neuronlayer 0.1.1 → 0.1.3

package/README.md

@@ -1,7 +1,8 @@
-# MemoryLayer
+# NeuronLayer
 
 **Persistent memory layer for AI coding assistants. Your codebase documents itself.**
 
+[![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/)
@@ -12,48 +13,32 @@
 
 AI coding assistants are powerful but forgetful:
 
-| Problem | Stat |
-|---------|------|
-| Productivity paradox | 19% SLOWER with AI |
-| "Almost right" frustration | 66% of developers |
-| Trust issues | Only 29% trust AI code |
-| Context collapse | AI forgets mid-session |
-| Technical debt | 1.64x higher errors |
-| Code duplication | 4x more cloning |
+- Context collapse - AI forgets mid-session
+- No persistent memory - every session starts fresh
+- Code duplication - AI doesn't know what already exists
+- Test breakage - AI suggestions break existing tests
 
 ## 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
-- **Context rot prevention** - AI stays sharp even in long sessions
-- **Pattern enforcement** - Stops code duplication before it happens
-- **Test-aware suggestions** - AI respects your tests
+- **Decisions persist** - Architectural decisions survive across sessions
+- **Patterns learned** - AI knows your coding conventions
+- **Context preserved** - Smart compaction prevents forgetting
+- **Tests respected** - AI knows what tests exist
 
 ---
 
-## 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 |
+|------|-----------|----------------|
+| 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 |
 
 ---
 
@@ -65,26 +50,78 @@ MemoryLayer gives AI assistants persistent, intelligent memory:
 npm install -g neuronlayer
 ```
 
-### Usage with Claude Desktop
-
-Add to your Claude Desktop config (`claude_desktop_config.json`):
+### One-Command Setup
 
-```json
-{
-  "mcpServers": {
-    "memorylayer": {
-      "command": "npx",
-      "args": ["-y", "neuronlayer", "--project", "/path/to/your/project"]
-    }
-  }
-}
+```bash
+cd your-project
+neuronlayer init
 ```
 
-### Usage with Any MCP Client
+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.
+
+---
+
+## MCP Tools
+
+NeuronLayer exposes **12 MCP tools** organized into 6 gateway tools and 6 standalone tools.
+
+### Gateway Tools (Smart Routing)
+
+These are the main tools. Each routes to multiple internal capabilities based on input:
+
+| Tool | Purpose |
+|------|---------|
+| `memory_query` | Search codebase, find code, look up symbols, get file context |
+| `memory_record` | Save decisions, learn patterns, record feedback, track features |
+| `memory_review` | Pre-code review: check patterns, conflicts, tests, get suggestions |
+| `memory_status` | Project overview, architecture, recent changes, health check |
+| `memory_ghost` | Proactive intelligence: conflicts, "you solved this before", session resume |
+| `memory_verify` | Pre-commit check: validate imports, security, dependencies |
+
+### Standalone Tools
+
+| Tool | Purpose |
+|------|---------|
+| `switch_project` | Switch between registered projects |
+| `switch_feature_context` | Resume work on a previous feature |
+| `trigger_compaction` | Reduce memory when context is full |
+| `update_decision_status` | Mark decisions as deprecated/superseded |
+| `export_decisions_to_adr` | Export decisions as ADR markdown files |
+| `discover_projects` | Find git repos on the system |
+
+---
+
+## Features
+
+### What's Implemented
+
+| Feature | Status | Description |
+|---------|--------|-------------|
+| **Semantic Search** | Working | Find code by meaning using embeddings |
+| **Decision Recording** | Working | Log architectural decisions with context |
+| **Pattern Library** | Working | Learn and validate coding patterns |
+| **File Indexing** | Working | AST-based symbol extraction |
+| **Context Compaction** | Working | Smart summarization when context fills |
+| **Test Indexing** | Working | Index tests, predict failures |
+| **Git Integration** | Working | Track changes, correlate with decisions |
+| **Multi-Project** | Working | Switch between projects |
+
+### Modules
 
-```bash
-# Start the MCP server
-memorylayer --project /path/to/your/project
+```
+src/core/
+├── living-docs/         # Architecture & changelog generation
+├── context-rot/         # Context health & compaction
+├── confidence/          # Source tracking & conflict detection
+├── change-intelligence/ # Git tracking & fix suggestions
+├── architecture/        # Pattern library & validation
+└── test-awareness/      # Test indexing & failure prediction
 ```
 
 ---
@@ -93,12 +130,12 @@ memorylayer --project /path/to/your/project
 
 ```
 +-------------------------------------------------------------+
-|                      MEMORYLAYER                             |
+|                      NEURONLAYER                             |
 +-------------------------------------------------------------+
 |                                                              |
 |  +--------------+    +--------------+    +--------------+   |
 |  |   AI Tool    |--->|  MCP Server  |--->|   Memory     |   |
-|  | (Claude etc) |    |   (stdio)    |    |   Engine     |   |
+|  | Claude/Open  |    |   (stdio)    |    |   Engine     |   |
 |  +--------------+    +--------------+    +--------------+   |
 |                                                    |         |
 |                            +--------------------+--+----+   |
@@ -119,187 +156,129 @@ memorylayer --project /path/to/your/project
 
 ---
 
-## MCP Tools
-
-MemoryLayer exposes 25+ MCP tools:
-
-### Query & Search
-- `memory_query` - Semantic search across codebase
-- `memory_status` - Project overview and health
-
-### Recording
-- `memory_record` - Save decisions, patterns, feedback
-- `memory_review` - Pre-flight check before code changes
-- `memory_verify` - Validate AI-generated code
-
-### Ghost Mode (AI-Proactive)
-- `memory_ghost` - Conflicts, deja vu, session resurrection
+## CLI Commands
 
-### Living Documentation
-- `get_architecture` - Project structure overview
-- `get_changelog` - Recent changes with context
-- `what_happened` - "What did we do yesterday?"
-
-### Architecture Enforcement
-- `validate_pattern` - Check code against patterns
-- `suggest_existing` - Find reusable functions
-- `learn_pattern` - Teach new patterns
-
-### Test Awareness
-- `get_related_tests` - Tests for a file/function
-- `check_tests` - Predict test failures
-- `suggest_test_update` - Test update suggestions
-
----
+```bash
+# Quick setup (auto-configures AI tools)
+neuronlayer init
 
-## Configuration
+# Initialize specific project
+neuronlayer init /path/to/project
 
-MemoryLayer stores data in:
-- **Windows**: `%APPDATA%\.memorylayer\<project-hash>\`
-- **macOS/Linux**: `~/.memorylayer/<project-hash>/`
+# List all registered projects
+neuronlayer projects list
 
-### CLI Commands
+# Add a new project
+neuronlayer projects add /path/to/my-project
 
-```bash
-# List all indexed projects
-memorylayer projects
+# Switch active project
+neuronlayer projects switch <id>
 
-# Export decisions as ADRs
-memorylayer export --format adr --output ./docs/decisions
+# Export decisions to ADR files
+neuronlayer export --format madr
 
 # Show help
-memorylayer help
+neuronlayer help
 ```
 
 ---
 
-## Architecture
+## Manual Configuration
 
-```
-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
-```
+### Claude Desktop
 
----
+Add to `claude_desktop_config.json`:
 
-## Development
+```json
+{
+  "mcpServers": {
+    "neuronlayer": {
+      "command": "npx",
+      "args": ["-y", "neuronlayer", "--project", "/path/to/your/project"]
+    }
+  }
+}
+```
 
-### Prerequisites
+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`
 
-- Node.js 18+
-- npm or yarn
+### OpenCode
 
-### Setup
+Add to `~/.opencode/config.json`:
 
-```bash
-# Clone the repository
-git clone https://github.com/anthropics/memorylayer.git
-cd memorylayer
+```json
+{
+  "mcpServers": {
+    "neuronlayer": {
+      "command": "npx",
+      "args": ["-y", "neuronlayer", "--project", "/path/to/your/project"]
+    }
+  }
+}
+```
 
-# Install dependencies
-npm install
+---
 
-# Build
-npm run build
+## Data Storage
 
-# Run tests
-npm test
+Each project has isolated data:
 
-# Type check
-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 |
+~/.memorylayer/
+├── projects/
+│   ├── project-a-abc123/
+│   │   ├── memorylayer.db    # SQLite database
+│   │   └── embeddings/       # Vector index
+│   └── project-b-def456/
+│       └── ...
+└── registry.json             # Project registry
+```
 
 ---
 
 ## Privacy
 
-MemoryLayer is **100% local by default**:
+NeuronLayer is **100% local**:
 
 - All data stored on your machine
-- No cloud services required
-- No telemetry or tracking
+- No cloud services
+- No telemetry
 - Works offline
 
-Optional cloud features (coming soon) will use your own infrastructure.
-
 ---
 
-## Contributing
-
-We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
-
-### Areas We Need Help
+## Development
 
-- Additional language support (Python, Go, Rust AST)
-- IDE extensions (VS Code, JetBrains)
-- Documentation improvements
-- Performance optimizations
-- Bug fixes and test coverage
+```bash
+# Clone
+git clone https://github.com/abhisavakar/neuronlayer.git
+cd neuronlayer
 
----
+# Install
+npm install
 
-## Roadmap
+# Build
+npm run build
 
-- [x] Core MCP server
-- [x] Living Documentation
-- [x] Context Rot Prevention
-- [x] Confidence Scoring
-- [x] Change Intelligence
-- [x] Architecture Enforcement
-- [x] Test-Aware Suggestions
-- [ ] VS Code extension
-- [ ] Team features (shared memory)
-- [ ] Enterprise deployment (AWS Bedrock)
+# Test
+npm test
+```
 
 ---
 
 ## License
 
-MIT License - see [LICENSE](LICENSE) for details.
+MIT License - see [LICENSE](LICENSE)
 
 ---
 
-## Acknowledgments
+## Author
 
-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
+**Abhishek Arun Savakar** - [savakar.com](https://savakar.com)
 
 ---
 
-**Made with determination over a weekend.**
-
-*Your codebase documents itself. AI that never forgets.*
+Built with [Model Context Protocol](https://modelcontextprotocol.io/) by Anthropic.