Does tradememory-protocol auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Is tradememory-protocol free?

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Data

Plugin

tradememory-protocol

Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.

FLOW.md

mnemox-ai@mnemox-ai

GitHub

Plugin Signal79/100Solid

maintained95

capable52

documented100

adopted67

Install

$ npx -y skills add mnemox-ai/tradememory-protocol --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python Bash Ruby SQLite REST API

+5 tags

Docker Git GitHub Anthropic MCP

1,408

Stars

165

Forks

Active

Maintenance

Python

Language

MIT

License

10d ago

Last commit

5mo ago

Created

Repo: mnemox-ai/tradememory-protocol

In this plugin

5 commands 5 skills 1 MCP

See everything inside

What's inside

Badges

README

Read on GitHub

Your trading AI has amnesia. And regulators are starting to notice.

It makes the same mistakes every session. It can't explain why it traded. It forgets everything when the context window ends. Meanwhile, MiFID II is raising the bar for algorithmic decision documentation (Article 17). The EU AI Act demands systematic logging of AI actions (Article 14). Your competitors' agents are learning from every trade.

The AI trading stack is missing a layer. Every MCP server handles execution — placing orders, fetching prices, reading charts. None handle memory.

Your agent can buy 100 shares of AAPL but can't answer: "What happened last time I bought AAPL in this condition?"

TradeMemory is the memory layer. One pip install, and your AI agent remembers every trade, every outcome, every mistake — with a SHA-256 tamper-evident audit trail.

Used in production by traders running pre-flight checklists before every position, and by EA systems logging thousands of decisions daily.

What it does

Before trading: ask your memory — what happened last time in this market condition? How did it end?
After trading: one call records everything — five memory layers update automatically
Safety rails: confidence tracking, drawdown alerts, losing streak detection — the system tells you when to stop

Works with any market (stocks, forex, crypto, futures), any broker, any AI platform. TradeMemory doesn't execute trades or touch your money — it only records and recalls.

Quick Start

pip install tradememory-protocol

Add to Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "tradememory": {
      "command": "uvx",
      "args": ["tradememory-protocol"]
    }
  }
}

Then tell Claude: "Record my AAPL long at $195 — earnings beat, institutional buying, high confidence."

# Claude Code
claude mcp add tradememory -- uvx tradememory-protocol

# From source
git clone https://github.com/mnemox-ai/tradememory-protocol.git
cd tradememory-protocol && pip install -e . && python -m tradememory

# Docker
docker compose up -d

Full walkthrough: Getting Started (Trader Track + Developer Track)

Who uses TradeMemory

	US Equity Trader	Forex EA System	Compliance Team
Market	Stocks (AAPL, TSLA, ...)	XAUUSD (Gold)	Multi-asset
How	Pre-flight checklist before every trade	Automated sync from MT5	Full decision audit trail
Key value	Discipline system — memory before every decision	Record why signals were blocked, not just executed	SHA-256 tamper-evident records for regulators
Details	Read more →	Read more →	Read more →

How it works

Recall — Before trading, retrieve past trades weighted by outcome quality, context similarity, recency, confidence, and emotional state (OWM Framework)
Record — After trading, one call to remember_trade writes to five memory layers: episodic, semantic, procedural, affective, and trade records
Reflect — Daily/weekly/monthly reviews detect behavioral drift, strategy decay, and trading mistakes
Audit — Every decision is SHA-256 hashed at creation. Export anytime for review or regulatory submission

MCP Tools

Category	Tools	Description
Memory	`remember_trade` · `recall_memories`	Record and recall trades with outcome-weighted scoring
State	`get_agent_state` · `get_behavioral_analysis`	Confidence, drawdown, streaks, behavioral patterns
Planning	`create_trading_plan` · `check_active_plans`	Prospective plans with conditional triggers
Risk	`check_trade_legitimacy`	5-factor pre-trade gate (full / reduced / skip)
Audit	`export_audit_trail` · `verify_audit_hash`	SHA-256 tamper detection + bulk export

