Skip to content

Commit a5ddfe7

Browse files
committed
docs: refresh README positioning and feature art
1 parent 8dac26d commit a5ddfe7

5 files changed

Lines changed: 131 additions & 71 deletions

File tree

README.md

Lines changed: 131 additions & 71 deletions
Original file line numberDiff line numberDiff line change
@@ -19,41 +19,34 @@
1919
<a href="https://pypi.org/project/vibe-trading-ai/"><img src="https://img.shields.io/pypi/v/vibe-trading-ai?style=flat&logo=pypi&logoColor=white" alt="PyPI"></a>
2020
<a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow?style=flat" alt="License"></a>
2121
<br>
22-
<img src="https://img.shields.io/badge/Skills-74-orange" alt="Skills">
23-
<img src="https://img.shields.io/badge/Swarm_Presets-29-7C3AED" alt="Swarm">
24-
<img src="https://img.shields.io/badge/Tools-27-0F766E" alt="Tools">
25-
<img src="https://img.shields.io/badge/Data_Sources-6-2563EB" alt="Data Sources">
26-
<br>
2722
<a href="https://github.com/HKUDS/.github/blob/main/profile/README.md"><img src="https://img.shields.io/badge/Feishu-Group-E9DBFC?style=flat-square&logo=feishu&logoColor=white" alt="Feishu"></a>
2823
<a href="https://github.com/HKUDS/.github/blob/main/profile/README.md"><img src="https://img.shields.io/badge/WeChat-Group-C5EAB4?style=flat-square&logo=wechat&logoColor=white" alt="WeChat"></a>
2924
<a href="https://discord.gg/2vDYc2w5"><img src="https://img.shields.io/badge/Discord-Join-7289DA?style=flat-square&logo=discord&logoColor=white" alt="Discord"></a>
3025
</p>
3126

3227
<p align="center">
28+
<a href="#-news">News</a> &nbsp;&middot;&nbsp;
3329
<a href="#-key-features">Features</a> &nbsp;&middot;&nbsp;
30+
<a href="#-shadow-account">Shadow Account</a> &nbsp;&middot;&nbsp;
3431
<a href="#-demo">Demo</a> &nbsp;&middot;&nbsp;
35-
<a href="#-what-is-vibe-trading">What Is It</a> &nbsp;&middot;&nbsp;
36-
<a href="#-get-started">Get Started</a> &nbsp;&middot;&nbsp;
37-
<a href="#-cli-reference">CLI</a> &nbsp;&middot;&nbsp;
38-
<a href="#-api-server">API</a> &nbsp;&middot;&nbsp;
39-
<a href="#-mcp-plugin">MCP</a> &nbsp;&middot;&nbsp;
40-
<a href="#-project-structure">Structure</a> &nbsp;&middot;&nbsp;
32+
<a href="#-quick-start">Quick Start</a> &nbsp;&middot;&nbsp;
33+
<a href="#-examples">Examples</a> &nbsp;&middot;&nbsp;
34+
<a href="#-api-server">API / MCP</a> &nbsp;&middot;&nbsp;
4135
<a href="#-roadmap">Roadmap</a> &nbsp;&middot;&nbsp;
42-
<a href="#-contributing">Contributing</a> &nbsp;&middot;&nbsp;
43-
<a href="#contributors">Contributors</a>
36+
<a href="#-contributing">Contributing</a>
4437
</p>
4538

4639
<p align="center">
47-
<a href="#-get-started"><img src="assets/pip-install.svg" height="45" alt="pip install vibe-trading-ai"></a>
40+
<a href="#-quick-start"><img src="assets/pip-install.svg" height="45" alt="pip install vibe-trading-ai"></a>
4841
</p>
4942

