plumb

[![CI](https://github.com/plumbkit/plumb/actions/workflows/ci.yml/badge.svg)](https://github.com/plumbkit/plumb/actions/workflows/ci.yml)
[![Go Reference](https://pkg.go.dev/badge/github.com/plumbkit/plumb.svg)](https://pkg.go.dev/github.com/plumbkit/plumb)
[![Go Report Card](https://goreportcard.com/badge/github.com/plumbkit/plumb)](https://goreportcard.com/report/github.com/plumbkit/plumb)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

<picture>
  <source media="(prefers-color-scheme: dark)" srcset="site/logo-dark.svg">
  <img alt="plumb" src="site/logo-light.svg" width="220">
</picture>

<br>

**IDE intelligence for agents — guardrails for unattended work, coordination for fleets.**

Plumb is an [MCP](https://modelcontextprotocol.io) server that gives a coding agent the intelligence layer of an IDE — [LSP](https://microsoft.github.io/language-server-protocol/)-backed semantics, a [tree-sitter](https://tree-sitter.github.io/tree-sitter/) code index, and project memory — inside guardrails: atomic, lock-serialised writes with transactional rollback, scoped filesystem and git access, and a daemon that survives its own crashes. And because every agent you run shares that one daemon, plumb is also the coordination layer between them: peers see the writes others made, message each other, and hand off work instead of duplicating it. A single binary; nothing else to install.

---

## Why Plumb

LLM agents usually work by reading whole files into the context window — token-heavy, lossy at scale, blind to symbol semantics, and unsafe to let loose on a real repo. Plumb is built on four pillars, in priority order.

### 1. Reliability & write-safety
Leaving an agent to edit a codebase for an hour is only viable if writes can't corrupt files and a crash can't wedge your session.

- **Atomic I/O** — every write is staged in a temp file and renamed into place. No partial writes, ever. Symlink-aware, CRLF-tolerant.
- **Per-path locking** — the daemon serialises concurrent writes to the same file across every session and chat window. No races.
- **Multi-file transactions** — apply edits across dozens of files with guaranteed atomic rollback if any step fails.
- **Crash-resilient daemon** — `plumb serve` is a reconnecting proxy. If the daemon crashes or hangs, it respawns one and replays the handshake; the agent never notices. In-flight writes are never silently re-run.
- **Optimistic concurrency** — mtime/sha guards catch stale edits before they clobber newer changes.

See it run: [`docs/demos/`](docs/demos/) — `two-agents-one-file.sh` (a stale write is refused, nothing is lost) and `daemon-respawn.sh` (below — the daemon is killed mid-session; the agent's next edit still succeeds):

![daemon-respawn.sh: the daemon is killed mid-session and the agent's next edit still succeeds](docs/assets/daemon-respawn.gif)

### 2. Multi-agent coordination
One daemon serves every agent you run — which makes it the natural place for agents to *see and talk to* each other, not merely avoid each other's writes. Locks stop two agents corrupting a file; coordination stops them duplicating a task, rebasing onto a function signature a peer is mid-rewrite of, or shipping a change a peer's in-flight work is about to invalidate.

- **Peer awareness** (on by default) — `workspace_sessions` names every active session and the writes it made, as the daemon recorded them. Recorded activity, not another agent's say-so: an agent about to start a task can see that a peer is already in those files. (Read-only operations never appear, and a write that failed or was refused is kept but marked `[failed — no change applied]` — so "a peer is working here" and "this landed" are distinguishable at a glance.)
- **An agent-to-agent mailbox** (on by default, same workspace) — `leave_note` / `check_messages` give sessions a threaded channel: hand a change to the peer already rewriting those files, or ask a peer to *measure* a behaviour instead of assuming it. Messages ride on ordinary tool results, so a working agent receives them without polling.
- **Advisory intents** (opt-in: `[collab] intents`) — `share_intent` declares what an agent is working on; a peer whose write touches a claimed path gets a hint at the moment of the would-be collision. Intents are deliberately labelled as unverified claims, kept distinct from the daemon-recorded activity feed, and never block anything.
- **Durable findings** (opt-in: `[collab] knowledge_handoff`) — `share_findings` turns what an agent just learned into a searchable, secret-scrubbed project memory immediately, so the knowledge outlives the session that produced it.

Coordination is advisory by design — the write-safety above never depends on agents cooperating. Reference: [Cross-agent sharing](docs/tools.md#cross-agent-sharing-collab) in the tool docs and the [`[collab]` config section](docs/configuration.md#collab--cross-agent-sharing).

