@timmeck/brain 3.36.29 → 3.36.30

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.
Files changed (2) hide show
  1. package/README.md +33 -15
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -7,7 +7,7 @@
7
7
 
8
8
  **Autonomous Error Memory, Code Intelligence & Self-Improving AI for Claude Code — 162 MCP Tools, 72+ Engines**
9
9
 
10
- Brain is an MCP server that gives Claude Code a persistent, self-improving memory. It remembers errors, learns solutions, and runs 72+ autonomous engines in a 49-step feedback cycle. It observes itself, detects anomalies, forms and tests hypotheses, distills principles, reasons in chains, feels emotions, evolves strategies genetically, debates itself, challenges its own principles (Advocatus Diaboli), gets curious about knowledge gaps, syncs knowledge via Borg collective, loads community plugins, absorbs code from GitHub repos, extracts reusable features, and modifies its own source code. Multi-provider LLM (Anthropic + Ollama). RAG vector search across all knowledge. Knowledge Graph with transitive inference. RLHF feedback learning. Tool-use learning. User modeling. Proactive suggestions. Code assimilation with feature extraction. Autonomous web research missions. Live tech radar scanning. 162 MCP tools. 1607 tests.
10
+ Brain is an MCP server that gives Claude Code a persistent, self-improving memory. It remembers errors, learns solutions, and runs 72+ autonomous engines in a 50-step feedback cycle. It observes itself, detects anomalies, forms and tests hypotheses, distills principles, reasons in chains, feels emotions, evolves strategies genetically, debates itself, challenges its own principles (Advocatus Diaboli), gets curious about knowledge gaps, syncs knowledge via Borg collective, loads community plugins, absorbs code from GitHub repos, extracts reusable features, recommends missing features, and modifies its own source code. Multi-provider LLM (Anthropic + Ollama). RAG vector search across all knowledge. Knowledge Graph with transitive inference. RLHF feedback learning. Tool-use learning. User modeling. Proactive suggestions. Code assimilation with feature extraction + recommendation. Autonomous web research missions. Live tech radar scanning. 162 MCP tools. 3076 tests.
11
11
 