5043
---
5144

5245
## 📰 News
5346

54-
- **2026-05-14** 🧠 **Persistent memory CLI**: Added `vibe-trading memory list/show/search/forget` so users can inspect, search, and prune persistent memory without opening `~/.vibe-trading/memory/` by hand. The implementation keeps non-memory CLI startup fast with lazy imports and hardens memory frontmatter scanning by coercing parsed metadata values back to strings before Rich rendering or recall scoring ([#102](https://github.com/HKUDS/Vibe-Trading/pull/102), thanks @Teerapat-Vatpitak).
55-
- **2026-05-13** 🧭 **Real-price swarm grounding + worker event hygiene**: Swarm runs now pre-fetch market data and ground worker prompts with real prices before analysts start, routing symbol lookups through `_detect_market(code)` and keeping grounding payloads thread-safe ([#93](https://github.com/HKUDS/Vibe-Trading/pull/93)). Worker reports now persist under allowed swarm-run paths, with better `report.md` summary extraction, longer preset timeouts, and redacted/sanitized event previews for cleaner streaming updates ([#84](https://github.com/HKUDS/Vibe-Trading/pull/84)).
56-
- **2026-05-12** 🧾 **Trust Layer run cards**: Backtests now emit reproducible `run_card.json` and `run_card.md` files alongside artifacts, capturing config and strategy hashes, data sources, scalar metrics, validation payloads, warnings, and artifact checksums. The backtest tool also returns the run-card paths so CLI/API callers can surface the evidence package directly.
47+
- **2026-05-14** 🧠 Persistent memory is now inspectable from the CLI via `vibe-trading memory list/show/search/forget` ([#102](https://github.com/HKUDS/Vibe-Trading/pull/102), thanks @Teerapat-Vatpitak).
48+
- **2026-05-13** 🧭 Swarm runs now ground workers with fetched market data and cleaner persisted reports ([#93](https://github.com/HKUDS/Vibe-Trading/pull/93), [#84](https://github.com/HKUDS/Vibe-Trading/pull/84)).
49+
- **2026-05-12** 🧾 Backtests now emit `run_card.json` and `run_card.md` alongside artifacts for reproducible research runs.
5750

5851
<details>
5952
<summary>Earlier news</summary>
@@ -92,72 +85,127 @@
9285

9386
---
9487

95-
## 💡 What Is Vibe-Trading?
96-
97-
Vibe-Trading is an AI-powered multi-agent finance workspace that turns natural language requests into executable trading strategies, research insights, and portfolio analysis across global markets.
98-
99-
### Key Capabilities:
100-
**Natural Language → Strategy** — Describe an idea; the agent writes, tests, and exports trading code<br>
101-
**6 Data Sources, Zero Config** — A-shares, HK/US, crypto, futures & forex with automatic fallback<br>
102-
**29 Expert Teams** — Pre-built multi-agent swarm workflows for investment, trading & risk<br>
103-
**Cross-Session Memory** — Remembers preferences and insights; creates & evolves reusable skills<br>
104-
**7 Backtest Engines** — Cross-market composite testing with statistical validation & 4 optimizers<br>
105-
**Multi-Platform Export** — One-click to TradingView, TDX (通达信/同花顺), and MetaTrader 5
106-
107-
---
108-
10988
## ✨ Key Features
11089

