This release is a pre-release and may not be stable for production use.
Agentic coding. Local models. On your Mac.
Install
uv tool install localcode # or: pip install -U localcode
Upgrade with uv tool upgrade localcode (uv pip install -U does not upgrade a uv tool install; with pip, rerun pip install -U localcode).
Run
cd your-project
localcode
To use the running model from another local app, open /server or run localcode api for its
OpenAI compatible endpoint. See the Local API guide.
What it does
- Reads and edits files in your project
- Runs your tests, builds, Git and shell commands inside the project on its own, and asks before touching anything outside it
- Searches code by name, content or structure
- Scaffolds and launches apps, then checks that they respond
- Remembers the task across messages
Requirements
- Mac with Apple Silicon, macOS 13 or newer
- 16 GB unified memory or more
- Python 3.10 or newer
- Disk space for LocalCode and your chosen model (download sizes below)
Models
Choose from 12 models and 150+ quant options for coding, image input and typed decisions. Models download from Hugging Face. Downloads run in parallel and can resume if interrupted. Switch with /models. LocalCode recommends the most capable one that fits your Mac's memory and marks it with a star. Flint, Saluki, OpenJev, DiffusionGemma, Kolibri and DeepSeek V4 Flash are never picked automatically. DeepSeek V4 Flash runs on 128 GB Macs only. The Flint row shows its two curated quants; the picker lists every Unsloth quant.
Speed: Gemma 4, Qwen 3.6, Muse Glimmer and Qwen 3.8 draft tokens with the vendor's own speculative drafter, which downloads with the model. The model server's GPU kernels ship precompiled, so the first start after an install is quicker.
| Model | Smallest download | Largest download |
|---|---|---|
| Gemma 4 12B | 4.2 GB | 23.8 GB |
| Qwen 3.8 27B | 6.2 GB | 31.5 GB |
| Underdog Saluki 27B 1.0 | 7.9 GB | 7.9 GB |
| North-Mini-Code 30B-A3B | 9.4 GB | 33.2 GB |
| Gemma 4 26B-A4B | 9.9 GB | 27.6 GB |
| Qwen 3.6 35B-A3B | 10.0 GB | 38.5 GB |
| Muse Glimmer 30B | 10.7 GB | 32.3 GB |
| Flint 40B-A2.5B | 11.4 GB | 42.3 GB |
| DiffusionGemma 26B-A4B | 16.8 GB | 50.5 GB |
| OpenJev 27B (decisions) | 19.4 GB | 53.8 GB |
| Kolibri 1 78B-A3B | 28.6 GB | 47.5 GB |
| DeepSeek V4 Flash 284B-A13B | 82.4 GB | 161.9 GB |
Network
Inference is local. Three features use the network: model downloads, the web_search and web_fetch tools, and any MCP servers you add. See Network Boundary for the full list.
Why local?
Powerful, personal AI should work for everyone, on any device, anywhere. That means running it locally. localcode is a first step.
Sponsors
To sponsor localcode, reach out.
Installation diagnostics: localcode doctor. See compatibility tests and local hardware verification.
Contributing
See CONTRIBUTING.md.
License
Apache 2.0. See LICENSE.
1 maintainer
Metadata
1 maintainer
Release files for localcode 0.5.42rc2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| localcode-0.5.42rc2.tar.gz | 67.5 MB | With provenance | Details for localcode-0.5.42rc2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| localcode-0.5.42rc2-py3-none-macosx_13_0_arm64.whl | Python 3 | none | macOS 13.0+ ARM64 | Details for localcode-0.5.42rc2-py3-none-macosx_13_0_arm64.whl |
Total release size: 129.1 MB
Release files / localcode-0.5.42rc2.tar.gz
| Download URL | localcode-0.5.42rc2.tar.gz |
|---|---|
| Size | 67.5 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b8bac2040aaea94754deea4e349b7c7ac8c7b5d96aad47c9288123398d354c06
|
|
BLAKE2b-256 checksum How to use checksums |
ef783bdf85f17647d73f657126ec1296d08d52fa780e686e2d9cf6d24af9beca
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 2, 2026.
Transparency logRelease files / localcode-0.5.42rc2-py3-none-macosx_13_0_arm64.whl
| Download URL | localcode-0.5.42rc2-py3-none-macosx_13_0_arm64.whl |
|---|---|
| Size | 61.6 MB |
| Tags | Python 3 macOS 13.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
07be99ca005d416eaab799b053be4fdc0ef47580502d9d6a3a481ce02a30b54d
|
|
BLAKE2b-256 checksum How to use checksums |
310d5eeefbcd84009c19d74624828288ed906393c997e7a9a88e4c2892cc213d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 2, 2026.
Transparency logSecurity for localcode 0.5.42rc2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for localcode-0.5.42rc2.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 2, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
