@timmeck/trading-brain 2.31.75 → 2.31.76
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 +2 -2
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -5,9 +5,9 @@
|
|
|
5
5
|
[](LICENSE)
|
|
6
6
|
[](https://github.com/timmeck/brain-ecosystem)
|
|
7
7
|
|
|
8
|
-
**Adaptive Trading Intelligence & Signal Learning System for Claude Code —
|
|
8
|
+
**Adaptive Trading Intelligence & Signal Learning System for Claude Code — 181 MCP Tools, 72+ Engines**
|
|
9
9
|
|
|
10
|
-
Trading Brain is an MCP server that gives Claude Code a persistent trading memory. It learns from every trade outcome — strengthening connections between signals, strategies, and results through a Hebbian synapse network ("signals that win together wire together"). Paper trading with live market data (CoinGecko, Yahoo Finance, CCXT WebSocket). Over time, it develops statistical confidence in signal combinations, adapts calibration parameters, and runs 72+ autonomous engines in a 68-step feedback cycle to discover patterns, reason about causality, evolve strategies genetically, and improve itself. Full intelligence suite: RAG, Knowledge Graph, feedback learning, tool tracking, user model, proactive suggestions. Multi-provider LLM (Anthropic + Ollama). PortfolioOptimizer with Kelly criterion position sizing and HHI diversification scoring. StrategyMutator for evolutionary strategy breeding (mutation, crossover, tournament selection). Engine Governance with formal profiles, runtime influence tracking, 4 anti-pattern detectors, and active control (throttle/cooldown/isolate/escalate/restore).
|
|
10
|
+
Trading Brain is an MCP server that gives Claude Code a persistent trading memory. It learns from every trade outcome — strengthening connections between signals, strategies, and results through a Hebbian synapse network ("signals that win together wire together"). Paper trading with live market data (CoinGecko, Yahoo Finance, CCXT WebSocket). Over time, it develops statistical confidence in signal combinations, adapts calibration parameters, and runs 72+ autonomous engines in a 68-step feedback cycle to discover patterns, reason about causality, evolve strategies genetically, and improve itself. Full intelligence suite: RAG, Knowledge Graph, feedback learning, tool tracking, user model, proactive suggestions. Multi-provider LLM (Anthropic + Ollama). PortfolioOptimizer with Kelly criterion position sizing and HHI diversification scoring. StrategyMutator for evolutionary strategy breeding (mutation, crossover, tournament selection). Engine Governance with formal profiles, runtime influence tracking, 4 anti-pattern detectors, and active control (throttle/cooldown/isolate/escalate/restore). 518 tests. Workflow checkpointing, structured LLM output, observability tracing, agent training, dynamic tool scoping.
|
|
11
11
|
|
|
12
12
|
## Quick Start
|
|
13
13
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@timmeck/trading-brain",
|
|
3
|
-
"version": "2.31.
|
|
3
|
+
"version": "2.31.76",
|
|
4
4
|
"description": "Adaptive trading intelligence system with Hebbian synapses, spreading activation, Wilson Score confidence, and adaptive calibration",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|