Skip to content
#

llm-token-compression

Star

Here are 5 public repositories matching this topic...

Language: All
Filter by language
All 5 Python 2 Go 1 TypeScript 1

open-compress / claw-compactor

Star 2.2k

14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

python tree-sitter developer-tools llm-tools llm-compression prompt-compression context-compression ai-infrastructure ai-agent-tools token-compression context-pruning context-window-optimization openclaw llm-token-compression llm-cost-reduction llm-context-compression claw-compactor reversible-compression ast-code-analysis fusion-pipeline
  • Updated Apr 1, 2026
  • Python

nawodyaishan / pdf2md-tui

Star 4

High-speed PDF → Markdown ingestion engine for multimodal RAG pipelines. Extracts structured text + isolated images so downstream chunkers, LlamaIndex, and VLM agents get context that actually works

go markdown cli golang tui clean-architecture data-extraction multi-modal batch-processing ai-agents rag cobra-cli pdftomarkdown clean-architechture document-parsing pdf-to-markdown token-efficiency llm-token-compression
  • Updated May 10, 2026
  • Go

leonardomg1 / Caveman-UTC

Star 0

Caveman-UTC (Ultra Token Compression): A formal, mathematical compression framework designed for Machine-to-Machine (M2M) communication, Agent Memory Systems, Knowledge Graphs, and System Prompts.

ai skill tokens ai-agents claude symbolic-logic knowledge-graphs llm prompt-engineering anthropic system-prompts antigravity token-compression agent-memory codex-skill llm-token-compression m2m-communication caveman-utc leosuite
  • Updated May 28, 2026

Improve this page

Add a description, image, and links to the llm-token-compression topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the llm-token-compression topic, visit your repo's landing page and select "manage topics."

Learn more