PyRank
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About

Context Compression Python Packages

Python packages with the GitHub topic context-compression. Sorted by relevance, with stars and monthly downloads.
juyterman1000
entroly-core

Open-source context engine that catches AI hallucinations and cuts your token bill 70–95%. The only AI helper that shows its work. Claude · Cursor · Codex,GPT & Custom Providers

13K 381 62
juyterman1000
entroly

Open-source context engine that catches AI hallucinations and cuts your token bill 70–95%. The only AI helper that shows its work. Claude · Cursor · Codex,GPT & Custom Providers

13K 381 62
MakeaMouse
fish-bridge-mcp

An economical and fuel(token) efficient AI tool, graph session memory for looong chat session

1K 0 0
naranor
agent-coderag

CodeRAG: Lightweight semantic code search and distillation utility for AI coding agents. It solves the API knowledge gap via real-time local signature extraction and intent analysis. Optimized for token efficiency, it compresses codebase context into compact semantic summaries stored in a local DuckDB vector similarity index.

1K 1 0
mo-tunn
tokenpack-rag

TokenPack packs long documents, codebases, PDFs, and folders into compact, evidence-dense LLM context using local embeddings, evidence scoring, and budget-aware selection.

905 7 0
open-compress
claw-compactor

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

709 2K 212
KRLabsOrg
squeez

Squeeze verbose LLM agent tool output down to only the relevant lines

570 17 0
castnettech
mnemosyne-engine

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

492 58 9
castnettech
mnemosyne-ollama

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

399 58 9
h2cker
llama-index-postprocessor-vecr

Deterministic, auditable LLM context compression — regex whitelist guarantees structured facts (IDs, URLs, dates, code) survive. Two layers: retention + heuristic knapsack.

329 0 0
h2cker
vecr-compress

Deterministic, auditable LLM context compression — regex whitelist guarantees structured facts (IDs, URLs, dates, code) survive. Two layers: retention + heuristic knapsack.

321 0 0
castnettech
mnemosyne-mcp

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

213 58 9
compactbench
compactbench

Open benchmark for LLM context compaction methods — measures what survives when you replace conversation history with a compacted artifact. Multi-cycle drift, hidden ranked set.

200 2 0
    • Data from PyPI, GitHub, ClickHouse, and BigQuery