uvx aipa-cli

aipa

uvx

1. Use plain

   uvx

   for fast cached execution:

   uvx aipa-cli get-ohlcv-data VCB

2. Fallback on failure — if a command fails with a schema or missing argument error, retry with

   @latest

   :

   uvx aipa-cli@latest get-ohlcv-data VCB

aipa

pip

pip install --upgrade aipa-cli

uvx aipa-cli

aipa

uvx

• Vietnamese stocks (

  source: vn

  ): VIC, VCB, FPT, HPG, VNM, MBB, TCB, CTG, VPB, HDB, etc.
• Cryptocurrencies (

  source: crypto

  ): BTCUSDT, ETHUSDT, BNBUSDT, SOLUSDT, etc.
• Global/Yahoo (

  source: global/yahoo

  ): AAPL, TSLA, NVDA, SPY, etc.
• SJC Gold (

  source: sjc

  ): SJC gold prices

• POC (Point of Control): price level with the highest volume
• Value Area: price range containing the target % of total volume (default 70%)
• Statistics: volume-weighted mean, median, standard deviation, skewness
• Profile: binned price levels with volume, percentage, and visual bar chart

• stdout: The OHLCV data table. This is what you should present to the user.
• stderr: Status messages with structured markers.

• English: "Data by AIPriceAction | AI-powered analysis — may contain errors. Verify before trading."
• Vietnamese: "Dữ liệu bởi AIPriceAction | Phân tích bởi AI — có thể chứa sai sót. Vui lòng kiểm chứng trước khi giao dịch."

Version gate:

aipa fundamentals

requires aipa-cli >= 0.1.43. Verify before use:

bash

aipa --version
# or
uvx aipa-cli --version

If the version is < 0.1.43, upgrade:

uvx aipa-cli@latest fundamentals info ACB

or

pip install --upgrade aipa-cli

.

vn.zip

IMPORTANT:

--lang

and

--no-system-prompt

are NOT valid flags for

aipa fundamentals

commands. Do NOT add them — the commands do not accept them and will error or ignore them silently. Fundamentals commands only accept the flags documented below.

1. --watchlist NAME

   — resolve from predefined (VN30, VINGROUP...) or custom watchlists
2. Positional

   tickers

   — explicit list
3. Default — all VN tickers from ticker metadata

• All filters are optional — pass only what you need
• Tickers with missing data for a filtered field are excluded
• Range filters are inclusive:

  --roe-min 0.15

  matches

  roe >= 0.15

• --industry

  is case-insensitive substring match (e.g.

  "ngân hàng"

  matches

  "Ngân hàng"

  )

• Nhóm Ngân hàng (Banking): VCB, BID, CTG, TCB, MBB, ACB, VPB, HDB, SHB, TPB, VIB, SSB, MSB, STB, LPB, EIB.
• Nhóm Bất động sản (Real Estate): VIC, VHM, VRE, VPL, DIG, CEO, L14, TCH, HHS, VGC, IDC.
• Nhóm Chứng khoán (Securities): SSI, VND, HCM, VCI, SHS, VIX, VDS.
• Nhóm Trụ cột / Sản xuất & Bán lẻ (Blue-chips / Core Economy): HPG, HSG, NKG, FPT, MWG, GAS, GVR, PLX, BSR, MSN, VNM, SAB.
• Nhóm Hệ sinh thái (Corporate Ecosystems):
  • Họ Vingroup: VIC, VHM, VRE, VPL.
  • Họ Bầu Thụy: STB, LPB, THD, HAG.
  • Họ Gelex ("Tuấn Mượt"): GEX, GEE, VIX, VGC, EIB, IDC.
  • Họ Hoàng Huy: TCH, HHS.
  • Họ A7: DIG, CEO, L14.
  • Họ TTC (Thành Thành Công): SBT, GEG, VDS.
  • Họ Masan: MSN, MCH, MSR, MML, VCF, VSN, NET.

1. NEVER generate, guess, estimate, or hallucinate any numbers — prices, volumes, MA values, MA scores, percentages, dates, or any financial data. Only use data from tool results or user-provided context
2. NEVER mention a specific number unless it appears in your tool results or user-provided context
3. Use tools proactively — call

   aipa get-ohlcv-data

   and/or

   aipa performers

   BEFORE answering price-related questions. Only fall back to asking the user if tools fail
4. When researching news or events, ALWAYS include the source name (e.g., "Source: CafeF", "Source: VNExpress")
5. Trading Hours: VN market trades 09:00–15:00 ICT (UTC+7), Mon–Fri. Crypto 24/7. If the latest bar shows unusually low volume, the session may still be in progress

• Row-by-Row Verification: When reading OHLCV data output from the CLI, you MUST strictly read the exact row for the exact date requested. Do not accidentally read data from an adjacent row or a different ticker's block in multi-ticker outputs.
• Precision Filter with Grep: To minimize reading errors and context volume, always use

  grep -E

  to isolate your target dates across one or multiple tickers. Use

  "time"

  as your header anchor.
  • Surgical view (Header + Today + Breakout Day):

    uvx aipa-cli get-ohlcv-data TCB MSB STB | grep -E "time|2026-05-27|2026-05-07"

