Activate Project Intelligence for your repo

Run one command from your repo, choose Claude Code, Codex, Cursor, VS Code, Gemini CLI, Mistral, ChatGPT Desktop, or any MCP client, then start with a briefed agent instead of a blank agent.

create-snipara scans the local workspace and writes the First Work Brief.

Editor surfaces expose the right entry point and handoff, not a second engine.

Companion continues the work with source sync, session-bootstrap, impact, and commits.

npx create-snipara@latest init --client vscode --starter --json

.snipara/activation/activation-manifest.json

.snipara/activation/first-brief.md

.snipara/activation/handoff.md

npx create-snipara

Connected to Snipara

AI client configured

Repository analyzed

Context index started

Code Graph indexing started

Memory candidates ready for review

First Work Brief generated

npx create-snipara --starter

npx create-snipara demo

npx -y snipara-companion@latest automations install --client claude-code

npx -y snipara-companion@latest automations diff

npx -y snipara-companion@latest automations update

npx -y snipara-companion@latest automations status

Interactive Setup

Run npx create-snipara in your project directory. The default flow uses the recommended hosted-companion profile and asks only for the local choices needed to connect this repo.

Use --advanced only when you want profile selection, project IDs, hooks, GitHub prompts, orchestrator opt-in, or Snipara Sandbox provider prompts. Use --profile hosted-only or --skip-companion for minimal locked-down installs.

snipara-companion session-bootstrap --include-session-context --max-context-tokens 1000

snipara-companion status

snipara-companion source init .

snipara-companion source sync --json

snipara-companion brief --task "ship auth hardening"

snipara-companion code impact --changed-files src/auth.ts --diff-summary "auth hardening"

snipara-companion memory supersede mem_old mem_new --reason "corrected decision"

snipara-companion workflow phase-commit build --summary "tests green"

snipara-companion handoff --summary "ready for release checks"

snipara-companion workflow resume --include-session-context

Browser Approval

create-snipara uses the terminal for local setup and the browser for identity or source approval.

• The terminal writes config, doctor reports, hooks, and local project wiring.
• The browser handles Snipara login and GitHub approval.
• Local source activation does not need provider approval; it writes local snapshots and overlay caches from the current folder.
• GitHub approval stays in the browser because the user must explicitly choose which account, organization, and repositories Snipara can read.

That keeps repository sync explicit and revocable. The Hosted MCP server is for agent usage after setup, not for the initial source-permission choice.

Choose Sources

Local folder first

Use snipara-companion source init . immediately after setup when the user has not installed the GitHub App, when the folder has no Git metadata, or when they want a private local fallback. It creates .snipara/source/latest.json, previews supported document sync, and refreshes the local code overlay. Add source sync --json to refresh that state after file changes.

GitHub repository

Use npx create-snipara --github when the current folder is a GitHub repo and the team wants canonical hosted repository sync, shared CODE graph freshness, and PR Answer Packs. The CLI detects the repo and opens the Snipara GitHub App flow with repo, branch, and optional path filter already carried through.

GitLab repository

For GitLab repositories, connect GitLab from the dashboard, choose the repository, branch, and path filter, then enable repository sync. Push webhooks refresh docs and CODE graph files, while merge request events queue MR Answer Packs and publish ready packs back to a sticky GitLab merge request note.

Business workflows

Use Helvabase when the user wants to work from local folders, mounted Drive or SharePoint exports, old offers, PowerPoints, templates, or RFP files. Snipara source is for local project activation; Helvabase is for controlled business dossier workflows.

Maintenance Commands

npx create-snipara doctor

npx create-snipara repair

npx create-snipara repair --with-orchestrator

Execution Environments

When you select Snipara Sandbox during setup, you'll be asked if you want to run snipara-sandbox init to configure the execution environment:

You can also configure the environment later by running snipara-sandbox init manually.

API Key Requirements

API Keys

Command Line Options

Basic usage

npx create-snipara

With existing API key

npx create-snipara --api-key snp-your-key

Specify project slug

npx create-snipara --slug my-project

Starter activation mode

npx create-snipara --starter

Open the guided activation demo without changing this repo

npx create-snipara demo

npx create-snipara demo --no-open

Advanced prompts for profiles, hooks, GitHub, and Snipara Sandbox

npx create-snipara --advanced

Snipara Sandbox only - no Snipara API key needed

npx create-snipara --runtime-only

Open GitHub automation for the detected repo

npx create-snipara --github

npx create-snipara --github-path docs/

Skip local companion CLI

npx create-snipara --skip-companion

Skip specific installations

npx create-snipara --skip-mcp # Skip local snipara-mcp package

npx create-snipara --skip-runtime # Skip snipara-sandbox

npx create-snipara --skip-hooks # Skip local hooks

npx create-snipara --skip-test # Skip connection test

npx create-snipara --skip-github # Skip GitHub automation prompt

Accept all defaults (non-interactive)

npx create-snipara -y --api-key snp-xxx --slug my-project

What Gets Created

.mcp.json

{

  "mcpServers": {

    "snipara": {

      "type": "http",

      "url": "https://api.snipara.com/mcp/your-project",

      "headers": {

        "X-API-Key": "snp-your-key"

      }

    },

    "snipara-sandbox": {

      "type": "http",

      "url": "http://localhost:8765/mcp",

      "headers": {}

    }

  }

}

Claude Code Hooks (if selected)

• snipara-startup.sh - Restores session context
• snipara-session.sh, auto-remembers commits
• snipara-compact.sh, saves context before compaction

Local Companion Pack

create-snipara also generates a small project-local starter pack under .snipara/companion. The default hosted-companion mode uses it for managed workflow commands; hosted-only keeps the same pack as an upgrade path.

• README.md - client-aware usage guidance and starter commands
• commands.json - machine-readable command presets for local workflows

Companion Workflows

The companion CLI is a thin local facade over hosted Snipara workflows. It is useful when you want repeatable local commands in addition to MCP access.

snipara-companion query --query "how does auth middleware work?"

snipara-companion shared-context --categories MANDATORY BEST_PRACTICES

snipara-companion plan --query "implement webhook retry hardening"

snipara-companion multi-query --queries "recent incidents" "rate limit headers"

snipara-companion orchestrate --query "map auth architecture"

snipara-companion load-document --path docs/architecture/auth.md

snipara-companion recall --query "What did we decide about auth retries?" --type decision

snipara-companion events recent --limit 20

snipara-companion session-bootstrap --include-session-context --max-context-tokens 1000

snipara-companion task-commit --summary "Shipped retry hardening"

These commands print human-readable output by default. Add --json when you need the raw hosted response.

Environment Files

Updates .env.example and .env.local with:

Snipara Configuration

SNIPARA_API_KEY=your_api_key

SNIPARA_PROJECT_SLUG=your-project

Snipara Sandbox LLM Provider (if configured)

OPENAI_API_KEY=sk-...

or

ANTHROPIC_API_KEY=sk-ant-...

After Installation

For Claude Code / Cursor

1. Claude Code loads MCP from the generated project .mcp.json; .claude/settings.json is used only when hooks are enabled. Cursor uses the generated project MCP config and rule files.
2. Restart your AI client or open a new agent session.
3. Confirm Snipara appears in MCP settings or ToolSearch. If not, run npx create-snipara doctor --client claude-code.

For Claude Desktop

1. Restart Claude Desktop
2. Config is at ~/Library/Application Support/Claude/claude_desktop_config.json

Business Folder Onboarding

For dashboardless business-context imports, let Claude, ChatGPT, Codex, or another LLM client use its own Drive, Gmail, Notion, or local-file access to materialize a folder, then use snipara-companion to preview and apply the import.

snipara-companion onboard-folder ./client-export --source-provider local_folder --write-manifest ./snipara-onboard.json

snipara-companion onboard-folder ./client-export --source-provider local_folder --apply

onboard-folder classifies folders as business, code, mixed, or unknown, but it is business-first. If it detects a source-code repository, use the GitHub or GitLab onboarding path instead.

GitHub Repository Automation

When create-snipara detects a GitHub remote, it can open the Snipara GitHub App flow with owner/repo, branch, and optional path filter already carried through. The browser flow installs or updates the GitHub App, lets the user connect the detected repository, creates or reuses the matching Snipara project, enables push sync, and starts the first documentation sync.

GitLab Repository Automation

GitLab automation is configured from the dashboard rather than the --github CLI flag. Connect the GitLab account, select the project, enable sync, and keep the managed webhook active. Snipara then treats GitLab pushes and merge requests as first-class repository evidence for docs, CODE graph freshness, and MR Answer Packs.

npx create-snipara --github

npx create-snipara --github-path docs/

If you intentionally started with hosted-only, enable companion before using business-folder imports:

npx create-snipara repair --with-companion

Snipara Sandbox Usage

MCP Tools (no LLM API key needed):

Your AI client (Claude, GPT, etc.) provides the LLM, no additional API key required.

CLI Commands (requires LLM API key):

For snipara-sandbox run and snipara-sandbox agent, you need an LLM provider API key:

Set your LLM provider

export OPENAI_API_KEY=sk-...

or

export ANTHROPIC_API_KEY=sk-ant-...

Run commands

snipara-sandbox init # Initialize configuration

snipara-sandbox run --env docker # Run with Docker isolation

snipara-sandbox agent "task" # Autonomous agent mode

snipara-sandbox visualize # Launch trajectory dashboard

Available MCP Tools

If you enable hook-compatible local tooling, the install can also forward canonical lifecycle events into Snipara's automation API. That lets local adapters feel closer to a local-memory workflow while keeping review and persistence centralized.

After setup, you have access to the current 128-tool MCP contract across context, memory, automation, analytics, and orchestration:

Requirements

• Node.js 18+
• Python 3.10+ (for snipara-mcp and snipara-sandbox)
• Docker (optional, for Snipara Sandbox isolation)

Links

Next Steps