Switch between model providers (DeepSeek, Gemini, OpenAI, Anthropic) in Claude Code

Portable, vendor-neutral AI Dev OS for multi-agent coding workflows

Standing red-team and gate calibration for the ADLC toolkit — generator-adversary fan-out (C-tool).

N-version programming for failing tests — fan N LLM completions, group by agreement, recommend the smallest consensus fix (C7/P4).

Scan debug.log file to find unknown errors

bccg adapter for [Google Gemini CLI](https://github.com/google-gemini/gemini-cli).

MCP server that proxies image generation to Azure (GPT-Image, DALL-E 3, FLUX Kontext Pro), saves to local disk, and returns file paths instead of base64 to keep context windows clean.

bccg adapter for [OpenAI Codex CLI](https://github.com/openai/codex).

Shared types, interfaces, error classes, and constants for bccg adapters. Zero runtime dependencies.

Config driven testing suite for protractor

bccg adapter for [Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code).

bccg adapter for [GitHub Copilot CLI](https://docs.github.com/en/copilot/github-copilot-in-the-cli). This is the project's core adapter — the only CLI with `--model` flag for intra-CLI model routing.

bccg adapter for [OpenAI Codex CLI](https://github.com/openai/codex).

bccg adapter for [Google Gemini CLI](https://github.com/google-gemini/gemini-cli).

bccg adapter for [OpenCode CLI](https://github.com/sst/opencode). BYOK multi-model adapter supporting 75+ providers.

bccg adapter for [Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code).

Shared types, interfaces, error classes, and constants for bccg adapters. Zero runtime dependencies.

Research-backed Multi-LLM Router with parallel execution, learned routing (RouteLLM), prefix caching (RadixAttention), speculative decoding (Medusa/EAGLE), token compression (ISON), local LLM support (Ollama/vLLM/LM Studio), batch processing. Python bindi

Core database contracts and document primitives for Zelavis services.