ContextEngine

Persistent memory and mechanical enforcement for AI coding agents — so they stop repeating your mistakes.

ContextEngine indexes your copilot-instructions.md, SKILLS.md, CLAUDE.md, runbooks, and source code — then exposes it via the Model Context Protocol so AI coding assistants (GitHub Copilot, Claude, Cursor, Windsurf, OpenClaw) can search your accumulated knowledge in real time.

Why

AI coding agents are powerful — but they forget everything between sessions. They repeat mistakes you've already solved, skip commit discipline, and ignore the docs they wrote yesterday.

ContextEngine solves this with three layers:

1. Persistent memory — learnings saved once auto-surface in future sessions. "Never use bare node in mcp.json" gets saved once and recalled forever.

2. Mechanical enforcement — pre-commit hooks and Protocol Firewall ensure agents commit, document, and follow protocol. Not by asking nicely — by blocking.

3. Structural checklist — scoring motivates CI, tests, Docker, and docs. It validates content quality (not just file existence) — but treat the score as scaffolding, not a quality metric.

Think of it as guardrails and muscle memory for your AI agents — practical structure while we wait for these agents to become smarter.

ContextEngine fixes the biggest gap: zero-config, fully local, privacy-first.

• 🔍 Hybrid Search — keyword + semantic (vector embeddings) across all your docs

• 🧠 Semantic Search — all-MiniLM-L6-v2 runs locally on CPU (no API keys)

• 📁 Auto-discover — finds copilot-instructions.md, CLAUDE.md, .cursorrules, AGENTS.md across all projects

• 💻 Code Parsing — extracts functions, classes, interfaces from TS/JS/Python source files

• ⚙️ Operational Intelligence — collects git, Docker, PM2, nginx, cron, package.json data

• 🔒 Local-only — nothing leaves your machine

• ⚡ Instant startup — keyword search ready immediately, embeddings load in background

• 💾 Session Persistence — AI agents can save/restore context across conversations

• 💡 Learning Store — permanent operational rules that auto-surface in search results

• �️ Protocol Firewall — progressive enforcement that ensures agents commit, document, and save learnings

• �🔌 Plugin Adapters — extend with custom data sources (Notion, Jira, RSS, etc.)

• 🧩 MCP native — works with any MCP-compatible client (VS Code, Claude, Cursor, OpenClaw)

What ContextEngine is NOT

• Not a code quality tool — it checks project structure (CI, tests, Docker, docs) and validates content depth, but won't tell you if your code is good. An A+ score means "well-organized for AI agents," not "production-ready."

• Not required for day-to-day agent work — agents read copilot-instructions.md natively. CE adds value when you have many projects, hundreds of learnings, or need cross-session memory.

• Not worth chasing 100% — invest time in your PIPELINES.md and SKILLS docs instead of score-chasing. Those prevent costly mistakes; the score keeps you honest.

Quick Start

1. Scaffold config (optional)

npx @compr/contextengine-mcp init

Detects your project type, creates contextengine.json + .github/copilot-instructions.md template.

2. Add to your MCP client

VS Code (recommended — per-project setup)

Create .vscode/mcp.json in your project root:

{
  "servers": {
    "contextengine": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@compr/contextengine-mcp"]
    }
  }
}

This activates ContextEngine when the workspace is open. Add this file to each project that needs it.

Note: VS Code deprecated MCP configuration in user settings.json. Use .vscode/mcp.json per workspace instead.

Claude Desktop — add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "ContextEngine": {
      "command": "npx",
      "args": ["-y", "@compr/contextengine-mcp"]
    }
  }
}

Cursor — add to MCP settings:

{
  "mcpServers": {
    "ContextEngine": {
      "command": "npx",
      "args": ["-y", "@compr/contextengine-mcp"]
    }
  }
}

OpenClaw — add ContextEngine as an MCP server in your OpenClaw config, or use the bundled skill:

# Option 1: Copy the skill to your OpenClaw workspace
cp -r node_modules/@compr/contextengine-mcp/skills/contextengine ~/.openclaw/workspace/skills/

# Option 2: Add as MCP server in openclaw.json

{
  "mcpServers": {
    "contextengine": {
      "command": "npx",
      "args": ["-y", "@compr/contextengine-mcp"],
      "env": { "CONTEXTENGINE_WORKSPACES": "~/Projects" }
    }
  }
}

3. Pin your config (recommended)

If you have a contextengine.json with custom sources, add this to your shell profile (~/.zshrc or ~/.bashrc):

export CONTEXTENGINE_CONFIG="$HOME/path/to/contextengine.json"

Without this, ContextEngine falls back to auto-discovery (finds copilot-instructions.md etc.) but won't load your explicit sources, code dirs, or custom patterns.

