Skip to content

Releases: twomathematicians-code/raix

v0.8.1 — AI Simulation Engine

Choose a tag to compare

@twomathematicians-code twomathematicians-code released this 31 Jul 08:06

raix_simulate() — Describe a system, get a complete simulation

# Power analysis
raix_simulate("Power analysis for t-test with effect size 0.5, sample sizes 20-200")

# Stock price simulation
raix_simulate("Geometric Brownian motion stock price, 252 days, drift 0.07, volatility 0.2", run = TRUE)

# Monte Carlo integration
raix_simulate("Estimate pi using Monte Carlo method")

# Epidemiology model
raix_simulate("SIR disease spread model with 1000 population, beta 0.3, gamma 0.1, 100 days")

AI handles: approach design → parameter setup → simulation loop → results analysis → visualization.

42 functions total.

v0.8.0 — Advanced Tools: Test, Refactor, Translate, SQL, Web

Choose a tag to compare

@twomathematicians-code twomathematicians-code released this 31 Jul 07:44

raix v0.8.0 — Advanced Developer Tools

New Functions

Function What it does
raix_test(my_func) AI generates testthat unit tests for any R function
raix_refactor(code) AI refactoring suggestions — performance, readability, safety
raix_translate(code, to='python') Convert R ↔ Python code with idiomatic translation
raix_sql('top 10 customers') Natural language → SQL (Postgres, MySQL, SQLite, SQL Server)
raix_web(url) Fetch and summarize any web page with AI
raix_history() View, search, and clear chat history

Now 41 exported functions

Chat & Code: raix_chat, raix_gui, raix_dashboard, raix_send, raix_explain, raix_generate, raix_debug, raix_document

Developer Agent: raix_solve, raix_script, raix_notebook, raix_project, raix_package, raix_read, raix_write

Compute Engine: raix_terminal, raix_python, raix_compile, raix_pipeline, raix_benchmark, raix_parallel, raix_sysinfo, raix_run

Advanced: raix_test, raix_refactor, raix_translate, raix_sql, raix_web, raix_history

Setup & Data: raix_setup, raix_configure, raix_info, raix_config, raix_check, raix_small_mode, raix_analyze, raix_search, raix_diagnose, raix_google, raix_rstudio, raix_help, raix_google

Install

remotes::install_github("twomathematicians-code/raix@v0.8.0")

v0.7.1 — Published with DOI

Choose a tag to compare

@twomathematicians-code twomathematicians-code released this 31 Jul 07:27

raix v0.7.1

Published release for Zenodo DOI registration.

Install

remotes::install_github("twomathematicians-code/raix")

Citation

citation("raix")

See LICENSE and SOP.md for full documentation.

v0.7.0 — Creative Open Source · CI Green · Production Ready

Choose a tag to compare

@twomathematicians-code twomathematicians-code released this 31 Jul 06:11

raix v0.7.0 — Production Ready

✅ CI Green — All checks pass

  • R CMD build + check: PASS
  • Tests: 29 PASS, 3 SKIP (needs live AI)
  • No parse errors, no dependency issues

📦 Install (always works)

remotes::install_github("twomathematicians-code/raix")
library(raix)
raix_setup()

🆕 v0.7.0 Changes

  • Creative Open Source License — MIT-based with attribution + AI training permission
  • SOP.md — Complete Standard Operating Procedures (install, setup, workflows, troubleshooting)
  • NA-safe input validation — All functions handle NULL/NA gracefully
  • Custom system_prompt preserved — Small-model optimization no longer overwrites user prompts
  • Base packages removed from Imports — No more installation failures
  • RStudio Viewer dashboard — raix_dashboard() opens inside RStudio
  • White/navy hero image — Clean, minimalist

Previous Features (v0.5.x)

  • 34 functions: Chat · Code Gen · Developer Agent · Compute Engine
  • Small LLM auto-detection and optimization
  • Auto-detect Ollama with model warmup
  • Windows-safe TCP port checking
  • Smart retry with timeout detection
  • 13+ AI providers | 33 man pages | Full Shiny dashboard

v0.5.1 — Production Stable: Windows-Safe + Auto-Warmup

Choose a tag to compare

@twomathematicians-code twomathematicians-code released this 31 Jul 05:21

raix v0.5.1 — Production Stable

Critical Fixes

Windows-safe auto-detection — TCP port check (socketConnection) replaces curl for backend detection. No more segfaults on Windows when checking if Ollama is running.

Model pre-warming — On setup, raix sends a warmup request to load the model into RAM. Your first real call never times out.

Smart retry — Detects cold-start vs. connection failure. First call gets 180s timeout, subsequent calls 120s. Automatic retry if model is still loading.

Helpful error messages — Distinguishes between:

  • Model loading into memory → suggests waiting and retrying
  • Ollama not running → shows start command
  • Model not found → shows pull command
  • Connection refused → suggests switching provider

All Features (v0.5.x)

  • 33 functions: Chat, Code Gen, Developer Agent, Compute Engine
  • 13+ providers with custom endpoint support
  • Small LLM optimization (auto-detects 7B-9B models)
  • Modern Shiny GUI with chat bubbles and typing indicators
  • Developer agent: solve, script, notebook, pipeline, compile, benchmark
  • Cross-language: terminal, Python, C++/Rcpp, shell scripts

Install

remotes::install_github("twomathematicians-code/raix@v0.5.1")

v0.5.0 — Developer Agent + Small LLM Optimized

Choose a tag to compare

@twomathematicians-code twomathematicians-code released this 30 Jul 22:10

raix v0.5.0 — R + AI + eXperiment

What's New

Developer Agent — raix now acts as an autonomous coding agent:

  • raix_solve() — English problem → complete R solution with package selection, plan, and code
  • raix_script() — Generate .R scripts from descriptions
  • raix_notebook() — Generate .Rmd notebooks ready to knit
  • raix_project() — Scan directories, read files, build full AI context
  • raix_package() — Find the best R package for any task
  • raix_read() — Read files with AI summarization
  • raix_write() — Write AI-generated content directly to files

Small LLM Optimization — Auto-detects local models (7B-9B):

  • Detects qwen2.5-coder, phi3.5, gemma2, llama3.2, and more
  • Auto-switches to concise, directive prompts for reliable results
  • raix_small_mode() toggle for manual control
  • Higher temperature (0.3) and lower max_tokens (1024) for small models

Redesigned GUI — Modern chat interface:

  • Chat bubbles with avatars, typing indicators
  • Auto-connect on launch, quick-prompt pills
  • Collapsible sidebar, dark/light design

One-Click Setupraix_setup() auto-detects running Ollama, LM Studio, vLLM, or API keys from environment variables. Zero configuration needed.

Complete Rename — All air_*raix_*. 25 functions total.

Installation

remotes::install_github("twomathematicians-code/raix@v0.5.0")

Or download raix_0.5.0.tar.gz below and install locally:

install.packages("raix_0.5.0.tar.gz", repos = NULL, type = "source")

Supported Models

OpenAI · Claude · Ollama · Groq · Mistral · DeepSeek · Together AI · Perplexity · LM Studio · vLLM · OpenRouter · Custom (any OpenAI-compatible endpoint)