tokensave MCP工具

Single native binary, zero dependencies

Every alternative requires a runtime: Python, Node.js, or both. tokensave ships as a single ~25 MB Rust binary with all 34 tree-sitter grammars bundled. Nothing else to install.

1. Install

Homebrew (macOS):

brew install aovestdipaperino/tap/tokensave

Scoop (Windows):

scoop bucket add tokensave https://github.com/aovestdipaperino/scoop-bucket
scoop install tokensave

Cargo (any platform):

cargo install tokensave                          # full (34 languages, default)
cargo install tokensave --features medium        # medium (20 languages)
cargo install tokensave --no-default-features    # lite (11 languages, smallest binary)

Prebuilt binaries (Linux, Windows, macOS):

Download from the latest release and place the binary in your PATH.

Building

cargo build --release                          # full (34 languages, default)
cargo build --release --features medium        # medium (20 languages)
cargo build --release --no-default-features    # lite (11 languages)

cargo test                                     # run all tests (requires full)
cargo check --no-default-features              # verify lite compiles
cargo clippy --all

Quick Start

2. Configure your agent

tokensave install                         # auto-detects installed agents
tokensave install --agent antigravity     # Google Antigravity (formerly Windsurf)
tokensave install --agent claude          # Claude Code
tokensave install --agent cline           # Cline
tokensave install --agent codex           # OpenAI Codex CLI
tokensave install --agent copilot         # GitHub Copilot
tokensave install --agent cursor          # Cursor
tokensave install --agent gemini          # Gemini CLI
tokensave install --agent kilo            # Kilo CLI
tokensave install --agent kiro            # AWS Kiro
tokensave install --agent kimi            # Moonshot Kimi CLI
tokensave install --agent opencode        # OpenCode
tokensave install --agent roo-code        # Roo Code
tokensave install --agent vibe            # Mistral Vibe
tokensave install --agent zed             # Zed

Each agent gets its MCP server registered in the native config format. Claude Code additionally gets a PreToolUse hook (blocks wasteful Explore agents), a UserPromptSubmit hook, a Stop hook, prompt rules in CLAUDE.md, and auto-allowed tool permissions. Kiro gets global MCP config, read-only tokensave auto-approval, AGENTS.md steering, and a tokensave-managed default agent with delegation guardrail hooks plus post-write sync; user-managed Kiro agents are preserved.

All changes are idempotent -- safe to run again after upgrading. After agent setup, you'll be offered a global git post-commit hook.

Multi-Branch Indexing (Optional)

tokensave can optionally maintain a separate code graph per git branch. When enabled, switching branches never gives you stale results and never re-indexes files you already parsed on another branch. Multi-branch tracking is opt-in -- without it, tokensave uses a single database for all branches.

CLI commands

tokensave branch add              # track the current branch
tokensave branch list             # see tracked branches and DB sizes
tokensave branch remove <name>    # stop tracking a branch
tokensave branch removeall        # remove all tracked branches except default
tokensave branch gc               # clean up branches deleted from git

CLI Reference

tokensave init [path]              # Initialize a new project (full index)
tokensave sync [path]              # Incremental sync (must be initialized first)
tokensave sync --force [path]      # Force a full re-index
tokensave sync --doctor [path]     # Sync and list added/modified/removed files
tokensave status [path]            # Show statistics + cost summary
tokensave status [path] --json     # Show statistics (JSON output)
tokensave status --details         # Include node-kind breakdown
tokensave cost [range]             # Token cost summary (default: 7d)
tokensave cost --by-model          # Cost grouped by model
tokensave cost --by-task           # Cost grouped by task category
tokensave cost --export json|csv   # Export cost data
tokensave query <search> [path]    # Search symbols
tokensave files [--filter dir] [--pattern glob] [--json]   # List indexed files
tokensave affected <files...> [--stdin] [--depth N]        # Find affected test files
tokensave install [--agent NAME]   # Configure agent integration
tokensave reinstall                # Refresh settings for all installed agents
tokensave uninstall [--agent NAME] # Remove agent integration
tokensave serve                    # Start MCP server
tokensave monitor                  # Live TUI showing MCP calls across all projects
tokensave upgrade                  # Self-update to latest version
tokensave channel [stable|beta]    # Show or switch update channel
tokensave doctor [--agent NAME]    # Check installation health
tokensave branch add|list|remove|removeall|gc   # Multi-branch management
tokensave current-counter          # Show per-project token counter
tokensave reset-counter            # Reset per-project token counter
tokensave disable-upload-counter   # Opt out of worldwide counter uploads
tokensave enable-upload-counter    # Re-enable worldwide counter uploads

---

Git & Workflow

tokensave vs CodeGraph

tokensave is a ground-up Rust rewrite of CodeGraph (Node.js/TypeScript). Both build semantic code graphs for AI coding agents, but they diverge significantly in scope and capabilities.

CodeGraph pioneered the approach and remains a solid choice if you prefer npm tooling and only need Claude Code integration. tokensave extends the concept with deeper analysis, more agents, background sync, multi-branch support, and a native binary with no runtime dependencies.

For detailed comparisons against CodeGraph, Dual-Graph (GrapeRoot), code-review-graph, and OpenWolf, see docs/COMPARABLE-TOOLS.md.

---

Why tokensave Over the Alternatives

Several tools reduce token usage for AI coding agents. Here's why tokensave stands apart.

Troubleshooting