That's it. ContextEngine auto-discovers your docs in ~/Projects.

📦 VS Code Extension

ContextEngine has a free VS Code extension that provides proactive enforcement — no MCP setup required:

• 📊 Value meter — shows what ContextEngine saved you this session: learnings recalled, learnings saved, estimated time saved. Falls back to git status when no MCP session is active

• 📈 Live stats dashboard — click ℹ️ to see real-time session metrics (tool calls, recalls, nudges, truncations, time saved)

• @contextengine chat — /status, /commit, /search, /remind, /sync in Copilot Chat

• Escalating notifications — warns when files accumulate without commits

• Terminal watcher — monitors commands with smart classification (git, deploy, database, python, build, test), credential redaction in logs, and stuck-pattern detection (alerts after 3+ consecutive failures)

• One-click commit — commit all changes across all repos

The extension reads live metrics from the MCP server (via ~/.contextengine/session-stats.json). For search, learnings, sessions, and scoring — it uses the MCP server (npx @compr/contextengine-mcp).

⭐ PRO Features

ContextEngine is free and open-core. The free tier covers everything agents need — search, memory, sessions, and compliance enforcement. PRO adds team and ops intelligence across multiple projects:

Pricing

→ Get PRO · Annual plans save 17%

# Activate after purchase
npx @compr/contextengine-mcp activate

CLI Usage (no MCP required)

ContextEngine also works as a standalone CLI tool — no MCP client setup needed:

# Search across all your project knowledge
npx @compr/contextengine-mcp search "docker nginx"
npx @compr/contextengine-mcp search "rate limiting" -n 10

# List all indexed sources
npx @compr/contextengine-mcp list-sources

# Discover and analyze all projects
npx @compr/contextengine-mcp list-projects

# AI-readiness score (one or all projects)
npx @compr/contextengine-mcp score
npx @compr/contextengine-mcp score ContextEngine

# Visual HTML report (opens in browser)
npx @compr/contextengine-mcp score --html
npx @compr/contextengine-mcp score ContextEngine --html

# List permanent learnings (optionally by category)
npx @compr/contextengine-mcp list-learnings
npx @compr/contextengine-mcp list-learnings security

# Show live MCP session stats (value meter)
npx @compr/contextengine-mcp stats

# Run compliance audit across all projects
npx @compr/contextengine-mcp audit

# Scaffold config for a new project
npx @compr/contextengine-mcp init

# Show all commands
npx @compr/contextengine-mcp help

CLI mode uses keyword search (BM25) which is instant — no model loading required.

Tools (19)

All tools are wrapped by the Protocol Firewall — a built-in enforcement layer that ensures agents save learnings, persist sessions, and commit code. No action needed from users; it's automatic.

Configuration

ContextEngine works zero-config — it auto-discovers documentation files in ~/Projects.

For full control, create a contextengine.json:

{
  "sources": [
    { "name": "Team Runbook", "path": "./docs/RUNBOOK.md" },
    { "name": "Architecture", "path": "./docs/ARCHITECTURE.md" }
  ],
  "workspaces": ["~/Projects"],
  "patterns": [
    ".github/copilot-instructions.md",
    "CLAUDE.md",
    ".cursorrules",
    "AGENTS.md"
  ],
  "codeDirs": ["src"],
  "adapters": [
    { "name": "feeds", "module": "./adapters/rss-adapter.js", "config": { "feeds": ["https://blog.example.com/rss.xml"] } }
  ]
}

Auto-discovered patterns

Config resolution order

Plugin Adapters

Extend ContextEngine with custom data sources via the adapter interface. Adapters are ES modules that collect data and return searchable chunks.

