Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepSeek V4 Flash (1M ctx). Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.
C-Rank Grade: D (Risky) - 8/100
External PR Merge Rate: -
Response Time: -
First Timer Success: -
nicedreamzapp/claude-code-local has a recorded first-timer success rate of 0.0%. Repositories ranked D typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in nicedreamzapp/claude-code-local 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 7.5 places nicedreamzapp/claude-code-local in the D tier.
The external contributor pull request merge rate for nicedreamzapp/claude-code-local is 0.0%, based on public PR activity from non-core contributors.
nicedreamzapp/claude-code-local currently has 2 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepSeek V4 Flash (1M ctx). Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.
Active maintainer team in nicedreamzapp/claude-code-local welcoming community pull requests and bug fixes.
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/nicedreamzapp/claude-code-local?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 08:00 UTC (08:00 UTC in your timezone). Recommended submission window is Tuesday - Thursday from 06:00 to 10:00 UTC (06:00 - 10:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~16 hours (81% approval). Large PRs (>500 lines) take ~115 hours (29% approval). Keep your diff compact for rapid review.
local models write tool calls in a lot of different shapes, and every shape the parser has learned so far came from someone pasting what their model actually printed. scripts/test_parse_tool_calls.py runs without a model or a server, so this is a good first contribution. what to do run your model through claude-code-local and grab the raw text of one response that contains a tool call (the server log shows it) add it as a new check(...) case in scripts/test_parse_tool_calls.py with the calls you expect run python3 scripts/test_parse_tool_calls.py if it passes, great, it guards against regressions. if it fails, you've found a real bug; open the PR anyway and say which model produced it. you'll be named in the README and the credits table in docs/FULL-GUIDE.md. thanks!
i only own one Mac, a big one, so the 16 GB tier (Hermes 4 14B) is the part of this project i know least about. if you have a 16 GB MacBook Air or base Mac mini, a report from you would help a lot of people decide whether this is worth installing. how to test (about 15 minutes plus the download) bash setup.sh and let it pick the model for your RAM bash scripts/doctor.sh --bench open the launcher and give Claude Code one small real task, like "add a --verbose flag to this script" what to post back chip and RAM (e.g. M2 Air, 16 GB) and macOS version what doctor.sh --bench printed whether the task finished, roughly how long it took, and anything that went wrong (swap, the fan, tool calls that got garbled) older chips (M1, M2) and 8 GB machines are just as welcome, even if the answer is "it doesn't fit". thank you, this is exactly the kind of thing i can't find out on my own.
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 nicedreamzapp/claude-code-local, 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 nicedreamzapp/claude-code-local acknowledge new external contributions in approximately -. Out of all submitted pull requests from non-core authors in the last 180-day window, 0.0% were successfully merged into the primary branch.
nicedreamzapp/claude-code-local has a recorded first-timer success rate of 0.0%. Repositories ranked Risky 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 7.5 places nicedreamzapp/claude-code-local in the Risky tier.
The external pull request merge rate is 0.0%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, nicedreamzapp/claude-code-local 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 nicedreamzapp/claude-code-local 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.