# nicedreamzapp/claude-code-local

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.

Repository: https://github.com/nicedreamzapp/claude-code-local
Canonical: https://ross.abutalabs.com/products/claude-code-local
Homepage: https://www.youtube.com/@nicedreamzapps
Language: Python
License: MIT
License Family: permissive
Topics: abliterated, ai-privacy, airgap, ambient-computing, anthropic, apple-silicon, browser-agent, claude-code, gemma, llama, local-ai, local-llm, macos, mlx, mlx-lm, offline-ai, on-device-ai, private-ai, qwen, voice-ai
Last push: 2026-08-22T22:36:42+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 87, longevity 11
- inputs: {"age_days": 160, "days_push": 11, "days_rel": 11, "gap_med": 53.0, "n_releases_24m": 3}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3240, forks 619 (observed 2026-08-28T04:07:50.455479+00:00)

## What it is
An MLX-native server for Apple Silicon that exposes an Anthropic-API-compatible endpoint so Claude Code and similar agents can run entirely on-device with local models. It bundles a curated lineup of local LLMs (including multimodal and long-context options), plus voice mode, a browser agent, and MCP server support, with no cloud dependency.

## Use cases
- run claude code locally without an api key
- use ai coding agents offline on a mac
- keep code private under NDA with on-device llm
- serve an anthropic-compatible api from local models
- airgapped ai assistant for legal or healthcare work
- run local llm inference on apple silicon with mlx
- replace cloud claude usage limit with local models

## When to choose
- you need Claude Code or agent workflows fully offline and private on Apple Silicon
- you want an Anthropic-API-compatible local endpoint without code changes
- you handle sensitive data (NDA, legal, healthcare) that cannot leave the device

## When to avoid
- you need maximum model quality and cloud connectivity is acceptable
- you run on non-Apple hardware, since it is MLX/Apple Silicon specific
- you need a managed, scalable multi-user inference service

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, http-server, api-framework, agent-framework, mcp, chatbot, speech-recognition
- domain: large-language-models, artificial-intelligence, privacy, self-hosted, developer-tools
- platform: python, self-hosted, cli
- tags: anthropic-api-compatible, mlx, apple-silicon, on-device-ai, offline-ai, airgap, claude-code, local-llm, voice-mode, browser-agent, ai-agents, macos, gpu

## Member repositories
- nicedreamzapp/claude-code-local (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:50.455479+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:24:32.142337+00:00, confidence not recorded.
  - readme: https://github.com/nicedreamzapp/claude-code-local (fetched 2026-08-28T04:07:50.455479+00:00, sha 337327fc4fd7)
  - homepage: https://www.youtube.com/@nicedreamzapps (fetched 2026-08-29T09:37:17.663376+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.