Skip to content
View Oroboros26's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report Oroboros26

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Oroboros26/README.md

SAHBI Mohamed

🚀 Data / AI Platform Engineer

I turn messy data and business questions into working, measured AI systems: built end to end, handed over with runbooks.

🛠️ What I build

🧭 How I work

Eval first, defence in depth, honest results. Each repo says what was measured and what wasn't.

🧰 Stack: Don't worry, we'll find the right tech for the problem. (Usually Python, SQL, and a lot of coffee ☕)

Pinned Loading

  1. agent-framework-load-benchmark agent-framework-load-benchmark Public

    Benchmark AI agent frameworks (LangGraph, OpenAI Agents SDK, Pydantic AI, Microsoft Agent Framework, Google ADK) against plain Python under a deterministic fake LLM, one CPU core

    Python

  2. agent-orchestration-platform agent-orchestration-platform Public

    Platform for deploying, versioning, routing and monitoring LLM agents: registry, model router, budget guard, evals, FastAPI + Streamlit

    Python

  3. governed-metrics-gateway governed-metrics-gateway Public

    Governed gateway giving people and AI agents one definition of every business metric: YAML semantic view, Pydantic and NetworkX validation, sqlglot SQL compiler, FastAPI REST and MCP-style tools, R…

    TypeScript

  4. text-to-sql-agent-guardrails text-to-sql-agent-guardrails Public

    Tool-using LLM agent for analytics questions over SQLite, with layered guardrails: sqlglot SQL guard, Pydantic tool validation, read-only DB, timeouts and injection tests

    Python

  5. text-to-sql-lora-finetune text-to-sql-lora-finetune Public

    Does QLoRA fine-tuning a small open model beat prompting for text-to-SQL? Dataset generation, QLoRA training, merge and a five-system evaluation harness

    Python

  6. text-to-sql-in-one-file text-to-sql-in-one-file Public

    Text-to-SQL in 97 lines of Python: one semantic YAML file, validated read-only SQL, a plain tool loop. No framework.

    Python