animica-serve
Serve Animica AICF inference jobs from anything with a CPU — phones under Termux included. Torch-free and dependency-free: llama.cpp does the inference, this package does the earning. Each job you win credits its full estimated cost in ANM to your wallet address on the network's worker ledger.
The zero-install browser version of this worker lives at
https://pool.animica.org/serve — this package is the terminal lane: it
survives reboots in a tmux/sv session, doesn't need the screen on, and
uses llama.cpp's native ARM speed.
Termux (Android)
pkg install python llama-cpp # llama.cpp built for your phone's CPU
pip install animica-serve
animica-serve --address anim1yourwallet
The default model (Qwen 2.5 1.5B Instruct, Q4_K_M, ~1.1 GB) downloads once and
is cached; use --model qwen2.5-0.5b on older/low-RAM phones. Add
--charge-only to pause while unplugged (needs the Termux:API app +
pkg install termux-api). Keep Termux alive in the background with
termux-wake-lock.
Anywhere else
Any Linux/macOS box works the same way. If you already run a llama-server or Ollama, skip the model download and point at it:
animica-serve --address anim1… --openai-url http://127.0.0.1:11434/v1 --openai-model qwen2.5:1.5b
No llama-server binary? pip install 'animica-serve[python-backend]' uses
llama-cpp-python in-process.
How earning works
Your worker registers your address (no keys ever leave your device), claims
jobs from the shared AICF queue on rpc.animica.org, answers locally, and
submits. Jobs are raced across several workers — the first good answer
wins and is credited (animica-serve earnings --address anim1… shows your
ledger). Losing races to faster desktop GPUs is normal; you win whenever you
are the fastest or only worker awake.
Metadata
Release files for animica-serve 0.1.7
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 |
|---|---|---|---|---|
| animica_serve-0.1.7.tar.gz | 13.1 kB | Without provenance | Details for animica_serve-0.1.7.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| animica_serve-0.1.7-py3-none-any.whl | Python 3 | none | any | Details for animica_serve-0.1.7-py3-none-any.whl |
Total release size: 26.0 kB
Release files / animica_serve-0.1.7.tar.gz
| Download URL | animica_serve-0.1.7.tar.gz |
|---|---|
| Size | 13.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
71ffdda00bbb6669e1a9eb0693dc3dfe3c40c425abc3e06d1319795348a76526
|
|
BLAKE2b-256 checksum How to use checksums |
f591e5cf4439208bb6760e2c57dc718dc217e3fe559c891201b994e404f6a84c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
Release files / animica_serve-0.1.7-py3-none-any.whl
| Download URL | animica_serve-0.1.7-py3-none-any.whl |
|---|---|
| Size | 12.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
91d80a5eeba757312d305bfdc79e9a72fb013acdb7ee830c1565a26532df4087
|
|
BLAKE2b-256 checksum How to use checksums |
4aef905680f5af5c986f1f95b93a189ef10a344cd9693213daf73e8fb21a9ef8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
Security for animica-serve 0.1.7
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A 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.