Skip to content
MCP server

Lockstep AI

Shared team memory for Claude Code: approved decisions, standards and skills

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, self-hosted
Runs
Locally
Version
0.4.0
Listing updated
3 days ago

About Lockstep AI

Lockstep AI is an open-source MCP server for knowledge and memory. It runs locally on your machine and is started by your AI client.

Lockstep treats a team decision as something with an owner, evidence and a version. It collects candidate decisions from PRDs, Slack, Jira and pull requests, but AI drafts never bind themselves: the named owner confirms them. New versions replace old ones without erasing them.

At the start of a Claude Code session the CLI briefs the agent on the approved rules that apply to the work, including why each exists and what was rejected. An opt-in check flags pull requests that may conflict with a binding decision and shows affected teams. From any change you can trace back to the originating request, evidence, owner and approval.

The npm CLI is installed globally and run with lockstep login, onboard and status; onboarding wires hooks and MCP for your agent. Self-hosting is documented, under Apache-2.0 with docker compose.

Install

Run in a terminal

claude mcp add lockstep -- npx -y lockstep-cli

Add to claude_desktop_config.json

{
  "mcpServers": {
    "lockstep": {
      "command": "npx",
      "args": [
        "-y",
        "lockstep-cli"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "lockstep": {
      "command": "npx",
      "args": [
        "-y",
        "lockstep-cli"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "lockstep": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "lockstep-cli"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "lockstep": {
      "command": "npx",
      "args": [
        "-y",
        "lockstep-cli"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "lockstep": {
      "command": "npx",
      "args": [
        "-y",
        "lockstep-cli"
      ]
    }
  }
}

Configuration

  • LOCKSTEP_VENDORAgent vendor label used for session registration (e.g. claude-code, cursor). Optional; defaults to unknown.

What it does

Owned decisions
Each rule has a named owner and attached evidence.
Session briefing
Claude Code sessions start with relevant approved rules.
Conflict checks
An opt-in check flags pull requests against binding decisions.
Version history
Replaced calls stay visible.
Standards rollout
Distributes team standards and skills.
Self-hostable
Apache-2.0 with a docker compose setup.

Good for

  • Make a new engineer's agent follow the team's current checkout rules
  • Trace a code change back to the PRD sentence behind it
  • Catch a pull request that contradicts an approved decision
  • See which sessions received which decisions

Pricing

Open source

Apache-2.0 and self-hostable; hosted prices not published

Prices change. Check getlockstep.dev before you buy.

Lockstep AI FAQ

Which agents does it work with?

It targets Claude Code, and the README says any MCP client can call the same tools.

How do I install it?

npm install -g lockstep-cli, then lockstep login and lockstep onboard.

Can AI decide for the team?

No. AI drafts do not bind until the owner approves.

Can I self-host?

Yes, under Apache-2.0 with docker compose.

Is Lockstep AI free?

Yes. Lockstep AI is open source, so you can use and self-host it for free.

How do I add Lockstep AI to Claude Code?

Run this command in your terminal: claude mcp add lockstep -- npx -y lockstep-cli

What are the best alternatives to Lockstep AI?

The closest alternatives to Lockstep AI are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Lockstep AI

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools