neuronlayer 0.1.0 → 1.1.0

package/README.md

@@ -1,7 +1,8 @@
-# MemoryLayer
+# NeuronLayer
 
-**Persistent memory layer for AI coding assistants. Your codebase documents itself.**
+**Turn any AI coding assistant into an intelligent one.**
 
+[![npm version](https://img.shields.io/npm/v/neuronlayer.svg)](https://www.npmjs.com/package/neuronlayer)
 [![MIT License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
 [![Node.js](https://img.shields.io/badge/Node.js-18+-339933.svg)](https://nodejs.org/)
 [![MCP](https://img.shields.io/badge/MCP-Compatible-blue.svg)](https://modelcontextprotocol.io/)
@@ -23,7 +24,7 @@ AI coding assistants are powerful but forgetful:
 
 ## The Solution
 
-MemoryLayer gives AI assistants persistent, intelligent memory:
+NeuronLayer gives AI assistants persistent, intelligent memory:
 
 - **Never forget context** - Decisions, patterns, and history persist across sessions
 - **Self-documenting codebase** - Architecture docs generate automatically
@@ -33,27 +34,17 @@ MemoryLayer gives AI assistants persistent, intelligent memory:
 
 ---
 
-## Features
-
-### Core Features (Free)
-
-| Feature | Description |
-|---------|-------------|
-| **Semantic Search** | Find code by meaning, not just keywords |
-| **Decision Recording** | Log architectural decisions with context |
-| **Pattern Library** | Learn and enforce coding patterns |
-| **File Indexing** | AST-based symbol extraction |
+## Compatibility
 
-### Advanced Features
-
-| Feature | Description |
-|---------|-------------|
-| **Living Documentation** | Auto-generated architecture docs |
-| **Context Rot Prevention** | Smart compaction keeps AI focused |
-| **Confidence Scoring** | Know when AI is guessing vs confident |
-| **Change Intelligence** | "What changed?" and "Why did it break?" |
-| **Architecture Enforcement** | Suggest existing functions, prevent duplication |
-| **Test-Aware Suggestions** | Predict test failures before they happen |
+| Tool | Supported | Auto-Configure |
+|------|-----------|----------------|
+| **memcode (Built-in agent)** | Yes | *N/A (Native)* |
+| Claude Desktop | Yes | `neuronlayer init` |
+| Claude Code (CLI) | Yes | `neuronlayer init` |
+| OpenCode | Yes | `neuronlayer init` |
+| VS Code + Continue | Yes | Manual config |
+| Cursor | Not yet | No MCP support |
+| Any MCP Client | Yes | Manual config |
 
 ---
 
@@ -62,50 +53,127 @@ MemoryLayer gives AI assistants persistent, intelligent memory:
 ### Installation
 
 ```bash
-npm install -g memory-layer
+npm install -g neuronlayer
+```
+
+### One-Command Setup
+
+```bash
+cd your-project
+neuronlayer init
+```
+
+That's it! This automatically:
+1. Registers your project
+2. Configures Claude Desktop
+3. Configures OpenCode
+4. Configures Claude Code
+
+Just restart your AI tool and NeuronLayer is active.
+
+### Output
+
 ```
+NeuronLayer initialized!
 
-### Usage with Claude Desktop
+Project: my-project
+Path: /home/user/my-project
+Data: ~/.neuronlayer/projects/my-project-abc123
 
-Add to your Claude Desktop config (`claude_desktop_config.json`):
+Configured MCP Clients:
+  ✓ Claude Desktop: ~/.config/claude/claude_desktop_config.json
+  ✓ OpenCode: ~/.opencode/config.json
+  ✓ Claude Code: ~/.claude.json
+
+Restart your AI tools to activate.
+```
+
+---
+
+## Manual Configuration
+
+If you prefer manual setup or use a different MCP client:
+
+### Claude Desktop
+
+Add to `claude_desktop_config.json`:
 
 ```json
 {
   "mcpServers": {
-    "memorylayer": {
+    "neuronlayer": {
       "command": "npx",
-      "args": ["-y", "memory-layer", "--project", "/path/to/your/project"]
+      "args": ["-y", "neuronlayer", "--project", "/path/to/your/project"]
     }
   }
 }
 ```
 
