io.github.Anandb71/arbor

Name: io.github.Anandb71/arbor
Rating: 5 (141 reviews)
Author: anandb71

编码与调试

by anandb71

面向代码的 Graph-Native 智能层，帮助以图结构方式理解、组织并分析代码关系。

用图结构把分散的代码关系串起来，帮你更快看懂复杂项目与依赖脉络；Graph-Native 智能层让跨文件分析和重构决策都更有把握。

141GitHub

什么是 io.github.Anandb71/arbor？

面向代码的 Graph-Native 智能层，帮助以图结构方式理解、组织并分析代码关系。

README

<img src="docs/assets/arbor-logo.svg" alt="Arbor logo" width="120" height="120" /> <h1 align="center">Arbor</h1> Graph-native intelligence for codebases. Know what breaks before you break it. <a href="https://github.com/Anandb71/arbor/actions"><img src="https://img.shields.io/github/actions/workflow/status/Anandb71/arbor/rust.yml?style=flat-square&label=Rust%20CI" alt="Rust CI" /></a> <a href="https://crates.io/crates/arbor-graph-cli"><img src="https://img.shields.io/crates/v/arbor-graph-cli?style=flat-square&label=crates.io" alt="Crates.io" /></a> <a href="https://github.com/Anandb71/arbor/releases"><img src="https://img.shields.io/github/v/release/Anandb71/arbor?style=flat-square&label=release" alt="Latest release" /></a> <a href="https://github.com/Anandb71/arbor/pkgs/container/arbor"><img src="https://img.shields.io/badge/GHCR-container-blue?style=flat-square" alt="GHCR" /></a> <a href="https://glama.ai/mcp/servers/@Anandb71/arbor"><img src="https://img.shields.io/badge/MCP%20Directory-Glama-6f42c1?style=flat-square" alt="Glama MCP Directory" /></a> <img src="https://img.shields.io/badge/license-MIT-green?style=flat-square" alt="MIT License" /> <img src="docs/assets/arbor-demo.gif" alt="Side-by-side: an agent navigating tokio with grep-and-read (47 tool calls, still searching) vs the same agent with arbor's code graph (4 graph calls + 1 read, done)" width="900" /> Simulated replay — the <code>arbor</code> commands and their output are real (tokio @ 178k LOC). Methodology: <a href="docs/BENCHMARKS.md">BENCHMARKS.md</a>

v2.5.0 — The Last Excuse · PageRank 23x faster (149.8ms → 6.6ms on a 10k-node graph). Indexing goes parallel across every core. A 178k-LOC codebase cold-indexes in 1.6s. "Indexing is slow" was the last argument for letting your agent navigate with grep -r — it's gone. Every number reproducible: BENCHMARKS.md · Release notes →

Why Arbor

Most AI coding tools treat code as text. Arbor builds a semantic dependency graph — functions, classes, and modules as nodes; calls, imports, and inheritance as edges — then answers execution-aware questions with deterministic precision:

Question	Arbor answer
If I change this symbol, what breaks?	Blast radius with depth, confidence, and risk level
Who calls this — directly and transitively?	Caller/callee traversal on the call graph
What's the shortest path between A and B?	A* path through real dependencies
Is this PR too risky to merge?	CI gate on blast-radius thresholds

No keyword guessing. No embedding hallucinations. One graph, every interface.

What's new in v2.5.0

Change	Measured
PageRank rewrite — flat call-graph adjacency replaces per-iteration traversal	149.8ms → 6.6ms on a 10k-node graph (23x), verified side-by-side vs the old implementation
Parallel indexing — parse fans out across all cores, deterministic assembly	Arbor: 253ms → 95ms · tokio (178k LOC): 2.7s → 1.6s
Warm-start centrality — watcher recomputes seed from previous scores	Converges in ~2 rounds after a one-file patch instead of the full 20-iteration budget
Convergence early-exit	Iteration stops at 1e-9 max delta — the budget is a ceiling, not a sentence

Zero breaking changes — cargo install arbor-graph-cli --force and everything is just faster. Think a number is wrong? cargo bench -p arbor-graph and prove it: BENCHMARKS.md.

