• About
  • Documentation

  • More Universes
  • Recent Updates
  • Leader board

  • All repositories
  • All packages
  • All articles
  • All datasets
  • All system Libraries
cornball-ai
  • Builds
  • Packages
  • Articles
  • Datasets
  • Contribution
  • Badges
  • API
  • Feed

Links tocornball-ai

corteza - AI Agent Runtime

An agent runtime that gives Large Language Models (LLMs) from 'Anthropic' <https://www.anthropic.com/>, 'OpenAI' <https://openai.com/>, 'Moonshot' <https://www.moonshot.ai/>, and 'Ollama' <https://ollama.com/> direct access to a live R session with managed workspace state. Tools execute as R function calls with provenance tracking, and a deterministic retrieval system keeps relevant objects in context across turns. Three entry points: a shell command-line interface (CLI), a console read-eval-print-loop via chat(), and a Model Context Protocol (MCP) server via serve() for external clients.

Last updated

6.93 score 11 stars 6 scripts 353 downloads

rformat - Base R Code Formatter

A minimal R code formatter following base R style conventions. Formats R code with consistent spacing, indentation, and structure.

Last updated

cpp

5.78 score 4 stars 4 scripts 490 downloads

pensar - LLM Wiki Engine

Personal wiki engine with a large language model (LLM) as research assistant. Supports guided sessions through a 'Claude Code' <https://github.com/anthropics/claude-code> skill bundle and autonomous research runs from R via autoresearch(). Results land in a structured vault of markdown pages with 'YAML' frontmatter and wikilinks, ready for hand-editing in your favourite editor alongside the LLM. Vaults are seeded with 'CLAUDE.md' and 'AGENTS.md' so 'Claude Code', 'Codex' <https://github.com/openai/codex>, and other agents share the same operating instructions. Can adopt an existing 'Obsidian' <https://obsidian.md/> vault in place via init_vault(adopt = TRUE).

Last updated

5.56 score 8 stars 384 downloads

saber - Context Engineering for Large Language Model Agents

Context-engineering primitives for Artificial Intelligence (AI) coding agents working in R. Assembles agent context from memory and instruction files ('AGENTS.md', 'CLAUDE.md'), traces function call blast radius across projects, generates project briefings, parses source into Abstract Syntax Tree (AST) symbol indices, discovers dependency graphs, and introspects installed packages. Zero dependencies.

Last updated

5.30 score 7 stars 1 dependents 21 scripts 925 downloads

llm.api - Minimal LLM Chat Interface

A minimal-dependency client for Large Language Model chat APIs. Supports 'OpenAI' <https://openai.com/>, 'Anthropic' 'Claude' <https://claude.com/>, 'Moonshot' 'Kimi' <https://www.moonshot.ai/>, 'Ollama' <https://ollama.com/>, and other 'OpenAI'-compatible endpoints. Includes an agent loop with tool use and a 'Model Context Protocol' client <https://modelcontextprotocol.io/>. API design is derived from the 'ellmer' package, reimplemented with only base R, 'curl', and 'jsonlite'.

Last updated

4.56 score 2 stars 1 dependents 1 scripts 934 downloads

whisper - Native R 'torch' Implementation of 'OpenAI' 'Whisper'

Speech-to-text transcription using a native R 'torch' implementation of 'OpenAI' 'Whisper' model <https://github.com/openai/whisper>. Supports multiple model sizes from tiny (39M parameters) to large-v3 (1.5B parameters) with integrated download from 'HuggingFace' <https://huggingface.co/> via the 'hfhub' package. Provides automatic speech recognition with optional language detection and translation to English. Audio preprocessing, mel spectrogram computation, and transformer-based encoder-decoder inference are all implemented in R using the 'torch' package.

Last updated

4.45 score 7 stars 9 scripts 544 downloads

stt.api - 'OpenAI' Compatible Speech-to-Text API Client

A minimal-dependency R client for 'OpenAI'-compatible speech-to-text APIs (see <https://platform.openai.com/docs/api-reference/audio>) with optional local fallbacks. Supports 'OpenAI', local servers, and the 'whisper' package for local transcription.

Last updated

4.13 score 3 stars 190 downloads

tinyrox - Minimal R Documentation Generator

A deterministic, dependency-free documentation generator for R packages. Generates valid Rd files and NAMESPACE from 'roxygen2'-style comments using only base R. Supports a strict subset of tags with no markdown parsing, no inference magic, and explicit-only behavior.

Last updated

4.08 score 2 stars 2 scripts 487 downloads

tinypkgr - Minimal R Package Development Utilities

Lightweight wrappers around 'R CMD INSTALL', 'R CMD check', 'R CMD build', 'win-builder' uploads, and 'CRAN' submission. Provides functions for installing, loading, checking, building, and submitting R packages with minimal dependencies (only 'curl' for uploads). Background on R package development is in Wickham and Bryan (2023, ISBN:9781098134945), "Writing R Extensions" <https://cran.r-project.org/doc/manuals/R-exts.html>, and the 'CRAN' Repository Policy <https://cran.r-project.org/web/packages/policies.html>.

Last updated

4.02 score 3 stars 1 scripts 557 downloads

pensar - LLM Wiki Engine

Personal wiki engine with a large language model (LLM) as research assistant. Supports guided sessions through a 'Claude Code' <https://github.com/anthropics/claude-code> skill bundle and autonomous research runs from R via autoresearch(). Results land in a structured vault of markdown pages with 'YAML' frontmatter and wikilinks, ready for hand-editing in your favourite editor alongside the LLM. Vaults are seeded with 'CLAUDE.md' and 'AGENTS.md' so 'Claude Code', 'Codex' <https://github.com/openai/codex>, and other agents share the same operating instructions. Can adopt an existing 'Obsidian' <https://obsidian.md/> vault in place via init_vault(adopt = TRUE).

Last updated

3.00 score 171 downloads

mx.api - Minimal Matrix Client-Server API

A minimal-dependency client for the 'Matrix' Client-Server HTTP API <https://spec.matrix.org/>, suitable for talking to a 'Synapse' <https://element-hq.github.io/synapse/> or 'Conduit' <https://conduit.rs/> homeserver. Covers login, room management, message send and history, media upload or download, and the transport endpoints needed to coordinate end-to-end encryption (device-key and one-time-key publication, key query and claim, to-device events). Encryption itself is out of scope; pair with a separate crypto package.

Last updated

3.00 score 410 downloads