Token Reduction Python Packages

neuralmind

Persistent memory for AI coding agents. Your agent learns your codebase the way a senior engineer would — what files go together, what you usually edit next. Works with Claude Code, Cursor, Cline, Continue. 100% local. (Side effect: 12-50× cheaper code questions.)

indexio-cli

Code Search and MCP server for AI coding agents. Instant Token Reduction.

tzero-mcp

AST Codebase Context Engine & 21-Tool MCP Server for AI Coding Agents — Up to 95% Token Reduction & Zero-Leak Security Architecture

local-context-compiler

Cut LLM context and Claude Code sessions 40–80% without rewriting a byte. Offline, verbatim, with an audit receipt for every block dropped. CLI, MCP server and Claude Code/Open AI Plugin. MIT.

tokentrust-cli

CLI and MCP server that verifies AI coding agent context-reduction proxies' token and cost savings claims

dompruner

Token-efficient web content extraction for Python. DOM AST pruning + BM25 section filtering cuts LLM context by 90%+ — LangChain-compatible, no API key required.

arbiterx-gate

Your AI writes code. ArbiterX decides if it's good enough. Intelligent middleware for AI coding assistants — 97% token reduction, smart model routing, quality gate scoring. Works with Claude Code, Codex, Cursor, Copilot, Aider & more.

reducethemtokens

Compress any code repo into a compact skeleton to reduce LLM token usage. 90%+ reduction with full structural retention.

astra-mcp

MCP server giving Claude Code, Cursor & Codex permanent AST code memory. 98.9% token reduction. 100% local.

context-compressor

AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while preserving semantic meaning with advanced compression strategies.

contextos-cli

AI context infrastructure layer — reduce token consumption, maintain AI continuity. Fully removable.

rust-cave-001

Rust + PyO3 implementation of Caveman Compression for LLM token reduction

tokenseive

Multi-layer token optimization for LLM applications — compress prompts, map codebases, reduce output. Zero required dependencies.

certainlogic-guard

Linguistic confidence gate for AI responses. Catches hedging words (maybe, I think). Not fact verification. Zero dependencies.

prompt-compressor

Reduce LLM prompt tokens by 20–70% using rule-based algorithms. No model, no API. Web tool + npm package.

software-dlc-tile

Token-efficient tabular encoding for JSON and LLM prompt payloads.