rrahimi-uci

rrahimi-uci/caliber-suite

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

1 stars 0 forks 1 watchers Python

agentic-workflows ai-agents evaluation human-in-the-loop llmops mcp mlflow mlflow-plugin model-context-protocol observability prompt-engineering rag workflow-automation

View on GitHub Website

18 Open Issues Need Help Last updated: Aug 13, 2026

Open Issues Need Help

View All on GitHub

Pilot 20 — Perform a first-time-user UX and documentation review about 1 hour ago

help wanted release-v0.1.0 area-testing area-docs priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 19 — Test agents, Aria plans, approvals, and pause/resume about 1 hour ago

help wanted release-v0.1.0 area-core area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 18 — Test governed release and audit semantics about 1 hour ago

help wanted release-v0.1.0 area-core area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 17 — Test review-queue creation, labeling, and feedback about 1 hour ago

help wanted release-v0.1.0 area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 16 — Test observability, traces, logs, and troubleshooting about 1 hour ago

help wanted release-v0.1.0 area-observability area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 15 — Test calibration for prompts, skills, workflows, or tools about 1 hour ago

help wanted release-v0.1.0 area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 14 — Test judges, scorecards, evaluations, and review evidence about 1 hour ago

help wanted release-v0.1.0 area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 13 — Test test-set creation, examples, and dataset lineage about 1 hour ago

help wanted release-v0.1.0 area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 12 — Test LLM Gateway provider setup and guardrails about 1 hour ago

help wanted release-v0.1.0 area-testing area-operations priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 11 — Validate the supported management API, SDK, and CLI path about 1 hour ago

help wanted release-v0.1.0 area-core area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 9 — Test MCP server connection, discovery, and policy about 1 hour ago

help wanted release-v0.1.0 area-security area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 10 — Test OpenAPI integration import, preview, and invocation about 1 hour ago

help wanted release-v0.1.0 area-core area-security priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 8 — Test object-store upload, metadata, and retrieval about 1 hour ago

help wanted release-v0.1.0 area-testing area-operations priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 7 — Test knowledge-base ingestion, retrieval, and provenance about 1 hour ago

help wanted release-v0.1.0 area-core area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 6 — Test Workflow Studio and workflow runtime execution about 1 hour ago

help wanted release-v0.1.0 area-core area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 5 — Test the tool registry and safe execution journey about 1 hour ago

help wanted release-v0.1.0 area-security area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 4 — Test the skill authoring, validation, and runtime journey about 1 hour ago

help wanted release-v0.1.0 area-core area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation

Pilot 3 — Test the prompt authoring and lifecycle journey about 1 hour ago

help wanted release-v0.1.0 area-core area-testing priority-p1

rrahimi-uci/caliber-suite

1

Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.

Python

#agentic-workflows#ai-agents#evaluation#human-in-the-loop#llmops#mcp#mlflow#mlflow-plugin#model-context-protocol#observability#prompt-engineering#rag#workflow-automation