Category	Tools
Core Memory	`get_strategy_performance` · `get_trade_reflection`
OWM Cognitive	`remember_trade` · `recall_memories` · `get_behavioral_analysis` · `get_agent_state` · `create_trading_plan` · `check_active_plans`
Risk & Governance	`check_trade_legitimacy` · `validate_strategy` · `compute_dqs`
Evolution	`evolution_fetch_market_data` · `evolution_discover_patterns` · `evolution_run_backtest` · `evolution_evolve_strategy` · `evolution_get_log`
Audit	`export_audit_trail` · `verify_audit_hash` · `verify_audit_chain` · `get_daily_root`

REST API: 35+ endpoints for trade recording, reflections, risk, MT5 sync, OWM, evolution, and audit. Full reference →

Pricing

	Community	Pro	Enterprise
Price	Free	$29/mo (Coming Soon)	Contact Us
MCP tools	20 tools	20 tools	20 tools
Storage	SQLite, self-hosted	Hosted API	Private deployment
Dashboard	—	Web dashboard	Custom dashboard
Compliance	Audit trail included	Audit trail included	Compliance reports + SLA
Support	GitHub Issues	Priority support	Dedicated support
	Get Started →	Coming soon	dev@mnemox.ai

Need Help Integrating?

Building a trading AI agent and want battle-tested memory architecture?

Free 30-min strategy call — we'll map your agent's memory needs and design guardrails for your specific workflow.

dev@mnemox.ai | Book a call

We've helped traders build pre-flight checklists, connect MT5/Binance, and design custom guardrails for forex, equities, and crypto.

Enterprise & Compliance

Every trading decision your agent makes — including decisions not to trade — is recorded as a Trading Decision Record (TDR). Per-record SHA-256 content hashes are linked into a forward-chained audit ledger; every UTC day is summarised by a Merkle root which itself chains across days. Tampering with any historical record invalidates every subsequent link.

Regulation	Requirement	TradeMemory Coverage
MiFID II Article 17	Record every algorithmic trading decision factor	Full decision chain: conditions, filters, indicators, execution
EU AI Act Article 14	Human oversight of high-risk AI systems	Explainable reasoning + memory context for every decision
EU AI Act Article 12	Automatic, tamper-resistant logs over system lifetime	Linked SHA-256 chain + daily Merkle roots (RFC 3161 TSA in Phase 1.5)

# Verify a single record hasn't been tampered with
verify_audit_hash(trade_id="MT5-7047640363")
# → {"verified": true, "chain_entry": {"sequence_num": 42, ...}}

# Walk the entire chain (or a slice) end-to-end
verify_audit_chain(from_seq=1, to_seq=None)
# → {"verified": true, "checked_count": 1284, "first_break_at": null}

# Daily Merkle root — single 32-byte anchor over every TDR for that day
get_daily_root(date="2026-05-14")
# → {"verified": true, "root_hash": "a05544...", "record_count": 18}

# Bulk export for regulatory submission
GET /audit/export?strategy=VolBreakout&start=2026-03-01&format=jsonl

See LIMITATIONS.md for the full audit-chain maturity statement, including what's not in v0.5.2 yet (TSA timestamping, external anchoring, zkML proof of inference).

Need a custom deployment for your fund? → dev@mnemox.ai

Security

Never touches API keys. TradeMemory does not execute trades, move funds, or access wallets.
Read and record only. Your agent passes decision context to TradeMemory. It stores it. That's it.
Local-first. The only outbound call is RFC 3161 trusted timestamping of daily audit roots — a 32-byte hash, no trade data (on by default; disable with TRADEMEMORY_TSA=off). Nothing else leaves your machine.
SHA-256 chained audit ledger. Every record is hashed at creation and linked to the previous record. Daily Merkle roots anchor the chain. Verify integrity at the record, slice, or day level. Tampering is detectable at every level; external anchoring (TSA by default) is on the roadmap.
1,400+ tests passing. Full test suite with CI.

