The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing
-
Updated
Apr 23, 2026 - Python
#
token-savings
Here are 19 public repositories matching this topic...
Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.
cli ai mcp code-analysis developer-tools codebase cursor copilot codex claude llm context-engineering token-savings repo-map
-
Updated
Apr 24, 2026 - TypeScript
SDL-MCP gives coding agents the right code context, not your entire repo. It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.
mcp code-analysis agents codegraph semantic-analysis ai-agents code-context agent-tools agentic-workflow vibe-coding coding-agent agentic-coding codebase-indexing codebase-intelligence agent-context token-savings
-
Updated
Apr 24, 2026 - TypeScript
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 developer-tools code-generation ai-agents claude developer-tool openai-api local-llm ollama lm-studio model-context-protocol mcp-server mcp-client claude-mcp vibe-coding-assistant lm-studio-mcp token-savings
-
Updated
Apr 21, 2026 - JavaScript
MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration
mcp static-analysis tokens developer-tools token tokenization codex ai-agents claude code-intelligence claude-ai claude-desktop mcp-server claude-code claude-code-plugin claude-skills claude-skill claude-code-skill codex-skill token-savings
-
Updated
Apr 24, 2026 - TypeScript
A reversible code minifier for AI. Save tokens by stripping code format in your prompt, then perfectly restore it in the responces.
-
Updated
Mar 23, 2026 - Python
Guardian Agent and Token Savings for Claude Code
headroom rtk agent-gateway gurdian codex-monitor token-savings token-saving guardian-agents claude-code-token-saving vulnerability-guardian
-
Updated
Apr 23, 2026 - Rust
Turn any OpenAPI spec into a native CLI binary. No MCP, no bloat, no runtime dependencies, ONLY CLI.
go shell cli golang mcp swagger openapi ai-agents ai-agent ai-agents-cli ai-agent-tools token-savings token-saving
-
Updated
Mar 30, 2026 - Go
TSCG — Deterministic tool-schema compiler for LLM agents. 50-72% token savings, 50 tools in 2.4ms. Phi-4 recovers from 0% to 90% accuracy. 459 tests, zero dependencies, MIT.
typescript compression mcp tool-use llm langchain function-calling prompt-optimization agentic-ai token-savings
-
Updated
Apr 22, 2026 - TypeScript
Caveman output style for Claude Code: 40% fewer output tokens, always-on formatting
-
Updated
Apr 17, 2026
Run Claude Code or Codex 50–80% cheaper: Hermit is an MCP executor with Codex-first fallback routing (codex → z.ai → local) while your orchestrator stays in charge.
python mcp developer-tools glm codex cost-optimization fastapi ai-agent llm local-llm ollama z-ai llm-routing mcp-server claude-code coding-agent token-savings claude-code-extension sub-agent
-
Updated
Apr 24, 2026 - Python
Make GitHub Copilot responses terse across VS Code Chat, Copilot CLI, cloud agent, and code review. One command. 40-75% fewer response tokens, no correctness hit.
cli developer-tools npx concise github-copilot llm prompt-engineering copilot-chat copilot-instructions agents-md chatmode token-savings
-
Updated
Apr 22, 2026 - TypeScript
Save Claude tokens by offloading tasks to free LLM APIs - 19x more workflows with the same token budget
-
Updated
Jan 29, 2026 - Shell
lowfat - slim your command output. strips noise, saves tokens.
rust cli open-source developer-tools shell-script llm cost-reduction token-optimization agentic-coding-tool token-savings token-saving
-
Updated
Apr 23, 2026 - Rust
Local Ollama-backed MCP server for Claude Code. Query large files without burning context (~30x token savings)
python mcp ai-tools llm anthropic claude-ai local-llm ollama context-compression mcp-server claude-code token-savings
-
Updated
Apr 14, 2026 - Python
CodeCrew — Senior engineering team for your AI-generated code. One command. Saves $20-40/day in tokens.
-
Updated
Apr 21, 2026 - JavaScript
Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.
memory sqlite mcp openai persistent-memory codex local-first ai-agent ollama qwen deepseek context-compression gemini-cli model-context-protocol mcp-server claude-code codex-cli token-savings codex-memory auditable-memory
-
Updated
Apr 23, 2026 - Python
Nuke your token usage. Code indexing MCP server: 15 tools, 10 languages, O(1) retrieval, hybrid search, call graphs.
-
Updated
Mar 2, 2026 - Python
FigureOut is a Python package allows developers to easily integrate LLM into their application.
natural-language-processing mcp python-library orchestration ai-agents llm tool-calling langchain-alternatives token-savings
-
Updated
Apr 20, 2026 - Python
Improve this page
Add a description, image, and links to the token-savings topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the token-savings topic, visit your repo's landing page and select "manage topics."