicesReady() inside the same try as native.refreshModelRegistry(...). If the guard rejects, the native call never runs, so neither the downloaded-model discovery pre-pass nor the registry refresh happens. The guard rejects when completeServicesInitialization rethrows (Public/RunAnywhere.ts:222) or when retryHTTPSetupInternal rethrows (Public/RunAnywhere.ts:631). Swift (RunAnywhere+ModelRegistry.swift:48-52, try? await ensureServicesReady()) and Kotlin (RunAnywhereModelRegistry.kt:143-151, catch and continue) still rescan in that case. Why it matters models.refresh() is the only React Native call that picks up model files changed on disk, and it is a local-only operation. When the netw
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 RunanywhereAI/runanywhere-sdks, 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 RunanywhereAI/runanywhere-sdks acknowledge new external contributions in approximately -. Out of all submitted pull requests from non-core authors in the last 180-day window, 67.5% were successfully merged into the primary branch.
RunanywhereAI/runanywhere-sdks has a recorded first-timer success rate of 45.5%. Repositories ranked Welcoming typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~-. 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 65.4 places RunanywhereAI/runanywhere-sdks in the Welcoming tier.
The external pull request merge rate is 67.5%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
RunanywhereAI/runanywhere-sdks does not have open beginner labels indexed currently, but external PRs for bugs and documentation improvements are evaluated via normal issue triage.
All metrics displayed for RunanywhereAI/runanywhere-sdks 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.