### 3. Semantic intelligence
The same primitives your editor has, exposed as structured tools:

- **LSP-backed refactors** — `rename_symbol`, `replace_symbol_body`, `safe_delete_symbol` understand scope, types, and references.
- **Real diagnostics inline** — actual `gopls`/`pyright` output is appended to every write, so the agent learns it broke the build immediately.
- **Symbol search** — scoped to your code, no stdlib or dependency noise.

### 4. Context efficiency & safety controls
- **Read only what you need** — symbols or line ranges, not 2,000-line files.
- **Scoped access you control** — a per-connection path allowlist (read-only vs read-write roots) plus tiered git gating (destructive and network operations are off by default and need explicit confirmation). See [SECURITY.md](SECURITY.md).
- **One-round-trip bootstrap** — `session_start` returns workspace, branch, recent commits, diagnostics, and project memory.

See the measured, reproducible numbers behind this: [**docs/use-cases.md**](docs/use-cases.md) — reading one function is 2.9×–33.4× less context than the whole file (the ratio is how much of the file you didn't need), and `find_references` returns the real call sites where a text search is 60% noise. The page publishes the losses too: `read_multiple_files` costs 1.31× **more** payload than reading the files natively (down from 1.32×, but still a loss — see Scenario 10 for why it isn't smaller). Every figure is regenerated by [`scripts/measure-use-cases.py`](scripts/measure-use-cases.py).

---

## Get started

Plumb is a single binary — from zero to your first answer:

**1. Install**

```sh
# Homebrew (macOS + Linux) — recommended
brew install plumbkit/plumb/plumb

# or with Go
go install github.com/plumbkit/plumb/cmd/plumb@latest

# or grab a prebuilt binary: https://github.com/plumbkit/plumb/releases
```

> **macOS note:** prebuilt binaries are not yet notarised — on first run you may
> need `xattr -d com.apple.quarantine ./plumb`, or right-click → Open. Homebrew
> installs avoid this.

**2. Connect your agent**

```sh
plumb setup claude-code      # also: claude-desktop, codex, gemini, cursor, …
```

`plumb setup` writes the MCP config for you — no hand-editing JSON.

**3. Open your project and try it**

Make sure the language server you need is on your `$PATH` (`gopls` for Go,
`pyright` for Python, …), then point your agent at a real question. In Claude
Code:

```sh
cd your/project
claude "Use plumb to orient in this repo (session_start), then show me
everywhere <Handler> is called and what would break if I changed its signature."
```

Plumb resolves the workspace and runs `session_start` for orientation, then
answers with real LSP and topology data — actual call sites and blast radius —
instead of guessing from file dumps. It's read-only; nothing is modified. (Any
connected agent works — just paste the prompt.)

> No `go.mod`/`pyproject.toml` and not a git repo? Run `plumb init` once to pin
> the workspace root (it also seeds `.plumb/context.md` and project config).

Full walkthrough → [**docs/getting-started.md**](docs/getting-started.md).

---

## Language support (honest version)

Plumb negotiates LSP capabilities per language and also ships a built-in tree-sitter index for search and navigation with no language server. Support comes in tiers — we'd rather be precise than claim a big number.

| Tier | Languages | What you get |
|---|---|---|
| **First-class** (CI-tested, real-binary integration) | **Go** (gopls), **Python** (pyright) | Full LSP: definitions, references, rename, diagnostics, hierarchies + all write tools |
| **Validated** | **Java** (jdtls), **Rust** (rust-analyzer), **Swift** (sourcekit-lsp), **TypeScript/JS** (typescript-language-server), **Zig** (zls), **Kotlin** (kotlin-lsp), **HTML** (vscode-html-language-server) | Full LSP; just put the server on `$PATH` and it activates automatically (exclude any language with `[lsp.<lang>] enabled = false`). HTML carries one caveat: that server has no filesystem access, so it answers only from documents already opened |
| **Search & navigation** (tree-sitter, no LSP needed) | 31+ incl. JS/TS/TSX, Ruby, C, C#, Elixir, Scala, PHP, JSON, CSS, SCSS, XML, Lua, C++, Objective-C, Dart, Bash, SQL, HCL, Dockerfile, TOML, YAML, Markdown | Ranked symbol search, outlines, graph exploration via the Topology index |

Real-binary validation has been exercised on **macOS and Linux** — as of 2026-08-21, all nine adapters pass their integration tests against real server binaries on both. Details, including three toolchain traps that look like adapter bugs, are in [docs/adding-an-lsp.md](docs/adding-an-lsp.md#validation-levels). Windows is [tracked but not yet supported](https://github.com/plumbkit/plumb/issues/8) — the daemon's Unix-socket architecture needs a port.

---

## How it works

`plumb serve` is a thin, reconnecting stdio proxy. The real work happens in one shared background daemon, so language servers stay warm across chats.

```mermaid
flowchart TD
    A1["C