12
12
  ## Quick Start
13
13
 
@@ -23,14 +23,13 @@ That's it. One command configures MCP, hooks, and starts the daemon.
23
23
  ```
24
24
  Claude Code ──MCP stdio──► Brain Daemon (:7777)
25
25
  Cursor/Windsurf ─MCP SSE──► MCP HTTP Server (:7778)
26
- Browser ────────HTTP──────► Mission Control (:7788)
27
- Command Center (:7790)
26
+ Browser ────────HTTP──────► Command Center (:7790)
28
27
 
29
28
  ┌───────────────┼───────────────┐
30
29
  ▼ ▼ ▼
31
30
  Error Memory Research Engine 72+ Engines
32
31
  Code Intel Mission Engine ResearchOrchestrator
33
- Synapse Net LLM Service 40-step feedback loop
32
+ Synapse Net LLM Service 50-step feedback loop
34
33
  Prevention Web Research │
35
34
  Git Intel TechRadar ┌───┴───────────┐
36
35
  │ ▼ ▼
@@ -80,7 +79,7 @@ Cross-brain communication via IPC named pipes (trading-brain, marketing-brain).
80
79
 
81
80
  ### 72+ Autonomous Engines
82
81
 
83
- The ResearchOrchestrator runs a 40-step feedback cycle every 5 minutes:
82
+ The ResearchOrchestrator runs a 50-step feedback cycle every 5 minutes:
84
83
 
85
84
  #### Core Research Engines
86
85
 
@@ -110,6 +109,15 @@ The ResearchOrchestrator runs a 40-step feedback cycle every 5 minutes:
110
109
  | CuriosityEngine | Detects knowledge gaps and generates exploration questions |
111
110
  | ResearchAgendaEngine | Prioritizes what to investigate next |
112
111
  | CounterfactualEngine | "What if X hadn't happened?" reasoning |
112
+ | RAGEngine | Vector search across all knowledge (insights, memories, errors) |
113
+ | KnowledgeGraphEngine | Typed fact relations with transitive inference |
114
+ | SemanticCompressor | Deduplicates and compresses similar insights |
115
+ | FeedbackEngine | RLHF reward signals from user corrections |
116
+ | ToolTracker | Tool usage learning and pattern detection |
117
+ | ProactiveEngine | Trigger-based improvement suggestions |
118
+ | UserModel | Adaptive responses based on user skill level |
119
+ | CodeHealthMonitor | Codebase quality tracking with trend analysis |
120
+ | ActiveLearner | Gap identification and multi-strategy closing |
113
121
 
114
122
  #### Meta-Cognition Engines
115
123
 
@@ -124,6 +132,8 @@ The ResearchOrchestrator runs a 40-step feedback cycle every 5 minutes:
124
132
  | EmotionalModel | Frustration, curiosity, satisfaction — influences priorities |
125
133
  | SelfTestEngine | Tests understanding of its own principles |
126
134
  | TeachEngine | Packages knowledge for transfer to other brains |
135
+ | TeachingProtocol | Inter-brain knowledge transfer via IPC |
136
+ | ConsensusEngine | Multi-brain voting for critical decisions |
127
137
 
128
138
  #### Autonomy Engines
129
139
 
@@ -136,7 +146,10 @@ The ResearchOrchestrator runs a 40-step feedback cycle every 5 minutes:
136
146
  | EvolutionEngine | Genetic algorithm for strategy optimization |
137
147
  | AdaptiveStrategyEngine | Real-time parameter adaptation based on outcomes |
138
148
  | DreamEngine | Offline memory consolidation during idle |
139
- | ResearchOrchestrator | Orchestrates the entire 40-step feedback cycle |
149
+ | RepoAbsorber | Absorbs external repos and indexes their knowledge |
150
+ | FeatureExtractor | Extracts reusable functions, patterns, data structures |
151
+ | FeatureRecommender | Detects needs, matches features, builds connections |
152
+ | ResearchOrchestrator | Orchestrates the entire 50-step feedback cycle |
140
153
 
141
154
  ### Self-Improvement Loop
142
155
 
@@ -199,16 +212,21 @@ Automatic anomaly response system:
199
212
  - **Configurable** — All providers optional, graceful fallback
200
213
  - **Event Routing** — Different events route to different channels
201
214
 
202
- ### Dashboards
215
+ ### Command Center Dashboard (:7790)
203
216
 
204
- | Dashboard | Port | What It Shows |
205
- |-----------|------|--------------|
206
- | **Mission Control** | 7788 | 7-tab: Overview, Consciousness Entity, Thoughts, CodeGen, Self-Mod, Engines, Intelligence |
207
- | **Command Center** | 7790 | 8-page: Ecosystem, Learning, Trading, Marketing, Cross-Brain & Borg, Debates & Challenges, Activity & Missions, Infrastructure |
217
+ 9-page live dashboard showing the entire ecosystem:
208
218
 
209
- **Mission Control** The Consciousness Entity visualization shows Brain's current emotional state, active thought streams, engine activity heatmap, and real-time thought generation. CodeGen tab shows pending code proposals. Self-Mod tab shows modification history with diffs.
210
-
211
- **Command Center** Live overview of the entire ecosystem: all 3 brains, 72+ engines, error log, self-modification feed, research missions, knowledge growth chart, engine dependency flow, quick actions, animated Borg network, peer graph, debate history, Advocatus Diaboli challenges with resilience bars, watchdog daemon monitoring, LLM usage tracking.
219
+ | Page | What It Shows |
220
+ |------|--------------|
221
+ | Overview | All 3 brains, 72+ engines, error log, quick actions |
222
+ | Learning Cycle | 6-stage pipeline: Data → Analysis → Hypotheses → Experiments → Principles → Actions |
223
+ | Trading Flow | Signals → Analysis → Trades → P&L, equity, positions, win rate |
224
+ | Code Intelligence | Repo absorption, feature extraction, code health |
225
+ | Research | Missions, knowledge growth, research agenda |
226
+ | Entity | Consciousness orb — emotional state, thought streams, dimension ring |
227
+ | Cross-Brain & Borg | Collective sync, peer graph, Borg network |
228
+ | Debates & Challenges | Debate history, Advocatus Diaboli, resilience bars |
229
+ | Infrastructure | Watchdog monitoring, LLM usage, plugins, self-modification |
212
230
 
213
231
  ## MCP Tools (137 tools)
214
232
 
@@ -256,7 +274,7 @@ brain export Export Brain data as JSON
256
274
 
257
275
  | Brain | Purpose | Ports |
258
276
  |-------|---------|-------|
259
- | **Brain** (this) | Error memory, code intelligence, full autonomy & self-modification | **7777** / 7778 / 7788 / 7790 |
277
+ | **Brain** (this) | Error memory, code intelligence, full autonomy & self-modification | **7777** / 7778 / 7790 |
260
278
  | [Trading Brain](../trading-brain) | Adaptive trading intelligence with signal learning & paper trading | 7779 / 7780 |
261
279
  | [Marketing Brain](../marketing-brain) | Content strategy, social engagement & cross-platform optimization | 7781 / 7782 / 7783 |
262
280
  | [Brain Core](../brain-core) | Shared infrastructure — 72+ engines | — |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@timmeck/brain",
3
- "version": "3.36.29",
3
+ "version": "3.36.30",
4
4
  "description": "Adaptive error memory and code intelligence system with Hebbian synapse network, hybrid search, and REST API",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",