-### Usage with Any MCP Client
+Config locations:
+- **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
+- **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
+- **Linux**: `~/.config/claude/claude_desktop_config.json`
 
-```bash
-# Start the MCP server
-memorylayer --project /path/to/your/project
+### OpenCode
+
+Add to `~/.opencode/config.json`:
+
+```json
+{
+  "mcpServers": {
+    "neuronlayer": {
+      "command": "npx",
+      "args": ["-y", "neuronlayer", "--project", "/path/to/your/project"]
+    }
+  }
+}
 ```
 
 ---
 
+## Features
+
+### Core Features
+
+| Feature | Description |
+|---------|-------------|
+| **Semantic Search** | Find code by meaning, not just keywords |
+| **Decision Recording** | Log architectural decisions with context |
+| **Pattern Library** | Learn and enforce coding patterns |
+| **File Indexing** | Symbol extraction for TS/JS/Python |
+
+### Advanced Features
+
+| Feature | Description |
+|---------|-------------|
+| **Living Documentation** | Auto-generated architecture docs |
+| **Context Rot Prevention** | Smart compaction keeps AI focused |
+| **Confidence Scoring** | Know when AI is guessing vs confident |
+| **Change Intelligence** | "What changed?" and "Why did it break?" |
+| **Architecture Enforcement** | Suggest existing functions, prevent duplication |
+| **Test-Aware Suggestions** | Predict test failures before they happen |
+| **Super Intelligent Brain (Ghost Mode)** | Proactively checks for conflicts, déjà vu, and session context |
+| **Pre-commit Quality Gate** | Validates AI-generated code against hallucination and patterns BEFORE commit |
+
+---
+
 ## How It Works
 
 ```
 +-------------------------------------------------------------+
-|                      MEMORYLAYER                             |
+|                      NEURONLAYER                             |
 +-------------------------------------------------------------+
 |                                                              |
 |  +--------------+    +--------------+    +--------------+   |
 |  |   AI Tool    |--->|  MCP Server  |--->|   Memory     |   |
-|  | (Claude etc) |    |   (stdio)    |    |   Engine     |   |
+|  | Claude/Open  |    |   (stdio)    |    |   Engine     |   |
 |  +--------------+    +--------------+    +--------------+   |
 |                                                    |         |
 |                            +--------------------+--+----+   |
 |                            |                    v       |   |
 |  +--------------+    +-----+----+    +------------------+|  |
 |  |  Your Code   |--->| Indexer  |--->|  SQLite + Vec DB ||  |
-|  |  (watched)   |    | (AST/Git)|    |  (embeddings)    ||  |
+|  |  (watched)   |    |  (Regex) |    |  (embeddings)    ||  |
 |  +--------------+    +----------+    +------------------+|  |
 |                                                          |  |
 +-------------------------------------------------------------+
@@ -119,88 +187,116 @@ memorylayer --project /path/to/your/project
 
 ---
 
-## MCP Tools
+## MCP Tools (The Gateway Architecture)
 
-MemoryLayer exposes 25+ MCP tools:
+NeuronLayer elegantly compresses 51+ granular internal functions into **12 optimized Gateway Tools**, dramatically saving prompt tokens and improving LLM routing reliability (proven 759x faster than standard grep).
 
-### Query & Search
-- `memory_query` - Semantic search across codebase
-- `memory_status` - Project overview and health
+### 6 Core Gateways
+- `memory_query` - Semantic search, symbol lookup, and focused context retrieval.
+- `memory_record` - Save architectural decisions, patterns, and feedback.
+- `memory_review` - Pre-flight check before code changes vs patterns & decisions.
+- `memory_status` - Project overview, architecture diagrams, and health checks.
+- `memory_ghost` - The "Super Intelligent Brain": flags conflicts, déjà vu, and session resurrection.
+- `memory_verify` - Pre-commit quality gate for AI-generated code (hallucinations, imports, security, tests).
 
