No packages match

agentr - Specification and Review Scaffolding for AI Agent Workflows

Specification, review, and scaffolding helpers for AI agent systems. The package standardizes workflow, memory, knowledge, interface, proposal, and review artifacts so humans and coding assistants can infer, inspect, revise, and hand off task designs. It intentionally excludes communication layers, provider-specific model client code, and full runtime execution engines so that design artifacts and implementation transport remain cleanly separated.

Last updated

3.90 score 10 scripts 448 downloads

strategyr - Execution-Oriented Strategy Workflows for Dynamic Trading Decisions

Modular, execution-oriented strategy workflows that transform market features, portfolio state, and dynamic quantitative analysis into actionable signals, target positions, portfolio adjustments, and order intents. The package emphasizes path-dependent historical simulation so strategy decisions remain consistent with evolving account state, execution assumptions, and market conditions.

Last updated

cpp

3.88 score 57 downloads

inferencer - Simple Unified Wrappers for Foundation Model Inference APIs

Provides lightweight R wrappers for querying and listing models from several hosted and local foundation model inference platforms, currently including 'OpenAI' <https://developers.openai.com/api/docs/>, 'Google Gemini' <https://ai.google.dev/gemini-api/docs>, 'Groq' <https://console.groq.com/docs/>, 'OpenRouter' <https://openrouter.ai/docs/>, 'Cerebras' <https://inference-docs.cerebras.ai/>, 'Ollama Cloud' <https://docs.ollama.com/cloud>, 'Alibaba Cloud Model Studio' <https://help.aliyun.com/en/model-studio/>, 'Zhipu AI' <https://docs.bigmodel.cn/>, 'DeepSeek' <https://api-docs.deepseek.com/>, 'Moonshot AI' <https://platform.kimi.ai/docs/>, and 'MiniMax' <https://platform.minimax.io/docs/>. The package is designed for simple inference workflows and quick experimentation, with minimal abstraction and a consistent interface across providers. It includes helper functions for model discovery, text generation, embeddings, image generation, and multimodal inputs, while leaving room for future support of provider-specific parameters and advanced options.

Last updated

3.85 score 276 downloads

investlabr - Research Workflows for Macro and Cross-Asset Analysis

Reusable research workflows for macro-financial and cross-asset analysis. The package sits on top of data packages such as 'investdatar' and focuses on transforming existing market and macro data into analysis-ready research tables, factor and indicator constructions, event and regime overlays, sensitivity estimates, scenario comparisons, and research-grade visualization outputs. Portfolio risk-return comparisons use the mean-variance framework of Markowitz (1952) <doi:10.1111/j.1540-6261.1952.tb01525.x>. Research-side volatility simulations include the generalized autoregressive conditional heteroskedasticity model of Bollerslev (1986) <doi:10.1016/0304-4076(86)90063-1>.

Last updated

cpp

3.81 score

investdatar - Investment Data Access and Preparation Toolkit

A toolkit for loading, transforming, and managing structured investment-related data. Includes functions for retrieving macroeconomic and public financial series, regulatory filings, futures positioning, energy and fiscal data, market open-high-low-close-volume data, fund holdings, narrative feeds, and crypto derivatives from multiple providers. It detects time-series gaps and synchronizes local '.rds' data stores with sidecar metadata for analysis and trading workflows. It also generates structured dataset descriptions for large language model (LLM)-based analyst agents that produce R code for analysis and visualization.

Last updated

3.81 score 1 stars 318 downloads

okxr - R Interface to the 'OKX' REST API

Provides lightweight R wrappers for the 'OKX' REST API, covering endpoints for market data, trading, account management, asset balances, copy trading, and affiliate data. The upstream API reference is available at <https://www.okx.com/docs-v5/en/>.

Last updated

3.74 score 245 downloads

tradesimr - Execution and Simulation Engine for Trading Strategies

An R-native trading simulation package with a C++ execution core that turns strategy intentions and explicit orders into simulated trades, positions, cash, profit and loss, risk, and performance outputs under configurable execution, margin, funding, and cost assumptions. The package provides historical replay, incremental exchange stepping, durable event tables, append-only agent command logs, registered assets, per-agent shared-cash cross-margin live accounts, AI agent competitors, scheduled live-feed stepping, strategy-backed AI agents with diagnostics, calibrated and coordinated multi-asset market simulation with static covariance, AR-GARCH, factor, and regime models, durable per-feed simulation state, profile-aware heterogeneous inventory and margin execution with atomic mixed-profile order groups, optional portfolio-margin enforcement through a multi-asset C++ step kernel, local live-service APIs, import/export helpers, separate replay, live-state, and agent dashboard exports, and installed local orchestration scripts. It is designed to consume signals, order intents, or target exposure decisions from compatible strategy packages and market data from compatible adapters.

Last updated

cpp

3.65 score

binxr - 'Binance' REST API Client

Client for the 'Binance' <https://www.binance.com/> Spot, USD-M Futures, and Options REST APIs. Provides helper functions for signed and unsigned requests, market data retrieval, account access, and order management with 'data.table' output by default. COIN-M Futures, Portfolio Margin, WebSocket, SBE, and FIX APIs are not included.

Last updated

3.60 score 355 downloads