  • Comparing recent days:

    uvx aipa-cli get-ohlcv-data VND | grep -E "time|2026-05-27|2026-05-26"

• Explicit Value Comparison: Before concluding whether a trend is broken or intact, explicitly state the values being compared:

  [Close Price]

  vs

  [MA/EMA Value]

  .
  • Example: "Close is 17.750, EMA20 is 16.881. 17.750 > 16.881 → Price is ABOVE EMA20 (Trend intact)."
• Breakout Validation: A breakout (significant positive price change + high volume) creates a critical support at the structural breakout level — the top of the pre-breakout base/range, the prior swing high, or the pattern's neckline. The breakout candle's Low is NOT a reliable invalidation point: it can extend well below the structural level due to gap opens, intraday noise, or volatile entry bars.
  • The correct invalidation is a fall back below the structural breakout level, not below the candle's Low.
  • If price pulls back but stays above the structural level, the breakout is intact — this is a healthy pullback.
  • If price falls below the structural breakout level, it is a Failed Breakout / Structural Violation.
  • Action: Always identify the pre-breakout structure first. Only then assess whether a pullback is healthy (above structure) or a failure (below structure).

1. No API key or backend needed:

   get-ohlcv-data

   fetches from public S3 archives. Works without

   OPENAI_API_KEY

   or a running backend.
2. Auto-uppercase: Ticker symbols are automatically uppercased.

   vcb

   ,

   btcusdt

   ,

   spy

   all work.
3. Default is 20 bars: If the user doesn't specify a count, they get 20 bars. Use

   --limit 50

   or

   --limit 100

   when more context is needed.

4. --no-ma --no-system-prompt

   for clean data: When the user wants raw numbers for their own analysis or a spreadsheet, strip everything except OHLCV with these flags.
5. For AI analysis, use

   aipa analyze

   : If the user wants insights, patterns, or recommendations, use the

   aipa-analyze

   skill instead. This skill is for raw data only.
6. Date range vs limit: Use

   --start-date

   /

   --end-date

   for specific periods. Use

   --limit

   for "last N bars". Don't combine both — the CLI handles conflicts gracefully but the intent is clearer with one approach.

7. --ema

   flag controls SMA vs EMA: By default, SMA is shown. Add

   --ema

   to switch to EMA.
8. Multi-ticker support: Pass multiple space-separated tickers to fetch them in one call (e.g.

   aipa get-ohlcv-data VCB TCB MBB

   ). The output table includes a

   symbol

   column to distinguish rows.
9. Use

   aipa live-data

   for market overview: When you need to identify the most active tickers or get a broad market snapshot, use

   aipa live-data

   instead of fetching individual tickers. It returns the latest candle sorted by trading value. Call it first with no arguments to discover what's moving, then drill into specific tickers with

   get-ohlcv-data

   .
10. Use

    aipa ticker-list

    to discover tickers: When you need to know what tickers are available or find tickers in a specific sector, use

    aipa ticker-list

    . Add

    --group

    to filter by sector (e.g.

    NGAN_HANG

    for banking) and

    --compact

    to get a comma-separated list for passing to other commands.
11. Use

    aipa performers

    for ranking — run multiple perspectives: When the user asks about market movers, top stocks, or "what's happening", run

    aipa performers

    with multiple

    --sort-by

    values to get a multi-perspective view. Always run at least these two: default (price change) and value (trading value). Add MA scores when the user cares about trends. Run them all — do not pick just one:
    bash

    aipa performers                                          # price change — top gainers / worst losers
    aipa performers --sort-by value                          # trading value — where the money flows
    aipa performers --sort-by ma50_score                     # MA50 trend — strongest/weakest medium-term trends
    aipa performers --sort-by ma20_score                     # MA20 trend — strongest/weakest short-term trends
    aipa performers --sort-by total_money_changed            # money flow change — unusual capital activity
    aipa performers --group NGAN_HANG --sort-by value        # banking sector by trading value
    aipa performers --group CHUNG_KHOAN --sort-by close_changed  # securities sector top gainers

    Cross-referencing these lists gives much richer insight than any single sort. A ticker appearing in both the top gainers AND top value lists is more significant than one appearing in only one. The AI agent can also call the

    get_performers

    tool directly.
12. Use

    aipa volume-profile

    for volume analysis: When you need to identify key price levels based on traded volume, use

    aipa volume-profile

    . It shows where the most volume was traded (POC), the value area, and volume-weighted statistics from 1-minute data. Prefer multi-day ranges (

    --start-date

    +

    --end-date

    , at least 20 trading days) over single-day profiles — multi-day ranges produce more reliable support/resistance levels and smooth out intraday noise. The AI agent can also call the

    get_volume_profile

    tool directly.