🔓Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
// ragheadroomlabs-ai/⟨Python⟩★ 74,459◷ Apache-2.0[ claude ]
Projects tagged #context-window
// context-window (16)
🔓
🔓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…
// mcp-serversjgravelle/⟨Python⟩★ 2,715◷ NOASSERTION[ claude ]
🔓Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
// pluginsalexgreensh/⟨Python⟩★ 2,460◷ NOASSERTION[ claude ]
🔓High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server,…
// mcp-serverszzet/⟨Go⟩★ 1,810◷ Apache-2.0[ claude ]
🔓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…
// skillsmemvid/⟨TypeScript⟩★ 578◷ MIT[ claude ]
🔓Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.
// plugins0xhimanshu/⟨Python⟩★ 134◷ MIT[ claude ]
🔓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)…
// ragdiegosouzapw/⟨TypeScript⟩★ 132◷ MIT[ claude ]
🔓Know your headroom. Context window usage bar for Claude Code.
// devtoolshenchmarketing-rgb/⟨Shell⟩★ 70◷ MIT[ claude ]
🔓Long-term memory for AI coding agents (Claude Code, Codex, opencode) as a tree of plain files
// mcp-serversgonzaroman/⟨Python⟩★ 11◷ MIT[ claude ]
🔓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…
// devtoolscompozy/⟨TypeScript⟩★ 27◷ MIT[ claude ]
🔓Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
// mcp-servers00200200/⟨Python⟩★ 10◷ MIT[ claude ]
🔓Btop-style real-time context monitor for Claude Code sessions — live context map, cache economics, subagents, and a compiled PDF report.
// devtoolsarian-shamaei/⟨Rust⟩★ 29◷ MIT[ claude ]
🔓🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)
// skillsmocasus/⟨Python⟩★ 20◷ MIT[ claude ]
🔓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…
// ragiKislay/⟨Python⟩★ 20◷ Apache-2.0[ claude ]
🔓AI-powered MCP proxy for Playwright and Figma. Optimize Claude Code and AI agents with session recovery, context reduction and intelligent tool routing.
// mcp-serversZenyaDAR/⟨JavaScript⟩★ 15◷ MIT[ claude ]
🔓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。
// devtoolszander-zyx/⟨TypeScript⟩★ 10◷ MIT[ claude ]