Token Savings Python Packages

jcodemunch-mcp

The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing

code-context-engine

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP server, free, open source.

memoryos

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

supamem

Project-agnostic dual-memory MCP CLI for Claude Code, Cursor, and OpenCode (Qdrant tuned hybrid retrieval + structural memory hooks)

cctx-mcp

CCTX-MCP — Code ConTeXt via MCP. AI agent code analysis that cuts token usage by 87%. tree-sitter AST parsers for Swift, Python, TS, Rust, Go, Dart.

codemunch-pro

Nuke your token usage. Code indexing MCP server: 15 tools, 10 languages, O(1) retrieval, hybrid search, call graphs.

tokennuke

Nuke your token usage. Code indexing MCP server: 15 tools, 10 languages, O(1) retrieval, hybrid search, call graphs.

iflow-mcp-memoryos

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

jmunch-core

The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing