neuronlayer 0.1.0 → 0.1.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -1,7 +1,8 @@
1
- # MemoryLayer
1
+ # NeuronLayer
2
2
 
3
3
  **Persistent memory layer for AI coding assistants. Your codebase documents itself.**
4
4
 
5
+ [![npm version](https://img.shields.io/npm/v/neuronlayer.svg)](https://www.npmjs.com/package/neuronlayer)
5
6
  [![MIT License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
6
7
  [![Node.js](https://img.shields.io/badge/Node.js-18+-339933.svg)](https://nodejs.org/)
7
8
  [![MCP](https://img.shields.io/badge/MCP-Compatible-blue.svg)](https://modelcontextprotocol.io/)
@@ -23,7 +24,7 @@ AI coding assistants are powerful but forgetful:
23
24
 
24
25
  ## The Solution
25
26
 
26
- MemoryLayer gives AI assistants persistent, intelligent memory:
27
+ NeuronLayer gives AI assistants persistent, intelligent memory:
27
28
 
28
29
  - **Never forget context** - Decisions, patterns, and history persist across sessions
29
30
  - **Self-documenting codebase** - Architecture docs generate automatically
@@ -33,27 +34,16 @@ MemoryLayer gives AI assistants persistent, intelligent memory:
33
34
 
34
35
  ---
35
36
 
36
- ## Features
37
-
38
- ### Core Features (Free)
37
+ ## Compatibility
39
38
 
40
- | Feature | Description |
41
- |---------|-------------|
42
- | **Semantic Search** | Find code by meaning, not just keywords |
43
- | **Decision Recording** | Log architectural decisions with context |
44
- | **Pattern Library** | Learn and enforce coding patterns |
45
- | **File Indexing** | AST-based symbol extraction |
46
-
47
- ### Advanced Features
48
-
49
- | Feature | Description |
50
- |---------|-------------|
51
- | **Living Documentation** | Auto-generated architecture docs |
52
- | **Context Rot Prevention** | Smart compaction keeps AI focused |
53
- | **Confidence Scoring** | Know when AI is guessing vs confident |
54
- | **Change Intelligence** | "What changed?" and "Why did it break?" |
55
- | **Architecture Enforcement** | Suggest existing functions, prevent duplication |
56
- | **Test-Aware Suggestions** | Predict test failures before they happen |
39
+ | Tool | Supported | Auto-Configure |
40
+ |------|-----------|----------------|
41
+ | Claude Desktop | Yes | `neuronlayer init` |
42
+ | Claude Code (CLI) | Yes | `neuronlayer init` |
43
+ | OpenCode | Yes | `neuronlayer init` |
44
+ | VS Code + Continue | Yes | Manual config |
45
+ | Cursor | Not yet | No MCP support |
46
+ | Any MCP Client | Yes | Manual config |
57
47
 
58
48
  ---
59
49
 
@@ -62,43 +52,118 @@ MemoryLayer gives AI assistants persistent, intelligent memory:
62
52
  ### Installation
63
53
 
64
54
  ```bash
65
- npm install -g memory-layer
55
+ npm install -g neuronlayer
66
56
  ```
67
57
 
68
- ### Usage with Claude Desktop
58
+ ### One-Command Setup
69
59
 
70
- Add to your Claude Desktop config (`claude_desktop_config.json`):
60
+ ```bash
61
+ cd your-project
62
+ neuronlayer init
63
+ ```
64
+
65
+ That's it! This automatically:
66
+ 1. Registers your project
67
+ 2. Configures Claude Desktop
68
+ 3. Configures OpenCode
69
+ 4. Configures Claude Code
70
+
71
+ Just restart your AI tool and NeuronLayer is active.
72
+
73
+ ### Output
74
+
75
+ ```
76
+ NeuronLayer initialized!
77
+
78
+ Project: my-project
79
+ Path: /home/user/my-project
80
+ Data: ~/.memorylayer/projects/my-project-abc123
81
+
82
+ Configured MCP Clients:
83
+ ✓ Claude Desktop: ~/.config/claude/claude_desktop_config.json
84
+ ✓ OpenCode: ~/.opencode/config.json
85
+ ✓ Claude Code: ~/.claude.json
86
+
87
+ Restart your AI tools to activate.
88
+ ```
89
+
90
+ ---
91
+
92
+ ## Manual Configuration
93
+
94
+ If you prefer manual setup or use a different MCP client:
95
+
96
+ ### Claude Desktop
97
+
98
+ Add to `claude_desktop_config.json`:
71
99
 
