crucible_ensemble

0.1.0

Multi-model ensemble prediction with voting strategies for AI reliability. Leverages BEAM parallelism for massively concurrent LLM queries.

HexDocs Report package

Current section

Files

Jump to

Readme 5 Versions 2 Dependencies Dependants Files Activity

crucible_ensemble CHANGELOG.md

Raw

CHANGELOG.md

# Changelog

All notable changes to this project will be documented in this file.

## [0.1.0] - 2025-10-07

### Added
- Initial release
- Multi-model ensemble prediction framework for AI reliability research
- Multiple voting strategies (majority, weighted, best confidence, unanimous)
- Flexible execution strategies (parallel, sequential, hedged, cascade)
- Support for multiple LLM providers (Google Gemini, OpenAI, Anthropic)
- Automatic cost tracking and estimation
- Comprehensive telemetry integration for research analysis
- Fault tolerance with graceful degradation
- BEAM concurrency leveraging lightweight processes for massive parallelism

### Documentation
- Comprehensive README with examples
- API documentation for all voting and execution strategies
- Usage examples for research experiments
- Performance benchmarks and research motivation

Operator	Description	Example
name:	Match package name. Supports * wildcards and repo/package form	name:phx* or name:hexpm/phoenix
description:	Full-text search of package descriptions	description:auth
depends:	Packages depending on a given package. Supports repo:package form	depends:ecto or depends:hexpm:ecto
build_tool:	Filter by build tool	build_tool:mix
updated_after:	Packages updated after an ISO8601 datetime	updated_after:2025-01-01T00:00:00Z
extra:	Match custom metadata (key,value). Nested keys are separated by commas	extra:license,MIT