@timmeck/trading-brain 2.31.26 → 2.31.28
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 +4 -4
- package/package.json +2 -2
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 — 151 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
|
|
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 49-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). 487 tests.
|
|
11
11
|
|
|
12
12
|
## Quick Start
|
|
13
13
|
|
|
@@ -52,7 +52,7 @@ That's it. One command configures MCP, hooks, and starts the daemon.
|
|
|
52
52
|
- **Rate Limiting** — Per-hour and per-day token budgets with automatic throttling
|
|
53
53
|
- **Usage Tracking** — Calls, tokens, latency, cache hit rate, cost tracking
|
|
54
54
|
|
|
55
|
-
###
|
|
55
|
+
### 72+ Autonomous Engines
|
|
56
56
|
|
|
57
57
|
The ResearchOrchestrator runs a 40-step feedback cycle every 5 minutes:
|
|
58
58
|
|
|
@@ -163,7 +163,7 @@ trading import <file> Import trades from JSON
|
|
|
163
163
|
| [Brain](../brain) | Error memory, code intelligence, full autonomy & self-modification | 7777 / 7778 / 7788 / 7790 |
|
|
164
164
|
| **Trading Brain** (this) | Adaptive trading intelligence with signal learning & paper trading | **7779** / 7780 |
|
|
165
165
|
| [Marketing Brain](../marketing-brain) | Content strategy, social engagement & cross-platform optimization | 7781 / 7782 / 7783 |
|
|
166
|
-
| [Brain Core](../brain-core) | Shared infrastructure —
|
|
166
|
+
| [Brain Core](../brain-core) | Shared infrastructure — 72+ engines | — |
|
|
167
167
|
|
|
168
168
|
## Support
|
|
169
169
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@timmeck/trading-brain",
|
|
3
|
-
"version": "2.31.
|
|
3
|
+
"version": "2.31.28",
|
|
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",
|
|
@@ -41,7 +41,7 @@
|
|
|
41
41
|
},
|
|
42
42
|
"dependencies": {
|
|
43
43
|
"@modelcontextprotocol/sdk": "^1.0.0",
|
|
44
|
-
"@timmeck/brain-core": "2.36.
|
|
44
|
+
"@timmeck/brain-core": "2.36.32",
|
|
45
45
|
"better-sqlite3": "^11.7.0",
|
|
46
46
|
"ccxt": "^4.5.42",
|
|
47
47
|
"chalk": "^5.6.2",
|