longhaul

yungmoneyhuncho/longhaul

★ 1 stars Python AI/LLM Updated 5d ago

Keep local-model chat sessions alive indefinitely. MCP server giving any local LLM automatic context compaction and permanent memory. Zero dependencies.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "longhaul": {
      "command": "uvx",
      "args": [
        "longhaul"
      ]
    }
  }
}

Or install with pip: pip install longhaul

README Excerpt

Use a local model the way you'd use ChatGPT or Claude. Just keep talking. It handles the context so you don't have to think about it, and it remembers across sessions. An MCP server, zero dependencies (stdlib Python), works with LM Studio, Ollama, llama.cpp, or any OpenAI-compatible endpoint. MIT. The thing that makes hosted assistants feel effortless isn't the model, it's

Tools (6)

LONGHAUL_API_KEYLONGHAUL_BASE_URLLONGHAUL_HOMELONGHAUL_MODELLONGHAUL_SESSIONLONGHAUL_TIMEOUT

Topics

context-managementllmlmstudiolocal-llmmcpmemoryollama

longhaul

Quick Install

README Excerpt

Tools (6)

Topics

Related AI/LLM Servers