The official repo for "LLoCo: Learning Long Contexts Offline"
-
Updated
Jun 15, 2024 - Python
#
context-compression
Here are 12 public repositories matching this topic...
Pytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)
-
Updated
Apr 18, 2024 - Python
Biological code organization system with 1,029+ production-ready snippets - 95% token reduction for Claude/GPT with AI-powered discovery & offline packs
developer-tools code-snippets code-organization cost-reduction token-reduction prompt-optimization context-management ai-assisted-coding context-compression rag-optimization chain-of-draft token-optimization llm-efficiency claude-optimization context-engineering context-pruning repository-aware gpt-optimization infinite-retrieval llm-context-window
-
Updated
Nov 10, 2025 - Python
Awesome list of paper on vision-based context compression
-
Updated
Feb 15, 2026
Exploring Context Compression techniques for token reduction. Fine-tuning LLMs for efficient text compression and reduced inference costs, analyzing the trade-offs with Q&A accuracy.
-
Updated
Jun 1, 2025 - Jupyter Notebook
MCP server that scores, compiles & optimizes prompts for any LLM. Deterministic prompt compiler with zero AI calls inside. Freemium: 10 free, then Pro or Power tier.
typescript ai mcp openai developer-tools freemium claude ai-tools llm prompt-engineering cost-reduction anthropic multi-llm prompt-optimization context-compression token-cost model-context-protocol mcp-server prompt-scoring prompt-compiler
-
Updated
Feb 27, 2026 - TypeScript
Exploring artificial compressed languages to improve efficiency, context usage, and cross-lingual unification in LLMs
natural-language-processing language-models interlingua ai-research compressed-representation llm context-compression token-efficiency
-
Updated
Aug 30, 2025
Retriever, Summarizer, Reader for LLM ODQA(Open-Domain Question Answering) to increase Information Density
-
Updated
Jan 8, 2026 - Python
Infinite context for AI assistants using semantic compression and retrieval with Gemini
-
Updated
Feb 7, 2026 - Python
LLM context compression proxy — 40-70% token savings, zero code changes
python proxy openai tfidf ai-agents claude fastapi gpt4 llm cost-reduction tiktoken anthropic context-window llm-optimization prompt-compression context-compression token-optimization
-
Updated
Feb 24, 2026 - Python
a technique for compressing verbose AI tool call outputs into concise summaries, reducing token consumption
-
Updated
Oct 30, 2025 - Jupyter Notebook
Detecting silent pivot substitution in LLMs under context compression
-
Updated
Feb 26, 2026 - Python
Improve this page
Add a description, image, and links to the context-compression topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the context-compression topic, visit your repo's landing page and select "manage topics."