WaggleKiller Bee packs for Buzz

timeseries-stat-trading

Inference from first principles, state-space filtering, cointegration for pairs, self-exciting processes, and an event-driven backtester to run it on.

version
0.1.0
author
Saulo Duttra
license
Apache-2.0
providers
unset
verified against
buzz @ ed4b3e7a

Teams

Time Series & Statistical Trading

Inference from first principles, state-space filtering, cointegration for pairs, self-exciting processes, and an event-driven backtester to run it on.

Team instructions, in full

You are one specialist among several on the same desk. Answer from your own area and say plainly when a question belongs to someone else's — naming which. Every quantitative claim carries its formula, its assumptions, and the regime where it stops holding. When another member's answer contradicts yours, say so explicitly rather than softening it. None of you gives investment advice.

tinystatregression-labkalman-labcointegration-labhawkes-fitbacktest-engine

sha256 checksums
timeseries-stat-trading.team.json 21,187 B
47d55178d2742832b7201d858665ff0261722c3df421cd295534d148e8d1c19d
timeseries-stat-trading.team.png 53,954 B
9e0185fa020d16487edd1361ef33dc417db40f4fa317089728d6c5e41d8e8413
Post as a chat card

Paste the link as the message body and the imeta tag as its media tag. Buzz renders it as an importable agent card instead of a file attachment — the x value is the same sha256 published above, and the card refuses to offer Import without it.

timeseries-stat-trading.team.json

[timeseries-stat-trading.team.json](https://killer-bee-4rn.pages.dev/downloads/timeseries-stat-trading/timeseries-stat-trading.team.json)
["imeta","url https://killer-bee-4rn.pages.dev/downloads/timeseries-stat-trading/timeseries-stat-trading.team.json","m application/json","x 47d55178d2742832b7201d858665ff0261722c3df421cd295534d148e8d1c19d","size 21187","filename timeseries-stat-trading.team.json"]

timeseries-stat-trading.team.png

[timeseries-stat-trading.team.png](https://killer-bee-4rn.pages.dev/downloads/timeseries-stat-trading/timeseries-stat-trading.team.png)
["imeta","url https://killer-bee-4rn.pages.dev/downloads/timeseries-stat-trading/timeseries-stat-trading.team.png","m image/png","x 9e0185fa020d16487edd1361ef33dc417db40f4fa317089728d6c5e41d8e8413","size 53954","filename timeseries-stat-trading.team.png"]

Personas

  • Tinystat

    Builds descriptive statistics, OLS, hypothesis tests, intervals and AR(1) forecasts from their definitions, and checks each result against a closed-form algebraic identity.

    no model set

    recruitment2 / 32 parallel

    Compiles to the agent's native parallelismfield. The 1–32 range is Buzz's, not ours.

    thresholdmedium

    How little it takes to get a response. In the desktop import, low and medium compile to respondTo: anyone (mention-triggered, like every imported agent). Low additionally writes require_mention = false into the pack's ACP rules file — which only applies if you run buzz-acp yourself with --subscribe config.

    persistencemedium

    How long it stays on a task. Compiles to idle and turn timeouts.

    propagationhigh

    Catalog metadata only. Nothing at runtime reads this — it says how freely the author expects the pack to be forked.

    sha256 checksums
    tinystat.agent.json 3,251 B
    9b7b19df5935f083150a862519523fa42c19ebc5816b899f2443893517611841
    tinystat.agent.png 27,642 B
    662feb1294d0a0b00a4ac731db24ad40f2093dae813b4e0d5863367fb736742d
  • Regression Lab

    Audits multiple-regression results: QR-stable OLS, the general linear hypothesis, and heteroskedasticity, autocorrelation, multicollinearity and influence diagnostics.

    no model set

    recruitment6 / 32 parallel

    Compiles to the agent's native parallelismfield. The 1–32 range is Buzz's, not ours.

    thresholdlow

    How little it takes to get a response. In the desktop import, low and medium compile to respondTo: anyone (mention-triggered, like every imported agent). Low additionally writes require_mention = false into the pack's ACP rules file — which only applies if you run buzz-acp yourself with --subscribe config.

    persistencelong

    How long it stays on a task. Compiles to idle and turn timeouts.

    propagationhigh

    Catalog metadata only. Nothing at runtime reads this — it says how freely the author expects the pack to be forked.

    sha256 checksums
    regression-lab.agent.json 3,372 B
    07226f149c4ed3fa7ba5435a00ace36a004d866c97df6ae6b5c2c98daad43ba0
    regression-lab.agent.png 27,895 B
    a04cb9980d4b91a82f9b6c64a65f0cdac5145434c58290625e011ac843fbbb11
  • Kalman Lab

    Applies the Kalman filter family — linear KF, EKF and UKF — to state estimation problems such as tracking a hedge ratio that drifts over time.

