Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
Projects tagged #context-window
// context-window (24)
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Co…
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server,…
Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. N…
Cut your Claude bill 59–70% by rendering bulky LLM context as dense PNG pages — 100% read accuracy, exact per-provider billing math (Anthropic/OpenAI/Gemini)…
Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.
Empirical analysis of Claude Code token usage: auto-compaction sweet spots across 8 developer workflows and Claude Desktop vs. CLI overhead
Your coding agent isn't getting dumber. Your context is just full of trash. Local context firewall & zero-loss runtime for Cursor, Claude Code, and autonomou…
Know your headroom. Context window usage bar for Claude Code.
Make every Claude token count. A Claude Code plugin that picks the model and effort for every prompt.
Find the dead weight in your Claude Code setup: what every request carries before you type, and what you never use. Single Rust binary.
Never kill a good Claude Code session again. A tiny, always-current ledger of mission-critical context that survives /clear and compaction.
Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
Long-term memory for AI coding agents (Claude Code, Codex, opencode) as a tree of plain files
Déjà vu for your coding agent: cuts ~30% of the input bill on real Claude Code sessions with cache-safe dedup and ski-rental context decay. Zero deps.
🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)
Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://gith…
Btop-style real-time context monitor for Claude Code sessions — live context map, cache economics, subagents, and a compiled PDF report.
AI-powered MCP proxy for Playwright and Figma. Optimize Claude Code and AI agents with session recovery, context reduction and intelligent tool routing.
Cost control for long Claude Code sessions on Windows, macOS and Linux: tiered context ceilings, a blocking handoff gate, and effort gears.
对标 claude-hud 核心功能,控制在 7 行以内更轻量。内置 13 个国产大模型平台用量查询 (智谱 GLM / MiniMax / DeepSeek / Kimi / StepFun / SiliconFlow 等),第三方代理用户也能实时看到额度消耗。
Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Ollama/VLLM/llama.cp…
✻ An animated HUD for Claude Code, with Claude's mascot: live context window, Max plan 5h/7d limits with pace forecast, cost, subagents and all your Claude w…