<details> <summary>v2.4.0 — The Agent-Native Leap (MCP <code>2026-07-28</code>, HTTP transport, Tasks, MCP Apps)</summary>

Feature	What it does
MCP `2026-07-28`	Stateless `server/discover`, response caching (`ttlMs`/`cacheScope`), dual-version fallback for `2025-03-26` clients
Tasks extension	`tasks/get` · `tasks/update` · `tasks/cancel` — cold-start indexing returns task handles, not errors
MCP Apps	Interactive blast-radius graph (`ui://arbor/blast-radius`) and architecture map (`ui://arbor/architecture-map`) inside agent hosts
HTTP transport	`arbor bridge --http --port 3333` — stateless MCP behind load balancers
Real `get_blast_radius`	Git-diff-aware impact analysis via shared `arbor-graph::compute_blast_radius`
Pagination	`offset` / `limit` / `hasMore` on `search_symbols` and `get_map`
Benchmarks	Criterion suite + CI regression gate — see BENCHMARKS.md

</details>

Quickstart

bash

# Install
cargo install arbor-graph-cli

# Index your project (one command)
cd your-project && arbor setup

# Explore before you edit
arbor map . --exclude-test          # ranked project skeleton (~1k tokens)
arbor refactor parse_file           # blast radius of changing a symbol
arbor diff                          # impact of uncommitted git changes

# Wire up your AI agent
claude mcp add --transport stdio --scope project arbor -- arbor bridge

Agent workflow: call get_map first → search_symbols / get_file_graph to locate code → Read only the target file. Full MCP guide →

For AI agents (MCP)

Arbor ships a production MCP server via arbor bridge. Stdio is the default; HTTP is opt-in for remote/enterprise.

bash

# Stdio (Claude, Cursor, VS Code)
arbor bridge

# HTTP (MCP 2026-07-28)
arbor bridge --http --port 3333

Cursor / VS Code

json

{
  "mcpServers": {
    "arbor": {
      "type": "stdio",
      "command": "arbor",
      "args": ["bridge"]
    }
  }
}

Templates: templates/mcp/ · Setup scripts: scripts/setup-mcp.sh · scripts/setup-mcp.ps1

16 MCP tools

Tier	Tools	Use when
Orientation	`get_map`	First call — token-budgeted project skeleton ranked by PageRank
Surgical	`list_entry_points` · `get_callers` · `get_callees` · `search_symbols` · `get_file_graph` · `get_node_detail`	Navigate to a specific symbol or file
Broad	`get_logic_path` · `analyze_impact` · `find_path` · `get_knowledge_path`	Trace dependencies, blast radius, paths
Agent-native	`get_blast_radius` · `explain_symbol` · `audit_security` · `get_architecture_overview` · `batch_query`	PR impact, onboarding, security audit, bulk lookup

Every tool returns { ok, tool, data, meta: { suggested_next_tool, suggested_next_args } } so agents chain calls without re-prompting.

Registry: io.github.Anandb71/arbor · Official API lookup · Glama listing

CLI reference

Command	Description
`arbor setup`	One-shot init + index
`arbor map`	Ranked, token-budgeted project skeleton
`arbor query <term>`	Fuzzy symbol search (supports `\|` OR)
`arbor callers / callees <sym>`	One-hop graph traversal
`arbor entry-points`	HTTP handlers, main, jobs, webhooks
`arbor file-graph <path>`	Symbols + edges in one file
`arbor inspect <sym>`	Full symbol detail
`arbor path <a> <b>`	Shortest call-graph path
`arbor refactor <sym>`	Blast radius before refactoring
`arbor diff`	Git-change impact report
`arbor check`	CI safety gate (`--max-blast-radius N`)
`arbor summary`	Auto-generate PR description
`arbor agent review`	Autonomous PR architecture review
`arbor agent onboard`	Codebase onboarding guide
`arbor agent guard`	Real-time architectural safety gate
`arbor bridge`	MCP server (add `--http` for HTTP transport)
`arbor watch`	Live re-index on file changes
`arbor gui`	Native desktop UI

All query commands support --json. map additionally supports --tokens N, --focus "pattern", --focus-changed.

Visual tour

Full recording: media/recording-2026-01-13.mp4

Installation

bash

# Rust / Cargo
cargo install arbor-graph-cli

# Homebrew (macOS/Linux)
brew install Anandb71/tap/arbor

# Scoop (Windows)
scoop bucket add arbor https://github.com/Anandb71/arbor && scoop install arbor

# npm wrapper (cross-platform)
npx @anandb71/arbor-cli

# Docker
docker pull ghcr.io/anandb71/arbor:latest

No-Rust installers:

macOS/Linux: curl -fsSL https://raw.githubusercontent.com/Anandb71/arbor/main/scripts/install.sh | bash
Windows: irm https://raw.githubusercontent.com/Anandb71/arbor/main/scripts/install.ps1 | iex

