Token Efficiency Python Packages

gcf-python

GCF Python implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

corvinos

Self-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.

tokdash

Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage across providers with heatmaps, cost tracking, token counting and quota resets..

codeprism-ai

Standalone Python package + MCP server that builds and maintains a persistent knowledge graph of any codebase, exposing precise, token-efficient context to AI coding agents.

grip-browser

CDP-native browser SDK for AI agents. Median 1,998-token semantic snapshot vs 58,912 tokens of raw HTML across 8 real pages (16.0x). No Playwright or Puppeteer.

furl-ctx

Context compression for AI agents — cut token usage costs with retrievable CCR compression. Rust core + Python API, Claude Code & Codex plugin, MCP server. PyPI: furl-ctx

agent-coherence

The coordination layer for Multiplayer AI

zerodom

Terminal-native DOM perception layer for AppSec and AI. Hook into live Chrome sessions, compress HTML tokens by 98.9%, and map attack surfaces deterministically.

gcf-proxy

MCP proxy: zero-code GCF adoption. Wraps any MCP server, converts JSON to GCF mid-flight. 53-71% fewer tokens. Works with any structured data.

context-handoff-bundle

Resume yesterday's AI coding session for ~3% of the tokens. Save what your agent learned, load it in any terminal -- with drift detection.

axiolex

Shared tool discovery and execution for AI clients and applications across MCP, A2A, and internal tools—intent-ranked Top-K retrieval with centrally managed provider and tool changes

algernon-mcp

Algernon — orchestrate a fleet, keep your mind. Open-source MCP for scoped parallel sub-task dispatch. Apache-2.0.

agent-readable

A lightweight Python protocol and tool for agent-oriented documentation

mnemosyne-lite

Local-first long-term memory for AI agents - plain Markdown vault + thin MCP server. CJK-aware BM25, token-efficient by design.

ison-py

🔥 Token-efficient JSON alternative for LLMs & agentic AI — same data, fewer tokens. Python · JS/TS · Rust · Go · C++

contexel

A complete, runnable code-execution agent that uses contexel as the deterministic context-economy layer.

lap-score

Measure and improve the token-efficiency of agent-facing APIs (OpenAPI & MCP): a scorer, linter, the LAP profile, and a reproducible token benchmark.

graphscout

Cached, incremental code-graph maps so AI agents query code structure instead of reading whole files. CLI + MCP, wires into Claude Code, Codex, Gemini CLI, Cursor. Auto-sync watch mode.

ison-cli

🔥 Token-efficient JSON alternative for LLMs & agentic AI — same data, fewer tokens. Python · JS/TS · Rust · Go · C++

cubest

cubest

codegraph-kit

Cached, incremental code-graph maps so AI agents query code structure instead of reading whole files. CLI + MCP, wires into Claude Code, Codex, Gemini CLI, Cursor. Auto-sync watch mode.

isonantic

🔥 Token-efficient JSON alternative for LLMs & agentic AI — same data, fewer tokens. Python · JS/TS · Rust · Go · C++

omnex

Universal retrieval. Structure-aware. Token-efficient.

surgraft

LLM tool to move functions across files with 0 token cost