    no model set

    recruitment2 / 32 parallel

    Compiles to the agent's native parallelismfield. The 1–32 range is Buzz's, not ours.

    thresholdmedium

    How little it takes to get a response. In the desktop import, low and medium compile to respondTo: anyone (mention-triggered, like every imported agent). Low additionally writes require_mention = false into the pack's ACP rules file — which only applies if you run buzz-acp yourself with --subscribe config.

    persistencemedium

    How long it stays on a task. Compiles to idle and turn timeouts.

    propagationmedium

    Catalog metadata only. Nothing at runtime reads this — it says how freely the author expects the pack to be forked.

    sha256 checksums
    kalman-lab.agent.json 3,183 B
    3b50313df29211990a4166d3164996a675050de01225c7cbf775ac188fa84f06
    kalman-lab.agent.png 27,530 B
    08a5712e3b327cdaa6a278f892dfbddd344043355aeab7908fbc19604c667f42
  • Cointegration Lab

    Tests whether two series are cointegrated using ADF and the Engle-Granger two-step procedure, and estimates the mean-reversion half-life of the resulting spread.

    no model set

    recruitment4 / 32 parallel

    Compiles to the agent's native parallelismfield. The 1–32 range is Buzz's, not ours.

    thresholdmedium

    How little it takes to get a response. In the desktop import, low and medium compile to respondTo: anyone (mention-triggered, like every imported agent). Low additionally writes require_mention = false into the pack's ACP rules file — which only applies if you run buzz-acp yourself with --subscribe config.

    persistencemedium

    How long it stays on a task. Compiles to idle and turn timeouts.

    propagationhigh

    Catalog metadata only. Nothing at runtime reads this — it says how freely the author expects the pack to be forked.

    sha256 checksums
    cointegration-lab.agent.json 3,179 B
    cf01b10761c2dba5a7dad94403d0e95619a1813a98149b70c58aa64cb11b9a29
    cointegration-lab.agent.png 27,712 B
    55dfd14185c1c96e18a6992b1e2f8f6c3af10dbfee984e0a822c74c1611a6de8
  • Hawkes Fit

    Simulates and fits univariate self-exciting Hawkes processes with an exponential kernel, for modelling clustered event arrivals such as order flow.

    no model set

    recruitment1 / 32 parallel

    Compiles to the agent's native parallelismfield. The 1–32 range is Buzz's, not ours.

    thresholdmedium

    How little it takes to get a response. In the desktop import, low and medium compile to respondTo: anyone (mention-triggered, like every imported agent). Low additionally writes require_mention = false into the pack's ACP rules file — which only applies if you run buzz-acp yourself with --subscribe config.

    persistencelong

    How long it stays on a task. Compiles to idle and turn timeouts.

    propagationmedium

    Catalog metadata only. Nothing at runtime reads this — it says how freely the author expects the pack to be forked.

    sha256 checksums
    hawkes-fit.agent.json 3,445 B
    6f074864d30e0c7b18b9503ba37d3ba760202117dae035d0d338cc8878705752
    hawkes-fit.agent.png 27,567 B
    f7241ce8227bd93b0d2e42d61b6ad96a0493500a07e1dc184b111d4469972de7
  • Backtest Engine

    Reasons about event-driven backtesting mechanics — bar loop, fills, slippage and cash reconciliation — using a deterministic header-only C++20 engine.

    no model set

    recruitment1 / 32 parallel

    Compiles to the agent's native parallelismfield. The 1–32 range is Buzz's, not ours.

    thresholdmedium

    How little it takes to get a response. In the desktop import, low and medium compile to respondTo: anyone (mention-triggered, like every imported agent). Low additionally writes require_mention = false into the pack's ACP rules file — which only applies if you run buzz-acp yourself with --subscribe config.

    persistencemedium

    How long it stays on a task. Compiles to idle and turn timeouts.

    propagationhigh

    Catalog metadata only. Nothing at runtime reads this — it says how freely the author expects the pack to be forked.

    sha256 checksums
    backtest-engine.agent.json 3,521 B
    de56582c2a2638f35dd9ce818de85211ce6c742bee92afae550520c82c143633
    backtest-engine.agent.png 27,796 B
    b55c44783c41b8cc58337a0d732e0fb2eee84b33b6906e06d981e862f6550aac

Installing

4 clicks plus the OS file picker. There is no drag-and-drop shortcut: the Agents section has no drop target.

  1. Download the file below.
  2. In Buzz Desktop, open the Agents section in the sidebar.
  3. Click the "+" card, then "Import".
  4. Pick the file, review the preview, and confirm.

Imported is not running

  • The agent exists but is not running yet.
  • It needs provider credentials from the app's global settings.
  • Adding it to a channel is a separate action in the agent's profile panel.

Or build it from source

The files above are generated from this repository. Nothing is fetched at runtime and nothing phones home.

uv run python -m killerbee build packs/timeseries-stat-trading