Research Status

TradeMemory's OWM framework is grounded in cognitive science (Tulving 1972) and reinforcement learning (Schaul et al. 2015). Current status:

OWM five-factor scoring: implemented, tested (1,400+ tests)
Statistical validation: DSR, MBL implemented (Bailey-de Prado 2014)
Audit trail: SHA-256 tamper-evident TDR
Evolution engine: research phase (strategy generation works, statistical gate pass rate under optimization)
Hybrid recall: OWM-only mode active, vector fusion available when embeddings configured
Empirical validation: ongoing (n=40 trades, target n>=100 for statistical significance)

Documentation

Doc	Description
Getting Started	Install → first trade → pre-flight checklist
Use Cases	3 real-world production scenarios
API Reference	All REST endpoints
OWM Framework	Outcome-Weighted Memory theory
Architecture	System design & layer separation
Tutorial	Detailed walkthrough
MT5 Setup	MetaTrader 5 integration
Research Log	Evolution experiments & data
Failure Taxonomy	11 trading AI failure modes
中文版	Traditional Chinese

Contributing

See Contributing Guide · Security Policy

MIT — see LICENSE. For educational/research purposes only. Not financial advice.

File tree

556

mnemox-ai/tradememory-protocolView on GitHub

.devcontainer/
  devcontainer.json
.dockerignore
.env.example
.github/
  CONTRIBUTING.md
  DISCUSSION_TEMPLATE/
    ideas.yml
    q-and-a.yml
    show-and-tell.yml
  ISSUE_TEMPLATE/
    bug_report.yml
    config.yml
    feature_request.yml
    question.yml
  PULL_REQUEST_TEMPLATE.md
  SECURITY.md
  workflows/
    ci.yml
    live-executor.yml
    publish.yml
    registry-publish.yml
.gitignore
.pre-commit-config.yaml
.skills/
  strategy-validator/
    SKILL.md
  tradememory/
    scripts/
      install.sh
      setup_mt5.sh
    SKILL.md
AGENTS.md
alembic/
alembic.ini
  env.py
  README
  script.py.mako
  versions/
    001_initial_schema.py
    002_add_vector.py
    003_recall_events.py
assets/
  before-after-dark.png
  before-after-light.png
  before-after-zh-dark.png
  before-after-zh-light.png
  evolution-zh.png
  evolution.png
  fb_post_whale_fingerprint.md
  generate_evolution_zh.html
  generate_evolution.html
  generate_header_zh.html
  generate_header.html
  generate_l1l2l3.html
  generate_memory-pipeline_zh.html
  generate_owm-factors_zh.html
  generate_owm.html
  generate_schema_zh.html
  generate_schema.html
  generate_whale_compare.html
  header-zh.png
  header.png
  hero-dark.png
  hero-light.png
  hero-zh-dark.png
  hero-zh-light.png
  memory-pipeline-zh.png
  memory-pipeline.png
  owm-architecture-dark.png
  owm-architecture-light.png
  owm-architecture-zh-dark.png
  owm-architecture-zh-light.png
  owm-factors-zh.png
  owm-factors.png
  schema-zh.png
  schema.png
  screenshots/
    demo-full.txt
    demo-l1.txt
    demo-l2.txt
    demo-l3.txt
  whale_compare.png
CHANGELOG.md
CLAUDE.md
dashboard/
  .env.production
  .gitignore
  eslint.config.js
  index.html
  package-lock.json
  package.json
  public/
    vite.svg
  README.md
  requirements.txt
  src/
    api/
      .gitkeep
      client.ts
      hooks.ts
      types.ts
    App.tsx
    assets/
      react.svg
    components/
      cards/
        .gitkeep
        BayesianBeliefs.module.css
        BayesianBeliefs.tsx
        MetricCard.module.css
        MetricCard.tsx
        ReflectionCard.module.css
        ReflectionCard.tsx
      charts/
        .gitkeep
        AdjustmentTimeline.module.css
        AdjustmentTimeline.tsx
        ConfidenceCalibration.tsx
