[PR #888] [CLOSED] Add GCF Token Optimization (61-71% savings) #14844

New Issue

GiteaMirror · 2026-07-12T22:39:56-05:00

GiteaMirror commented

2026-07-12 22:39:56 -05:00

📋 Pull Request Information

Original PR: https://github.com/Shubhamsaboo/awesome-llm-apps/pull/888
Author: @blackwell-systems
Created: 6/16/2026
Status: ❌ Closed

Base: main ← Head: add-gcf-optimization

📝 Commits (1)

672b71b Add GCF Token Optimization to LLM Optimization Tools

📊 Changes

5 files changed (+285 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)
➕ advanced_llm_apps/llm_optimization_tools/gcf_token_optimization/README.md (+126 -0)
➕ advanced_llm_apps/llm_optimization_tools/gcf_token_optimization/gcf_demo.py (+81 -0)
➕ advanced_llm_apps/llm_optimization_tools/gcf_token_optimization/gcf_llm_example.py (+74 -0)
➕ advanced_llm_apps/llm_optimization_tools/gcf_token_optimization/requirements.txt (+3 -0)

📄 Description

Summary

Adds GCF (Graph Compact Format) token optimization to the LLM Optimization Tools section.

What's included

gcf_demo.py: Token comparison demo (JSON vs GCF with tiktoken counts)
gcf_llm_example.py: LLM integration example showing identical answers with fewer tokens
README.md: Full documentation with format comparison and benchmarks
requirements.txt: Dependencies

Why GCF

61-71% token reduction vs JSON (verified with tiktoken)
100% comprehension on every frontier model (1,700+ evaluations)
Handles JSON, YAML, TOML, CSV, and MessagePack (not JSON-only)
33 billion+ lossless round-trips verified
Six language implementations, MIT licensed
Drop-in proxy for zero-code adoption

Website: https://gcformat.com
Benchmarks: https://gcformat.com/guide/benchmarks.html

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/Shubhamsaboo/awesome-llm-apps/pull/888 **Author:** [@blackwell-systems](https://github.com/blackwell-systems) **Created:** 6/16/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `add-gcf-optimization` --- ### 📝 Commits (1) - [`672b71b`](https://github.com/Shubhamsaboo/awesome-llm-apps/commit/672b71b906da42e461c4c1ed3b528c4fc77f724d) Add GCF Token Optimization to LLM Optimization Tools ### 📊 Changes **5 files changed** (+285 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) ➕ `advanced_llm_apps/llm_optimization_tools/gcf_token_optimization/README.md` (+126 -0) ➕ `advanced_llm_apps/llm_optimization_tools/gcf_token_optimization/gcf_demo.py` (+81 -0) ➕ `advanced_llm_apps/llm_optimization_tools/gcf_token_optimization/gcf_llm_example.py` (+74 -0) ➕ `advanced_llm_apps/llm_optimization_tools/gcf_token_optimization/requirements.txt` (+3 -0) </details> ### 📄 Description ## Summary Adds GCF (Graph Compact Format) token optimization to the LLM Optimization Tools section. ### What's included - `gcf_demo.py`: Token comparison demo (JSON vs GCF with tiktoken counts) - `gcf_llm_example.py`: LLM integration example showing identical answers with fewer tokens - `README.md`: Full documentation with format comparison and benchmarks - `requirements.txt`: Dependencies ### Why GCF - 61-71% token reduction vs JSON (verified with tiktoken) - 100% comprehension on every frontier model (1,700+ evaluations) - Handles JSON, YAML, TOML, CSV, and MessagePack (not JSON-only) - 33 billion+ lossless round-trips verified - Six language implementations, MIT licensed - Drop-in proxy for zero-code adoption Website: https://gcformat.com Benchmarks: https://gcformat.com/guide/benchmarks.html --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

GiteaMirror added the pull-request label 2026-07-12 22:39:56 -05:00

GiteaMirror closed this issue

2026-07-12 22:39:57 -05:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/awesome-llm-apps#14844