#Token-savings
Showing 8 of 8 repositories tagged #token-savings, ranked by stars
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
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 Code, Cursor & any MCP client. 313B+ tokens saved.
Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.
lowfat - slim your command output. strips noise, saves tokens.
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration
MCP server for Git with local Ollama — zero tokens for git operations
Auditable context capsules for LLM handoffs, coding agents, and OpenCode MCP workflows.