        ConfidenceCalibration.web.tsx
        DreamComparison.tsx
        DreamComparison.web.tsx
        EquityCurveChart.tsx
        EquityCurveChart.web.tsx
        MemoryGrowth.tsx
        MemoryGrowth.web.tsx
        OWMScoreTrend.module.css
        OWMScoreTrend.tsx
        OWMScoreTrend.web.tsx
        ResonanceGauge.module.css
        ResonanceGauge.tsx
        ResonanceGauge.web.tsx
        RollingMetricsChart.tsx
        RollingMetricsChart.web.tsx
        StrategyHeatmap.module.css
        StrategyHeatmap.tsx
        StrategyHeatmap.web.tsx
      layout/
        .gitkeep
        Nav.module.css
        Nav.tsx
        PageShell.module.css
        PageShell.tsx
        Sidebar.module.css
        Sidebar.tsx
      ui/
        .gitkeep
        ChartTooltip.module.css
        ChartTooltip.tsx
        EmptyState.module.css
        EmptyState.tsx
        ErrorState.module.css
        ErrorState.tsx
        Skeleton.module.css
        Skeleton.tsx
    hooks/
      useScrollReveal.ts
    i18n/
      en.ts
      index.ts
      zh-TW.ts
    main.tsx
    mock/
      .gitkeep
      adjustments.json
      beliefs.json
      confidence-cal.json
      dream-results.json
      equity-curve.json
      evolution.json
      memory-growth.json
      overview.json
      owm-score-trend.json
      reflections.json
      rolling-metrics.json
      strategy-im.json
      strategy-pb.json
      strategy-vb.json
    pages/
      .gitkeep
      DreamsPage.module.css
      DreamsPage.tsx
      EvolutionPage.module.css
      EvolutionPage.tsx
      IntelligencePage.module.css
      IntelligencePage.tsx
      OverviewPage.module.css
      OverviewPage.tsx
      ReflectionsPage.module.css
      ReflectionsPage.tsx
      StrategiesPage.module.css
      StrategiesPage.tsx
    theme/
      .gitkeep
      components.css
      global.css
      variables.css
    utils/
      csvExport.ts
      formatRelativeTime.ts
  tsconfig.app.json
  tsconfig.json
  tsconfig.node.json
  vite.config.ts
data/
  sample_xauusd_m15.csv
  whale_0x7a16fF_trades.csv
deploy/
  Caddyfile
docker-compose.hosted.yml
docker-compose.yml
Dockerfile
docs/
  adr/
    001-owm-multiplicative-scoring.md
    002-sqlite-over-postgres.md
    003-mcp-protocol-choice.md
    004-evolution-statistical-gates.md
  anti-resonance-package.md
  API.md
  ARCHITECTURE.md
  article-adding-memory-to-ea.md
  AWESOME_LISTS.md
  BEFORE_AFTER.md
  blog-cover.png
  blog-evolution-experiment-zh.md
  blog-evolution-experiment.md
  blueprint.docx
  DAILY_REFLECTION_SETUP.md
  deployment.md
  example_strategy_prompt.md
  EXECUTION_LOG.md
  generate_cover.py
  GETTING_STARTED.md
  hosted-api-spec.md
  MT5_SYNC_SETUP.md
  MT5_SYNC_V3.md
  OWM_FRAMEWORK.md
  QUICK_START.md
  README_ZH.md
  REFLECTION_ENGINE_GUIDE.md
  REFLECTION_FORMAT.md
  research/
  RESEARCH_LOG.md
    arxiv-paper-behavioral-drift.html
    arxiv-paper-behavioral-drift.md
    arxiv-paper-behavioral-drift.pdf
    build_arxiv_pdf.py
    owm-technical-article.md
    self-calibrating-agent-research-report.md
    validation_step1_results.json
    validation_step2_results.json
    validation_step3_results.json
    validation_step4_results.json
  ROADMAP.md
  SCHEMA.md
  social-preview.png
  specs/
    2026-03-25-mcp-onboarding-design.md
    ssrt-phase2-spec.md
    ssrt-spec.md
  superpowers/
    plans/
      2026-04-05-readme-rewrite.md
      2026-07-14-policy-evolution-plane-implementation.md
    specs/
      2026-04-05-readme-rewrite-design.md
      2026-07-14-policy-evolution-plane-design.md
  TDR_SPEC_v1.md
  trading-ai-failure-taxonomy.md
  TUTORIAL_ZH.md
  TUTORIAL.md
  USE_CASES.md
  validation/
  VALIDATION_RESULTS.md
    ablation_comparison.png
    baseline_distribution.png
    time_bias_hourly.png
    walk_forward_windows.png
glama.json
hosted/
  __init__.py
  server.py
LICENSE
LIMITATIONS.md
llms.txt
pyproject.toml
README.md
render.yaml
requirements.txt
research/
  level2/
    analyze.py
    baselines_clean.py
    compare_maxdd.json
    compare_maxdd.py
    cusum_agent.py
    h_sensitivity_sync.py
    h_sensitivity.json
    h_sensitivity.py
    maxdd_baseline.py
    results.json
    RESULTS.md
    robustness_no_btc1h.json
    robustness_without_btc1h.py
    run_matrix.py
  README.md
  requirements.txt
scripts/
  analyze_trader.py
  backfill_audit_chain.py
  daily_reflection.py
  demo.py
  export_mt5_csv.py
  generate_index.py
  live_executor.py
  mt5_sync_v3.py
  mt5_sync.py
  platform/
    IndexGenerator_AutoStart.xml
    install_autostart.bat
    install.sh
    MT5SyncV3_AutoStart.xml
    run_index_generator.bat
    start_daily_reflection.bat
    start_mt5_sync_v3.bat
    start_services.bat
    start_trade_adapter.bat
    start_tradememory.pyw
    stop_services.bat
    TradeMemory_AutoStart.xml
    watchdog_mt5_sync.bat
  requirements-live.txt
  research/
    analyze_defi_behavior.py
    binance_sync.py
    check_mt5.py
    compare_defi_fingerprints.py
    daily_monitor.py
    daily_review.py
    dashboard.py
    evolution_binance_test.py
    evolution_demo.py
    evolution_live_test.py
    experiment_memory_injection.py
    experiment_memory_oos.py
    experiment_permutation_test.py
    export_backtest_trades.py
    fb_screenshot.py
    fetch_whale_trades.py
    generate_backtest_mock.py
    generate_readme_assets_zh.py
    generate_readme_assets.py
    generate_screenshots.py
    generate_validation_charts.py
    migrate_sqlite_to_pg.py
    migrate_strategy_names.py
    output/
      defi_fingerprint.json
      fingerprint_comparison.json
    parse_batch_results.py
    phase4_results.json
    phase4_results.md
    phase5_results.json
    phase5_results.md
    program.md
    random_baseline_demo.py
    record_demo.py
    replay_monitor.py
    run_b1_stability.py
    run_b2_transfer.py
    run_extended_oos.py
    run_grid_wfo.py
    run_llm_step0.py
    run_llm_wfo.py
    run_phase4.py
    run_phase5.py
    run_real_baseline.py
    run_time_bias_test.py
    run_walk_forward.py
    seed_backtest_trades.py
    ssrt_experiments.py
    trade_advisor.py
    validate_l2_patterns.py
    weekly_report.py
  strategy_definitions.py
  trade_adapter.py
server.json
skills/
  binance-skills-hub/
    trade-memory/
      SKILL.md
  tradememory-bridge/
    SKILL.md
smithery.yaml
src/
  tradememory/
    __init__.py
    adaptive_risk.py
    audit/
... 229 more

FAQ

tradememory-protocol is a Claude Code plugin with 5 hand-picked skills for data work, indexed on Flowy. Install it with the command on its page. It includes trade-memory, tradememory-bridge, evolution-engine. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is tradememory-protocol?: Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.
How do I install tradememory-protocol?: Run these in Claude Code: npx -y skills add mnemox-ai/tradememory-protocol --agent claude-code. Then prompt normally.
Does tradememory-protocol auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is tradememory-protocol free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.