11190
<table width="100%">
11291
<tr>
113-
<td align="center" width="25%" valign="top">
114-
<img src="assets/scene-research.png" height="150" alt="Research"/><br>
115-
<h3>🔍 DeepResearch for Trading</h3>
116-
<img src="https://img.shields.io/badge/74_Skills-FF6B6B?style=for-the-badge&logo=bookstack&logoColor=white" alt="Skills" /><br><br>
117-
<div align="left" style="font-size: 4px;">
118-
• 74 specialist skills with persistent cross-session memory<br>
119-
• Self-evolving: agent creates & refines workflows from experience<br>
120-
• 5-layer context compression — no info lost in long sessions<br>
121-
• Natural-language task routing across all finance domains
92+
<td align="center" width="50%" valign="top">
93+
<img src="assets/scene-research.png" height="130" alt="Self-improving trading agent"/><br>
94+
<h3>🔍 Self-Improving Trading Agent</h3>
95+
<div align="left">
96+
• Natural-language market research<br>
97+
• Strategy drafts and file/web analysis<br>
98+
• Memory-backed workflows
12299
</div>
123100
</td>
124-
<td align="center" width="25%" valign="top">
125-
<img src="assets/scene-swarm.png" height="150" alt="Swarm"/><br>
126-
<h3>🐝 Swarm Intelligence</h3>
127-
<img src="https://img.shields.io/badge/29_Trading_Teams-4ECDC4?style=for-the-badge&logo=hive&logoColor=white" alt="Swarm" /><br><br>
101+
<td align="center" width="50%" valign="top">
102+
<img src="assets/scene-swarm.png" height="130" alt="Multi-agent trading teams"/><br>
103+
<h3>🐝 Multi-Agent Trading Teams</h3>
128104
<div align="left">
129-
• 29 out-of-the-box trading team presets<br>
130-
• DAG-based multi-agent orchestration<br>
131-
• Real-time streaming dashboard with live agent status<br>
132-
• FTS5 session search across all past conversations
105+
• Investment, quant, crypto, and risk teams<br>
106+
• Streaming progress and persisted reports<br>
107+
• Workers grounded with fetched market data
133108
</div>
134109
</td>
135-
<td align="center" width="25%" valign="top">
136-
<img src="assets/scene-backtest.png" height="150" alt="Backtest"/><br>
137-
<h3>📊 Cross-Market Backtest</h3>
138-
<img src="https://img.shields.io/badge/6_Data_Sources-FFD93D?style=for-the-badge&logo=bitcoin&logoColor=black" alt="Backtest" /><br><br>
110+
</tr>
111+
<tr>
112+
<td align="center" width="50%" valign="top">
113+
<img src="assets/scene-backtest.png" height="130" alt="Cross-market data and backtesting"/><br>
114+
<h3>📊 Cross-Market Data & Backtesting</h3>
139115
<div align="left">
140-
• A-shares, HK/US equities, crypto, futures & forex<br>
141-
• 7 market engines + composite cross-market engine with shared capital pool<br>
142-
• Statistical validation: Monte Carlo, Bootstrap CI, Walk-Forward<br>
143-
• 15+ performance metrics & 4 optimizers
116+
• A/HK/US equities, crypto, futures, and forex<br>
117+
• Data fallback and composite backtests<br>
118+
• PIT data, validation, and run cards
144119
</div>
145120
</td>
146-
<td align="center" width="25%" valign="top">
147-
<img src="assets/scene-quant.png" height="150" alt="Quant"/><br>
148-
<h3>🧮 Quant Analysis Toolkit</h3>
149-
<img src="https://img.shields.io/badge/Quant_Tools-C77DFF?style=for-the-badge&logo=wolfram&logoColor=white" alt="Quant" /><br><br>
121+
<td align="center" width="50%" valign="top">
122+
<img src="assets/scene-quant.png" height="130" alt="Trade journal and strategy audit"/><br>
123+
<h3>👥 Trade Journal & Strategy Audit</h3>
150124
<div align="left">
151-
• Factor IC/IR analysis & quantile backtesting<br>
152-
• Black-Scholes pricing & full Greeks calculation<br>
153-
• Technical pattern recognition & detection<br>
154-
• Portfolio optimization via MVO/Risk Parity/BL
125+
• Broker-journal behavior diagnostics<br>
126+
• Rule-based Shadow Account comparisons<br>
127+
• Exportable audit reports and strategy code
155128
</div>
156129
</td>
157130
</tr>
158131
</table>
159132