-### Recording
-- `memory_record` - Save decisions, patterns, feedback
-- `memory_review` - Pre-flight check before code changes
-- `memory_verify` - Validate AI-generated code
+### 6 Standalone Commands
+- `switch_project` - Hot-swap active project context.
+- `switch_feature_context` - Resume tracking an ongoing feature.
+- `trigger_compaction` - Smart compression of context tree.
+- `update_decision_status` - Mark architectural choices as deprecated/superseded.
+- `export_decisions_to_adr` - Generate markdown Architecture Decision Records (ADRs).
+- `discover_projects` - Find eligible Git repositories on disk.
 
-### Ghost Mode (AI-Proactive)
-- `memory_ghost` - Conflicts, deja vu, session resurrection
+---
 
-### Living Documentation
-- `get_architecture` - Project structure overview
-- `get_changelog` - Recent changes with context
-- `what_happened` - "What did we do yesterday?"
+## 🤖 memcode - The First-Party AI Coding Assistant
 
-### Architecture Enforcement
-- `validate_pattern` - Check code against patterns
-- `suggest_existing` - Find reusable functions
-- `learn_pattern` - Teach new patterns
+NeuronLayer powers its own fully-featured terminal coding agent: **memcode**. 
+It natively understands NeuronLayer's context graph and avoids context rot.
 
-### Test Awareness
-- `get_related_tests` - Tests for a file/function
-- `check_tests` - Predict test failures
-- `suggest_test_update` - Test update suggestions
+### Quick Start
+```bash
+# Set your preferred API key
+export ANTHROPIC_API_KEY=your-key
 
----
+# Run memcode inside your project
+npx neuronlayer memcode
+```
+
+### memcode Features
+- **Multi-LLM Support**: Claude (Anthropic), all GPT/o1 (OpenAI), 200+ models via OpenRouter, and Local LLMs (Ollama).
+- **Persistent Memory**: Decisions and patterns automatically persist across your chat sessions.
+- **Full Shell & Git access**: Runs commands, tests, and edits files directly in your sandbox.
+- **Session Lifecycles**: Save and resume conversations exactly where you left them.
 
-## Configuration
+### Interactive Commands
+Inside a `memcode` session, use:
+- `/model [name]` - Hot-swap LLMs.
+- `/feature [name]` - Track a specific feature area.
+- `/cost` - Track precise token usage and cost.
+- `/save` & `/continue` - Session management.
 
-MemoryLayer stores data in:
-- **Windows**: `%APPDATA%\.memorylayer\<project-hash>\`
-- **macOS/Linux**: `~/.memorylayer/<project-hash>/`
+---
 
-### CLI Commands
+## CLI Commands
 
 ```bash
-# List all indexed projects
-memorylayer projects
+# Quick setup (auto-configures Claude Desktop, OpenCode)
+neuronlayer init
 
-# Export decisions as ADRs
-memorylayer export --format adr --output ./docs/decisions
+# Run the native AI Coding Assistant
+neuronlayer memcode
+
+# List all registered projects
+neuronlayer projects list
+
+# Add a new project
+neuronlayer projects add /path/to/my-project
+
+# Switch active project
+neuronlayer projects switch <id>
+
+# Export decisions to ADR files
+neuronlayer export --format madr
+
+# Discover projects in common locations
+neuronlayer projects discover
 
 # Show help
-memorylayer help
+neuronlayer help
 ```
 
