Arbor

Graph-native intelligence for codebases.
Know what breaks before you break it.

_{Simulated replay — the arbor commands and their output are real (tokio @ 178k LOC). Methodology: BENCHMARKS.md}

v2.6.0 — Ground Truth · The graph was wrong in ways v2.5.0 made fast. Colliding symbols were silently dropped, resolution depended on hash order, every edge claimed certainty, and every exported TypeScript symbol was indexed twice. All fixed, all tested. Edge recall +14% on TypeScript, +44% on Rust; 25% of a TS graph was phantom nodes. Reproduce it yourself: cargo run -p arbor-watcher --example graph_stats -- <dir>

---

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:

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

Where the graph is unsure, it says so — edges carry a confidence, and ambiguous resolutions are labelled rather than hidden. An honest unknown beats a confident wrong answer.

---

What's new in v2.6.0

Correctness, not speed. Each of these was silently wrong before.

New capability — concept search. Substring matching cannot find get_authenticated from login; they share no substring. Identifiers are now tokenized and expanded through curated concept clusters, and docstrings, signatures, and paths are indexed alongside names. Deterministic, offline, no model. Available on the library as ArborGraph::search_ranked (arbor query remains literal-substring for now).

New capability — hunk-level impact. changed_node_ids_for_ranges keeps only symbols whose lines actually changed, instead of every symbol in a touched file.

Measured on identical node sets, after the duplicate-extraction fix:

Graph caches from earlier versions are invalidated — centrality now means something different, so a stale cache would be read wrong.

v2.5.0 — The Last Excuse (PageRank 23x, parallel indexing, warm-start centrality)

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

Think a number is wrong? cargo bench -p arbor-graph and prove it: BENCHMARKS.md.

v2.4.0 — The Agent-Native Leap (MCP 2026-07-28, HTTP transport, Tasks, MCP Apps)

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

---

Quickstart

# 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.

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

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

Cursor / VS Code

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

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

16 MCP tools

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

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

# 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

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

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

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

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

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

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

---

Contributing

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

CONTRIBUTING.md · Good first issues · Code of conduct

---

Contributors

_{7 contributors | View all}

---

License

MIT — see LICENSE.