160-
## 74 Skills across 8 Categories
133+
## 💡 What Is Vibe-Trading?
134+
135+
Vibe-Trading is an open-source research workspace for turning finance questions into runnable analysis. It connects natural-language prompts to market-data loaders, strategy generation, backtest engines, reports, exports, and persistent research memory.
136+
137+
It is designed for research, simulation, and backtesting. It does not execute live trades.
138+
139+
---
140+
141+
## ✨ What You Can Do
142+
143+
| Task | Output |
144+
|------|--------|
145+
| **Ask a trading question** | Market research with tools, data, documents, and reusable session context. |
146+
| **Backtest a strategy idea** | Strategy code, metrics, benchmark context, validation artifacts, and run cards. |
147+
| **Review your own trades** | Broker-journal parsing, behavior diagnostics, rule extraction, and Shadow Account comparisons. |
148+
| **Improve repeated research** | Persistent memory and editable skills turn useful routines into reusable workflows. |
149+
| **Run analyst teams** | Multi-agent research reviews for investment, quant, crypto, macro, and risk workflows. |
150+
| **Ship usable artifacts** | Reports, TradingView Pine Script, TDX, MetaTrader 5, MCP tools, and later research sessions. |
151+
152+
---
153+
154+
## ⚡ Quick Example
155+
156+
```bash
157+
pip install vibe-trading-ai
158+
vibe-trading run -p "Backtest a BTC-USDT 20/50 moving-average strategy for 2024, summarize return and drawdown, then export the report"
159+
```
160+
161+
```bash
162+
vibe-trading --upload trades_export.csv
163+
vibe-trading run -p "Analyze my trading behavior, extract my shadow strategy, and compare it with my actual trades"
164+
```
165+
166+
---
167+
168+
## 👥 Shadow Account
169+
170+
Shadow Account starts from your own trading records instead of a generic strategy template.
171+
172+
Upload a broker export, let the agent summarize your behavior, then compare the actual trading path with a rule-based shadow strategy.
173+
174+
| Step | Agent output |
175+
|------|--------------|
176+
| **1. Read your journal** | Parses broker exports from 同花顺, 东方财富, 富途, and generic CSV formats. |
177+
| **2. Profile your behavior** | Holding days, win rate, PnL ratio, drawdown, disposition effect, overtrading, momentum chasing, and anchoring checks. |
178+
| **3. Extract your rules** | Turns recurring entries/exits into an explicit strategy profile instead of a hand-wavy summary. |
179+
| **4. Run the shadow** | Backtests the extracted rules and highlights rule breaks, early exits, missed signals, and alternative trade paths. |
180+
| **5. Deliver the report** | Produces an HTML/PDF report that can be inspected, archived, or refined in a later session. |
181+
182+
```bash
183+
vibe-trading --upload trades_export.csv
184+
vibe-trading run -p "Analyze my trading behavior, extract my shadow strategy, and compare it with my actual trades"
185+
```
186+
187+
---
188+
189+
## 🧪 Research Workflow
190+
191+
Most runs follow the same evidence path: route the request, load the right market context, execute tools, validate outputs, and keep the artifacts inspectable.
192+
193+
| Layer | What happens |
194+
|-------|--------------|
195+
| **Plan** | Selects the relevant finance skills, tools, data sources, and swarm preset when useful. |
196+
| **Ground** | Pulls A-shares, HK/US equities, crypto, futures, forex, documents, or web context through the available loaders. |
197+
| **Execute** | Generates testable strategy code, runs tools, and uses the matching backtest engine or analysis workflow. |
198+
| **Validate** | Adds metrics, benchmark comparison, Monte Carlo, Bootstrap, Walk-Forward, run cards, and warnings where applicable. |
199+
| **Deliver** | Returns reports, artifacts, tool traces, and exports for TradingView, TDX, MetaTrader 5, MCP clients, or later sessions. |
200+
201+
---
202+
203+
## 🔩 Detailed Capabilities
204+
205+
Detailed inventories are folded below to keep the main README scannable. Open them when you want to inspect the available building blocks.
206+
207+
<details>
208+
<summary><b>Finance Skill Library</b> <sub>74 skills across 8 categories</sub></summary>
161209

162210
- 📊 74 specialized finance skills organized into 8 categories
163211
- 🌐 Complete coverage from traditional markets to crypto & DeFi
@@ -174,7 +222,10 @@ Vibe-Trading is an AI-powered multi-agent finance workspace that turns natural l
174222
| Tool | 10 | `backtest-diagnose`, `report-generate`, `pine-script`, `doc-reader`, `web-reader`, `vnpy-export` |
175223
| Risk Analysis | 1 | `ashare-pre-st-filter` |
176224

177-
## 29 Agent Swarm Team Presets
225+
</details>
226+
227+
<details>
228+
<summary><b>Preset Trading Teams</b> <sub>29 swarm presets</sub></summary>
178229

179230
- 🏢 29 ready-to-use agent teams
180231
- ⚡ Pre-configured finance workflows
@@ -196,7 +247,9 @@ Vibe-Trading is an AI-powered multi-agent finance workspace that turns natural l
196247

