#token-optimization

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Enhanced fork of OpenWolf — a token-conscious second brain for Claude Code, with bounded storage, self-maintenance (openwolf doctor), .wolfignore scoping, and tunable retention. AGPL-3.0.

Windows fork of pxpipe: transparent Fable 5 compression for Claude Desktop on Windows 11.

Local orchestration for Claude Code — session recovery, scheduling, worktrees, Token Saver, and dashboards via official CLI transport. Independent third-party software.

Safe, quality-gated model+effort router for Claude Code - delegates cheap work down to save tokens, escalates hard/sensitive work up through a verify staircase, never-down gate, and fail-safe Lock, up to a consent-gated Fable 5 top rung. Not the cheapest router; the safest one inside Claude.

Local-first agentic memory lifecycle manager for AI coding IDEs

Cut Claude Code token costs ~80% by routing analysis to DeepSeek and graphify before reading source files.

Token optimizer for AI coding agents - Claude Code, Codex, Cursor, Aider, Gemini CLI, Cline, Windsurf, Copilot.

Local-first context cleaner for AI agents.

Obsidian-based persistent memory framework for AI coding agents. Set it up with just a single prompt.

Plug-and-play Copilot agent bundle that cuts token usage ~50% via orchestrator-worker context isolation

PECS: 基于 LangGraph 的四角色多智能体任务求解框架（Planner/Executor/Critic/Synthesizer）。WebShop 真实环境 +25pp (25% vs 0%)；GAIA 官方 53 题 26.4% vs ReAct 24.5%（McNemar 不显著）。含 AST 沙箱、50000 token 硬预算、FastAPI 限流/混沌/CI/Prometheus。

The non-obvious setup that keeps a Claude Code project sharp as it grows: skill architecture, context budget, document ingestion, and permission/trust. The things I wish I knew before I started.

Measure Claude Code token use, cut the waste, and prove your savings with a real before and after. Local, private, measured from your own usage counters.

Local context-compression layer for agent tool outputs. Claude Code PostToolUse hook or generic filter, single Go binary.

Reduce Codex and Claude context waste by measuring MCP tools, repo instructions, and safe token-budget cuts.

Deterministic Claude Code hook system that reduces real token consumption (no extra LLM calls) via read dedup, diff-serving, Bash output distillation, large-file outlines, compaction awareness, and capped cross-session memory.

Local-first context gateway that helps AI coding agents read less, spend less, and stay grounded in your repo.

A Claude skill that cuts token waste lean replies, smart file reading, zero redundant work

RTK + Caveman token-efficiency stack for Hermes Agent

engramx's bi-temporal mistakes + structural code-graph as auto-discoverable Claude Code Skills. Catches recurring mistakes before agents repeat them. Apache 2.0, local SQLite, zero cloud.

In-flight conversational context compressor and stale-turn pruner to eliminate context rot.

Confidence-gated model routing for coding agents — run work at the cheapest model that can pass verification. SKILL.md, MIT.