by MedChaouch
Multi-LLM orchestration framework
# Add to your Claude Code skills
git clone https://github.com/MedChaouch/Puzld.aiBeyond CLI wrappers. PuzldAI is a complete AI orchestration framework — route tasks, explore codebases, execute file edits, build memory, and generate training data.
PuzldAI is a terminal-native framework for orchestrating multiple AI agents. Route tasks to the best agent, compare responses, chain agents in pipelines, or let them collaborate. Agentic Mode gives LLMs tools to explore your codebase (view, glob, grep, bash) and propose file edits with permission prompts — like Claude Code, but for any LLM. Memory/RAG stores decisions and code for future context. Observation Layer logs everything for DPO fine-tuning. One framework that grows with your AI workflow.
| Problem | Solution | |---------|----------| | Claude is great at code, Gemini at research | Auto-routing picks the best agent | | Need specific model versions | Model selection — pick sonnet, opus, haiku, etc. | | Want multiple opinions | Compare mode runs all agents in parallel | | Complex tasks need multiple steps | chain agents together | | Repetitive workflows | save and reuse pipelines | | Need agents to review each other | — correct, debate, consensus | | Want LLM to explore & edit files safely | — tools, permission prompts, apply | | Context gets lost between sessions | — semantic retrieval of past decisions | | Need data to fine-tune models | — export DPO training pairs | | Need AI to understand your codebase | — AST parsing, semantic search, AGENTS.md |
gemini:analyze → claude:code (CLI)