Align CLI

Your AI agents know the code. They don't know the company.

The decisions behind the code live in commits, tickets, chat and meetings. Months later nobody can tell what still stands, what conflicts, or why. Align pulls them into one graph your agents check before they build.

Terminal

curl -fsSL https://align.tech/install.sh | sh
align

That is the whole thing. align sets itself up the first time you run it and asks whether you want it local-only or synced; after that it shows your graph and what to do next.

A standalone binary. No Node, no npm, nothing else to install, and local-only mode works fully - on-device embeddings included, running on a WASM backend bundled inside the binary. Linux, macOS and Windows, x64 and arm64, glibc and musl. Verified against the release's own checksums, and you can read install.sh before you pipe it anywhere.

Prefer npm, or already have Node? npm install -g @aligndottech/cli (Node 22.16+). Binaries for every platform are on the releases page.

MIT. No account needed. Beta, pre-1.0.

Run it inside a git repository. --local seeds the graph from your commit history, so you have something to ask about straight away, and your decisions stay in a SQLite file on your machine. Nothing is sent to Align. What touches the network.

Want sync across machines and cross-tool relationship detection? Drop the flag. align setup logs you in, connects your tools via read-only OAuth, and wires up your editors.

How it works

server.ts

  Your tools                      Align                       Your agents & you
  ──────────                   ───────────                  ───────────────────
  Git, GitHub, GitLab  ─┐                                  ┌─ align ask "why…"
  Jira, Confluence      ├─▶  import  ─▶  decision graph ─┐ ├─ MCP server (inline)
  Linear, Notion        │    (read-only) (what/why/who)  ├─┤  edit hooks (any agent)
  Slack, Teams, Zoom   ─┘                  + relationships┘ └─ align check (CI)

Import pulls decisions out of the tools you already use. Read-only, nothing is modified.
Align links them into a decision graph: what was decided, why, who decided it, and how decisions relate (supersedes, conflicts with, depends on).
Your agents query and check against it, over MCP, an edit hook, CI, or align ask.

Your agent checks before it writes

align setup wires Align in four ways, so context fires whether or not the model thinks to ask.

	What you get
MCP server	Claude Code, Cursor, Claude Desktop and Windsurf query the graph inline
Edit hooks	Prior decisions reach the model before it writes. Claude Code, pi, Gemini CLI, OpenCode
Editor rules	A managed block in `CLAUDE.md`, `AGENTS.md` and `.cursor/rules/align.md`
Shared `.mcp.json`	One committed file wires up the whole team

The hook is non-blocking and fail-open. It never denies an edit by default, and if Align is missing, slow or unreachable the edit proceeds untouched. It needs no AI provider key.

Cursor and Codex CLI can't do the pre-edit hook, and that's a limit of those hosts. They get the other three. Full per-host matrix: docs/agent-hooks.md.

The first time Claude Code loads a project with a committed hook, it shows a one-time "approve hooks" prompt. Accept it to enable automatic alignment.

Everyday commands

server.ts

align ask "how does our auth work"   # natural language answer with sources
align search "authentication"        # ranked list, no AI needed
align ask src/auth/session.ts        # a file path finds decisions about that file
align import git                     # pull commit history, no token
align import docs                    # pull ADRs + your CLAUDE.md/AGENTS.md, no token
align import jira --token ...        # add more sources
align capture <url>                  # capture one decision from a PR, ticket or thread
align check                          # check your staged diff against the graph
align context sync                   # write decisions to .align/decisions.md
align ratify <id>                     # stand behind an agent-made decision, as a human
align push <id>                       # send one ratified local decision to the shared graph

align ask needs an AI provider to write prose. Without one it returns the matching decisions as a ranked list, which needs no key. Bring your own: Anthropic, OpenAI, Gemini, Groq, Mistral, Grok, any OpenAI-compatible endpoint, or a local Ollama. Setting one up.

Docs


Importing	Every source, tokens, flags
Alignment check	Modes, exit codes, CI, the GitHub Action
Cloud or local-only	What runs where, what touches the network
MCP server	Editor config, the tools your assistant gets
Configuration	AI providers, env vars, auth, self-hosting
Agent hooks	Per-host capability matrix
All commands	Full reference

Why bother

In a published benchmark, giving a coding agent recorded product decisions took decision compliance from 46% to 95% (Dillon & Varanasi, arXiv:2605.08112 - a small vendor study, 8 tasks and 41 decision points, and it isn't our data).

Wiring context into an agent is the easy part, and this repo is the open-source version of it. The hard part is the record underneath: what your team actually decided, across every tool, kept current.

Want a hand setting it up? I do free 30 minute setup calls: https://calendly.com/tom-align/setup

License

MIT, see LICENSE. The CLI and MCP server are open source, along with the connector SDK. The hosted gateway is a separate commercial service.