{
  "adapters": [
    {
      "name": "notion",
      "module": "./adapters/notion-adapter.js",
      "config": { "token": "$NOTION_API_TOKEN" }
    },
    {
      "name": "feeds",
      "module": "./adapters/rss-adapter.js",
      "config": { "feeds": ["https://blog.example.com/rss.xml"], "maxItems": 20 }
    }
  ]
}

Creating an Adapter

An adapter is a JS/TS module that exports an object with a collect() method:

// my-adapter.js
export default {
  name: "my-source",
  description: "Fetches data from My Source",

  validate(config) {
    if (!config?.apiKey) return "Missing apiKey";
    return null;
  },

  async collect(config) {
    // Fetch data and return Chunk[]
    return [{
      source: "my-source",
      section: "## Title",
      content: "Content to index...",
      lineStart: 1,
      lineEnd: 1,
    }];
  },
};

See examples/adapters/ for complete Notion and RSS adapter examples.

Adapter Features

• Environment variable resolution — use "$ENV_VAR" syntax in config

• Factory pattern — export createAdapter(config) for per-instance configuration

• Validation — optional validate() method checks config before collection

• Lifecycle hooks — optional init() and destroy() for setup/cleanup

• Safe execution — adapter failures never crash the server

How It Works

Your Project Files           ContextEngine              AI Agent
+-----------------+    +-------------------+    +---------------+
| copilot-        |    | 1. Parse & chunk  |    | GitHub        |
|  instructions   |--->| 2. Embed vectors  |<-->|  Copilot      |
| CLAUDE.md       |    | 3. Hybrid search  |    | Claude        |
| source code     |    | 4. Return top-k   |    | Cursor        |
| git/docker/pm2  |    | 5. Persist state  |    | Windsurf      |
+-----------------+    +-------------------+    +---------------+
                            stdio (MCP)

1. Parse — chunks markdown + extracts functions from source code

2. Embed — sentence embeddings run locally on CPU (no API keys)

3. Search — hybrid keyword + semantic scoring

4. Collect — operational data from git, package.json, Docker, PM2, nginx

5. Audit — compliance checks, port conflicts, AI-readiness scoring

Scoring

The score command evaluates project AI-readiness across documentation, infrastructure, code quality, and security — producing a letter grade from A+ to F.

Grade scale: A+ (90%+) · A (80%+) · B (70%+) · C (60%+) · D (50%+) · F (<50%)

Project Naming & Structure Tips

The scorer discovers projects from your configured workspaces directories (default: ~/Projects). Each subdirectory is treated as a separate project. For best results:

• Use descriptive folder names — the folder name becomes the project name in reports

• Keep one project per directory — monorepos should have a root copilot-instructions.md

• Real files over symlinks — each project should have its own configs with project-specific content

• Install your tools — a linting config without the linter installed doesn't count as linting

Architecture

TypeScript monorepo — MCP server + CLI + search engine + operational collectors.

See the npm package for installation and usage.

Development

npm install @compr/contextengine-mcp
npx @compr/contextengine-mcp help

Requirements

• Node.js 18+

• No API keys needed — embeddings run locally

Contributing

Feedback, feature requests, and bug reports welcome — email yannick@compr.ch.

If you're using ContextEngine, we'd love to hear about it.

Privacy & Data Security

ContextEngine runs 100% on your machine. Your code, your data, your rules.

Everything happens locally — search, scoring, learnings, sessions, embeddings. No project data is ever sent to an external server.

What stays on your machine (always)

What the activation server receives (PRO only)

The server never receives: project names, file contents, learnings, sessions, git history, dependencies, code, .env variables, or anything about your actual work.

Why this matters

Most AI coding tools (Copilot, Cursor, Codeium) send your code to external servers for processing. ContextEngine takes the opposite approach — embeddings run locally on CPU, search runs locally, and all persistent state stays in ~/.contextengine/ on your disk. The only network call is a lightweight license check for PRO users.

License

BSL-1.1 (Business Source License) — see LICENSE.

You may use ContextEngine for any purpose, including production, except offering it as a hosted/managed service competing with ContextEngine PRO/Team/Enterprise.

Converts to AGPL-3.0 on February 22, 2030.

For commercial licensing: yannick@compr.ch

Built by PROD LLC

ContextEngine is built by the team behind compr.app · crowlr.io · crowlr.com · invoc.io · plank.io · konive.com · invoc.me