Skip to main content

🧙‍♂️ Sage: the senior dev in your terminal

Sage welcome page.

🤔 Why Sage?

  • Claude Code, Codex CLI, and Cursor are hella expensive.
  • Most open-source “alternatives” are too complicated and cluttered doing too much for mid context engineering and agentic features they are have.
  • I wanted a CLI that could switch between any model I want at any moment (500+ models, 50+ free ones).

⚙️ What It Does

  • Reads your project, understands your codebase, and helps you write, refactor, and debug all without switching tabs or selling your kidney for a subscription.
  • And yeah, it’s not just for coding. You can even ask it how to get a girlfriend? and sage will help (no agentic actions for that though, you gotta do that part yourself).

⬇️ How to Install

pip install sage-code
  • and then type
sage

in the terminal of the directory you created for your project (not in your downloads or desktop folder ).

  • then you will see Welcome! Setting up and analyzing your project now...
  • After that, just follow the terminal instructions.
  • Grab your API key from OpenRouter, paste it in.
  • select your favorite model, and start building your next project.

🧩 How It Works

  • The fundamental protocol is inspired by the hardest-working gatekeepers we all know.
  • If you’re into papers and minimal math, the technique’s on arXiv
  • The code is minimalist by design.
  • Inside the sage folder, you’ll find:
sage/
├── Starters/   : sets up the project, initializes the protocol, and provides context  
└── Core/       : handles the main agent orchestration and LLM communication 
  • Programming ideology? Procedural spaghetti.
  • Trust me bro you can figure it out and customize it. Just ask Sage itself (no ChatGPT though).

🤝 Oh btw,

  • if you’re unemployed and got some time to contribute to this project:
  • fork the repo,and make it cooler
  • or just add up to my spaghetti.I’ll be around to merge your PRs.

📢 Final Words

  • Just the first version, built after work — so don’t be harsh on babe.
  • Made with ❤️ by a brokie named Fikre.

Metadata

Release files for sage-code 0.1.4

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

Source distribution (sdist)

Source distribution for sage-code 0.1.4
File Size Uploaded Provenance Actions
sage_code-0.1.4.tar.gz 26.6 kB Without provenance Details for sage_code-0.1.4.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for sage-code 0.1.4
File Interpreter ABI Platform Actions
sage_code-0.1.4-py3-none-any.whl Python 3 none any Details for sage_code-0.1.4-py3-none-any.whl

Total release size: 57.2 kB

Release files / sage_code-0.1.4.tar.gz

Download URL sage_code-0.1.4.tar.gz
Size 26.6 kB
Tags Source
SHA-256 checksum
How to use checksums
8ca532166f2c96029b4b2000c1c9a56f05e8dc0af3c2db912253d1dafd2d3507
BLAKE2b-256 checksum
How to use checksums
654e58f20a66bf089df10a472934a20b1f1a7c563c2392df5d7ddd5e75733bd5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.4

Release files / sage_code-0.1.4-py3-none-any.whl

Download URL sage_code-0.1.4-py3-none-any.whl
Size 30.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
4edfa58c6aeaffd1514365d48c65858dd1d07152c069fabaf3ee99cd570c17b0
BLAKE2b-256 checksum
How to use checksums
e5a7b2f1255ea18eaccc2378498959d62320c5204844372c61e5c0bd5f02b314
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.4

Security for sage-code 0.1.4

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.

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