Skip to main content

BaseRT Local Coding Agent (basert-agent) 🚀

Fastest LLM inference runtime & local coding agent plugin for Apple Silicon via native Metal, with verifiable HDAR attestation receipts. Zero API keys, 100% on-device data privacy.

Quick Start

# 1. Install basert-agent
pip install basert-agent

# 2. Serve a model locally on Apple Silicon Metal
basert-agent serve basecompute/gemma-4-E4B-it

# 3. Run pi-basert local coding agent
pi-basert "Refactor local workspace modules"

Features

  • ⚡ Native Metal Apple Silicon Acceleration: High-throughput local LLM inference.
  • 🔒 Zero Data Leakage: No external API keys required; 100% on-device execution.
  • 🛡️ Verifiable HDAR Attestation Receipts: Every code generation produces cryptographic SHA-256 integrity proofs and Merkle roots.

License

MIT License

Metadata

Release files for basert-agent 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for basert-agent 1.0.0
File Size Uploaded
basert_agent-1.0.0.tar.gz 3.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for basert-agent 1.0.0
File Interpreter ABI Platform
basert_agent-1.0.0-py3-none-any.whl Python 3 none any Details

Total release size: 8.3 kB

Release files / basert_agent-1.0.0.tar.gz

Download URL basert_agent-1.0.0.tar.gz
Size 3.8 kB
Tags Source
SHA-256 checksum
How to use checksums
5d73d8861df2919bd882dfe0be2be0cad1d8bdb879f53ca15ce300cc83b87afb
BLAKE2b-256 checksum
How to use checksums
f9bf87a5dd06a2d27946b3a00d444a1a6e2a1d8665297b587ddccf3304264089
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.12

Release files / basert_agent-1.0.0-py3-none-any.whl

Download URL basert_agent-1.0.0-py3-none-any.whl
Size 4.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a6b11b9e84524eeeaed64e9d6874e47eeb0cbf17323c443875884d9e5909d6c5
BLAKE2b-256 checksum
How to use checksums
5d8db4f859b7ebc215fd386e4c6aafd9482c709e6edb7332e391243a27e79007
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.12

Release history Release notifications | RSS feed

This release

1.0.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page