 ---
 
-## Architecture
+## Data Storage
+
+NeuronLayer stores project data separately for each project:
 
 ```
-src/
-├── core/                    # Business logic
-│   ├── engine.ts            # Main orchestrator
-│   ├── living-docs/         # Auto-documentation
-│   ├── context-rot/         # Context health management
-│   ├── confidence/          # Trust scoring
-│   ├── change-intelligence/ # What changed & why
-│   ├── architecture/        # Pattern enforcement
-│   └── test-awareness/      # Test-respecting suggestions
-├── server/
-│   ├── mcp.ts               # MCP protocol handler
-│   ├── tools.ts             # Tool definitions
-│   └── gateways/            # Unified tool APIs
-├── storage/
-│   ├── tier1.ts             # Hot cache
-│   ├── tier2.ts             # SQLite storage
-│   └── tier3.ts             # Vector embeddings
-├── indexing/
-│   ├── indexer.ts           # File indexing
-│   ├── ast.ts               # AST parsing
-│   ├── embeddings.ts        # Embedding generation
-│   └── watcher.ts           # File watching
-└── types/                   # TypeScript definitions
+~/.neuronlayer/
+├── projects/
+│   ├── project-a-abc123/
+│   │   ├── neuronlayer.db    # SQLite database
+│   │   └── embeddings/       # Vector index
+│   └── project-b-def456/
+│       ├── neuronlayer.db
+│       └── embeddings/
+└── registry.json             # Project registry
 ```
 
+Each project is isolated - no data mixing between projects.
+
+---
+
+## Privacy
+
+NeuronLayer is **100% local by default**:
+
+- All data stored on your machine
+- No cloud services required
+- No telemetry or tracking
+- Works completely offline
+
 ---
 
 ## Development
@@ -214,8 +310,8 @@ src/
 
 ```bash
 # Clone the repository
-git clone https://github.com/anthropics/memorylayer.git
-cd memorylayer
+git clone https://github.com/abhisavakar/neuronlayer.git
+cd neuronlayer
 
 # Install dependencies
 npm install
@@ -230,29 +326,6 @@ npm test
 npm run typecheck
 ```
 
-### Scripts
-
-| Script | Description |
-|--------|-------------|
-| `npm run build` | Build the project |
-| `npm run dev` | Development mode with watch |
-| `npm run test` | Run tests |
-| `npm run typecheck` | Type check without building |
-| `npm run benchmark` | Run performance benchmarks |
-
----
-
-## Privacy
-
-MemoryLayer is **100% local by default**:
-
-- All data stored on your machine
-- No cloud services required
-- No telemetry or tracking
-- Works offline
-
-Optional cloud features (coming soon) will use your own infrastructure.
-
 ---
 
 ## Contributing
@@ -261,11 +334,11 @@ We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
 
 ### Areas We Need Help
 
-- Additional language support (Python, Go, Rust AST)
+- Additional language support (Go, Rust, Java)
 - IDE extensions (VS Code, JetBrains)
+- Cursor integration (when they add MCP support)
 - Documentation improvements
 - Performance optimizations
-- Bug fixes and test coverage
 
 ---
 
@@ -278,9 +351,11 @@ We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
 - [x] Change Intelligence
 - [x] Architecture Enforcement
 - [x] Test-Aware Suggestions
+- [x] Auto-setup for Claude Desktop
+- [x] Auto-setup for OpenCode
 - [ ] VS Code extension
+- [ ] Cursor support (pending MCP)
 - [ ] Team features (shared memory)
-- [ ] Enterprise deployment (AWS Bedrock)
 
 ---
 
@@ -290,16 +365,21 @@ MIT License - see [LICENSE](LICENSE) for details.
 
 ---
 
+## Author
+
+**Abhishek Arun Savakar** - [savakar.com](https://savakar.com)
+
+---
+
 ## Acknowledgments
 
 Built with:
 - [Model Context Protocol](https://modelcontextprotocol.io/) by Anthropic
 - [better-sqlite3](https://github.com/WiseLibs/better-sqlite3)
-- [tree-sitter](https://tree-sitter.github.io/tree-sitter/) for AST parsing
 - [Xenova/transformers](https://github.com/xenova/transformers.js) for embeddings
 
 ---
 
 **Made with determination over a weekend.**
 
-*Your codebase documents itself. AI that never forgets.*
+*Code intelligence that transforms AI assistants into intelligent coding partners.*