72
100
  ```json
73
101
  {
74
102
  "mcpServers": {
75
- "memorylayer": {
103
+ "neuronlayer": {
76
104
  "command": "npx",
77
- "args": ["-y", "memory-layer", "--project", "/path/to/your/project"]
105
+ "args": ["-y", "neuronlayer", "--project", "/path/to/your/project"]
78
106
  }
79
107
  }
80
108
  }
81
109
  ```
82
110
 
83
- ### Usage with Any MCP Client
111
+ Config locations:
112
+ - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
113
+ - **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
114
+ - **Linux**: `~/.config/claude/claude_desktop_config.json`
84
115
 
85
- ```bash
86
- # Start the MCP server
87
- memorylayer --project /path/to/your/project
116
+ ### OpenCode
117
+
118
+ Add to `~/.opencode/config.json`:
119
+
120
+ ```json
121
+ {
122
+ "mcpServers": {
123
+ "neuronlayer": {
124
+ "command": "npx",
125
+ "args": ["-y", "neuronlayer", "--project", "/path/to/your/project"]
126
+ }
127
+ }
128
+ }
88
129
  ```
89
130
 
90
131
  ---
91
132
 
133
+ ## Features
134
+
135
+ ### Core Features
136
+
137
+ | Feature | Description |
138
+ |---------|-------------|
139
+ | **Semantic Search** | Find code by meaning, not just keywords |
140
+ | **Decision Recording** | Log architectural decisions with context |
141
+ | **Pattern Library** | Learn and enforce coding patterns |
142
+ | **File Indexing** | AST-based symbol extraction |
143
+
144
+ ### Advanced Features
145
+
146
+ | Feature | Description |
147
+ |---------|-------------|
148
+ | **Living Documentation** | Auto-generated architecture docs |
149
+ | **Context Rot Prevention** | Smart compaction keeps AI focused |
150
+ | **Confidence Scoring** | Know when AI is guessing vs confident |
151
+ | **Change Intelligence** | "What changed?" and "Why did it break?" |
152
+ | **Architecture Enforcement** | Suggest existing functions, prevent duplication |
153
+ | **Test-Aware Suggestions** | Predict test failures before they happen |
154
+
155
+ ---
156
+
92
157
  ## How It Works
93
158
 
94
159
  ```
95
160
  +-------------------------------------------------------------+
96
- | MEMORYLAYER |
161
+ | NEURONLAYER |
97
162
  +-------------------------------------------------------------+
98
163
  | |
99
164
  | +--------------+ +--------------+ +--------------+ |
100
165
  | | AI Tool |--->| MCP Server |--->| Memory | |
101
- | | (Claude etc) | | (stdio) | | Engine | |
166
+ | | Claude/Open | | (stdio) | | Engine | |
102
167
  | +--------------+ +--------------+ +--------------+ |
103
168
  | | |
104
169
  | +--------------------+--+----+ |
@@ -121,7 +186,7 @@ memorylayer --project /path/to/your/project
121
186
 
122
187
  ## MCP Tools
123
188
 
124
- MemoryLayer exposes 25+ MCP tools:
189
+ NeuronLayer exposes 25+ MCP tools:
125
190
 
126
191
  ### Query & Search
127
192
  - `memory_query` - Semantic search across codebase
@@ -152,55 +217,65 @@ MemoryLayer exposes 25+ MCP tools:
152
217
 
153
218
  ---
154
219
 
155
- ## Configuration
220
+ ## CLI Commands
221
+
222
+ ```bash
223
+ # Quick setup (auto-configures AI tools)
224
+ neuronlayer init
156
225
 
157
- MemoryLayer stores data in:
158
- - **Windows**: `%APPDATA%\.memorylayer\<project-hash>\`
159
- - **macOS/Linux**: `~/.memorylayer/<project-hash>/`
226
+ # Initialize specific project
227
+ neuronlayer init /path/to/project
160
228
 
161
- ### CLI Commands
229
+ # List all registered projects
230
+ neuronlayer projects list
162
231
 
163
- ```bash
164
- # List all indexed projects
165
- memorylayer projects
232
+ # Add a new project
233
+ neuronlayer projects add /path/to/my-project
234
+
235
+ # Switch active project
236
+ neuronlayer projects switch <id>
166
237
 
167
- # Export decisions as ADRs
168
- memorylayer export --format adr --output ./docs/decisions
238
+ # Export decisions to ADR files
239
+ neuronlayer export --format madr
240
+
241
+ # Discover projects in common locations
242
+ neuronlayer projects discover
169
243
 