197248
</sub>
198249

199-
### 🎬 Demo
250+
</details>
251+
252+
## 🎬 Demo
200253

201254
<div align="center">
202255
<table>
@@ -220,14 +273,21 @@ https://github.com/user-attachments/assets/3754a414-c3ee-464f-b1e8-78e1a74fbd30
220273

221274
---
222275

223-
## 🚀 Quick Started
276+
## 🚀 Quick Start
224277

225278
### One-line install (PyPI)
226279

227280
```bash
228281
pip install vibe-trading-ai
229282
```
230283

284+
Then run a first research task:
285+
286+
```bash
287+
vibe-trading init
288+
vibe-trading run -p "Backtest a BTC-USDT 20/50 moving-average strategy for 2024 and summarize return and drawdown"
289+
```
290+
231291
> **Package name vs commands:** The PyPI package is `vibe-trading-ai`. Once installed, you get three commands:
232292
>
233293
> | Command | Purpose |
@@ -338,7 +398,7 @@ Copy `agent/.env.example` to `agent/.env` and uncomment the provider block you w
338398
| `LANGCHAIN_PROVIDER` | Yes | Provider name (`openrouter`, `deepseek`, `groq`, `ollama`, etc.) |
339399
| `<PROVIDER>_API_KEY` | Yes* | API key (`OPENROUTER_API_KEY`, `DEEPSEEK_API_KEY`, etc.) |
340400
| `<PROVIDER>_BASE_URL` | Yes | API endpoint URL |
341-
| `LANGCHAIN_MODEL_NAME` | Yes | Model name (e.g. `deepseek/deepseek-v3.2`) |
401+
| `LANGCHAIN_MODEL_NAME` | Yes | Model name (e.g. `deepseek-v4-pro`) |
342402
| `TUSHARE_TOKEN` | No | Tushare Pro token for A-share data (falls back to AKShare) |
343403
| `TIMEOUT_SECONDS` | No | LLM call timeout, default 120s |
344404
| `API_AUTH_KEY` | Recommended for network deployments | Bearer token required when the API is reachable from non-local clients |
@@ -357,10 +417,10 @@ Vibe-Trading is a tool-heavy agent — skills, backtests, memory, and swarms all
357417
| Tier | Examples | When to use |
358418
|------|----------|-------------|
359419
| **Best** | `anthropic/claude-opus-4.7`, `anthropic/claude-sonnet-4.6`, `openai/gpt-5.4`, `google/gemini-3.1-pro-preview` | Complex swarms (3+ agents), long research sessions, paper-grade analysis |
360-
| **Sweet spot** (default) | `deepseek/deepseek-v3.2`, `x-ai/grok-4.20`, `z-ai/glm-5.1`, `moonshotai/kimi-k2.5`, `qwen/qwen3-max-thinking` | Daily driver — reliable tool-calling at ~1/10 the cost |
420+
| **Sweet spot** (default) | `deepseek-v4-pro`, `deepseek/deepseek-v4-pro`, `x-ai/grok-4.20`, `z-ai/glm-5.1`, `moonshotai/kimi-k2.5`, `qwen/qwen3-max-thinking` | Daily driver — reliable tool-calling at ~1/10 the cost |
361421
| **Avoid for agent use** | `*-nano`, `*-flash-lite`, `*-coder-next`, small / distilled variants | Tool-calling is unreliable — the agent will appear to "answer from memory" instead of loading skills or running backtests |
362422

363-
The default `agent/.env.example` ships with `deepseek/deepseek-v3.2` — the cheapest option in the sweet-spot tier.
423+
The default `agent/.env.example` ships with DeepSeek official API + `deepseek-v4-pro`; OpenRouter users can use `deepseek/deepseek-v4-pro`.
364424

365425
---
366426

assets/scene-backtest.png

-583 KB
Loading

assets/scene-quant.png

-17.2 KB
Loading

assets/scene-research.png

-454 KB
Loading

assets/scene-swarm.png

-598 KB
Loading

0 commit comments

Comments
 (0)