Pinned installs: docs/INSTALL.md

Language support

Production parsers: Rust · TypeScript / JavaScript · Python · Go · Java · C / C++ · C# · Dart

Fallback parsers: Kotlin · Swift · Ruby · PHP · Shell

Adding languages →

CI & pull requests

bash

arbor diff --markdown
arbor check --max-blast-radius 30 --markdown
arbor summary

GitHub Action (pre-built binary, ~5s vs ~3–5min compile):

yaml

name: Arbor Check
on: [pull_request]

jobs:
  arbor:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - uses: Anandb71/arbor@v2.4.0
        with:
          command: check . --max-blast-radius 30 --markdown
          comment-on-pr: true
          github-token: ${{ secrets.GITHUB_TOKEN }}

Architecture

code

arbor-core (Tree-sitter parsing)
    └── arbor-graph (petgraph + PageRank + impact analysis)
            ├── arbor-cli      — CLI + MCP bridge
            ├── arbor-mcp      — MCP protocol server
            ├── arbor-server   — WebSocket JSON-RPC
            ├── arbor-watcher  — incremental file watcher
            └── arbor-gui      — desktop UI

Docs: Quickstart · Architecture · Graph schema · MCP integration · Benchmarks · Roadmap · Philosophy

Release channels: GitHub Releases · crates.io · GHCR · npm · VS Code / Open VSX · Homebrew · Scoop — Releasing guide

Philosophy

Consumer first — beautiful, intuitive, instantly useful
Accessibility second — works across ecosystems, runs anywhere
Affordability next — minimal overhead, from laptops to monoliths

Arbor is local-first: no mandatory data exfiltration, offline-capable, open source. Security policy →

Contributing

bash

cargo build --workspace
cargo test --workspace
cargo clippy --workspace --all-targets --all-features

CONTRIBUTING.md · Good first issues · Code of conduct

Contributors

<a href="https://github.com/Anandb71" title="Anandb71" style="text-decoration:none; margin:6px; display:inline-block;"> <img src="https://avatars.githubusercontent.com/u/169837340?v=4" alt="Anandb71" width="72" height="72" loading="lazy" style="border-radius:50%; border:2px solid #30363d; box-sizing:border-box;" /> </a> <a href="https://github.com/holg" title="holg" style="text-decoration:none; margin:6px; display:inline-block;"> <img src="https://avatars.githubusercontent.com/u/1383439?v=4" alt="holg" width="72" height="72" loading="lazy" style="border-radius:50%; border:2px solid #30363d; box-sizing:border-box;" /> </a> <a href="https://github.com/cabinlab" title="cabinlab" style="text-decoration:none; margin:6px; display:inline-block;"> <img src="https://avatars.githubusercontent.com/u/66889299?v=4" alt="cabinlab" width="72" height="72" loading="lazy" style="border-radius:50%; border:2px solid #30363d; box-sizing:border-box;" /> </a> <a href="https://github.com/Karthiksenthilkumar1" title="Karthiksenthilkumar1" style="text-decoration:none; margin:6px; display:inline-block;"> <img src="https://avatars.githubusercontent.com/u/182195883?v=4" alt="Karthiksenthilkumar1" width="72" height="72" loading="lazy" style="border-radius:50%; border:2px solid #30363d; box-sizing:border-box;" /> </a> <a href="https://github.com/zacwolfe" title="zacwolfe" style="text-decoration:none; margin:6px; display:inline-block;"> <img src="https://avatars.githubusercontent.com/u/2164736?v=4" alt="zacwolfe" width="72" height="72" loading="lazy" style="border-radius:50%; border:2px solid #30363d; box-sizing:border-box;" /> </a> <a href="https://github.com/sanjayy-j" title="sanjayy-j" style="text-decoration:none; margin:6px; display:inline-block;"> <img src="https://avatars.githubusercontent.com/u/178475117?v=4" alt="sanjayy-j" width="72" height="72" loading="lazy" style="border-radius:50%; border:2px solid #30363d; box-sizing:border-box;" /> </a> <a href="https://github.com/sathguru07" title="sathguru07" style="text-decoration:none; margin:6px; display:inline-block;"> <img src="https://avatars.githubusercontent.com/u/182798669?v=4" alt="sathguru07" width="72" height="72" loading="lazy" style="border-radius:50%; border:2px solid #30363d; box-sizing:border-box;" /> </a> 7 contributors | <a href="https://github.com/Anandb71/arbor/graphs/contributors">View all</a>

License

MIT — see LICENSE.

常见问题