170
244
  # Show help
171
- memorylayer help
245
+ neuronlayer help
172
246
  ```
173
247
 
174
248
  ---
175
249
 
176
- ## Architecture
250
+ ## Data Storage
251
+
252
+ NeuronLayer stores project data separately for each project:
177
253
 
178
254
  ```
179
- src/
180
- ├── core/ # Business logic
181
- │ ├── engine.ts # Main orchestrator
182
- │ ├── living-docs/ # Auto-documentation
183
- ├── context-rot/ # Context health management
184
- ├── confidence/ # Trust scoring
185
- ├── change-intelligence/ # What changed & why
186
- ├── architecture/ # Pattern enforcement
187
- └── test-awareness/ # Test-respecting suggestions
188
- ├── server/
189
- │ ├── mcp.ts # MCP protocol handler
190
- │ ├── tools.ts # Tool definitions
191
- │ └── gateways/ # Unified tool APIs
192
- ├── storage/
193
- │ ├── tier1.ts # Hot cache
194
- │ ├── tier2.ts # SQLite storage
195
- │ └── tier3.ts # Vector embeddings
196
- ├── indexing/
197
- │ ├── indexer.ts # File indexing
198
- │ ├── ast.ts # AST parsing
199
- │ ├── embeddings.ts # Embedding generation
200
- │ └── watcher.ts # File watching
201
- └── types/ # TypeScript definitions
255
+ ~/.memorylayer/
256
+ ├── projects/
257
+ │ ├── project-a-abc123/
258
+ ├── memorylayer.db # SQLite database
259
+ │ └── embeddings/ # Vector index
260
+ └── project-b-def456/
261
+ ├── memorylayer.db
262
+ └── embeddings/
263
+ └── registry.json # Project registry
202
264
  ```
203
265
 
266
+ Each project is isolated - no data mixing between projects.
267
+
268
+ ---
269
+
270
+ ## Privacy
271
+
272
+ NeuronLayer is **100% local by default**:
273
+
274
+ - All data stored on your machine
275
+ - No cloud services required
276
+ - No telemetry or tracking
277
+ - Works completely offline
278
+
204
279
  ---
205
280
 
206
281
  ## Development
@@ -214,8 +289,8 @@ src/
214
289
 
215
290
  ```bash
216
291
  # Clone the repository
217
- git clone https://github.com/anthropics/memorylayer.git
218
- cd memorylayer
292
+ git clone https://github.com/abhisavakar/neuronlayer.git
293
+ cd neuronlayer
219
294
 
220
295
  # Install dependencies
221
296
  npm install
@@ -230,29 +305,6 @@ npm test
230
305
  npm run typecheck
231
306
  ```
232
307
 
233
- ### Scripts
234
-
235
- | Script | Description |
236
- |--------|-------------|
237
- | `npm run build` | Build the project |
238
- | `npm run dev` | Development mode with watch |
239
- | `npm run test` | Run tests |
240
- | `npm run typecheck` | Type check without building |
241
- | `npm run benchmark` | Run performance benchmarks |
242
-
243
- ---
244
-
245
- ## Privacy
246
-
247
- MemoryLayer is **100% local by default**:
248
-
249
- - All data stored on your machine
250
- - No cloud services required
251
- - No telemetry or tracking
252
- - Works offline
253
-
254
- Optional cloud features (coming soon) will use your own infrastructure.
255
-
256
308
  ---
257
309
 
258
310
  ## Contributing
@@ -263,9 +315,9 @@ We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
263
315
 
264
316
  - Additional language support (Python, Go, Rust AST)
265
317
  - IDE extensions (VS Code, JetBrains)
318
+ - Cursor integration (when they add MCP support)
266
319
  - Documentation improvements
267
320
  - Performance optimizations
268
- - Bug fixes and test coverage
269
321
 
270
322
  ---
271
323
 
@@ -278,9 +330,11 @@ We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
278
330
  - [x] Change Intelligence
279
331
  - [x] Architecture Enforcement
280
332
  - [x] Test-Aware Suggestions
333
+ - [x] Auto-setup for Claude Desktop
334
+ - [x] Auto-setup for OpenCode
281
335
  - [ ] VS Code extension
336
+ - [ ] Cursor support (pending MCP)
282
337
  - [ ] Team features (shared memory)
283
- - [ ] Enterprise deployment (AWS Bedrock)
284
338
 
285
339
  ---
286
340
 
@@ -290,6 +344,12 @@ MIT License - see [LICENSE](LICENSE) for details.
290
344
 
291
345
  ---
292
346
 
347
+ ## Author
348
+
349
+ **Abhishek Arun Savakar** - [savakar.com](https://savakar.com)
350
+
351
+ ---
352
+
293
353
  ## Acknowledgments
294
354
 
295
355
  Built with: