raphaelmansuy
Joined 5 years ago
Karma
4
Submissions
20
Member since
Jan 13
Recent submissions
Comment · 8 months ago
Hi — I'm Raphael Mansuy. I built edgequake-litellm to provide a low-latency, Rust-backed drop-in replacement for LiteLLM. It exposes the same Python API (`completion()`, `acompletion()`, `stream()`, `embedding()`), supports provider/model routing (OpenAI, Anthropic, Gemini, Mistral, xAI, OpenRouter, Ollama, LM Studio, etc.), and ships as a single ABI3 wheel with zero Python runtime deps.
Quick migration:
```python import edgequake_litellm as litellm # drop-in alias ```
Why build it? LiteLLM is excellent, but its pure-Python HTTP layer adds SDK overhead. I moved the core into Rust (edgequake-llm) and wrapped it with PyO3 to cut latency and provide a robust, multi-arch wheel. This is v0.1 — P0 compatibility is in place, but I'd love feedback on priorities: provider coverage, proxy features, billing/budgets, or tool-calling parity.
Install:
pip install edgequake-litellm
Repo: https://github.com/raphaelmansuy/edgequake-llm
If you try it, please star the repo and open issues for features you want most — I'm actively iterating. Happy to answer technical questions here.
Comment · 1 year ago
Quantalogic: A ReAct Coding Agent framework 100% autonomous that seamlessly integrates with GPT-4o, Claude 3.5, and DeepSeek V3, DeepSeek R1 !
https://www.youtube.com/watch?v=QNEdHP_yZIc
If you're into AI agents that can code, reason, and execute tasks autonomously, check out Quantalogic:
https://github.com/quantalogic/quantalogic
What makes it special:
- Support code editing, efficient code search - Enterprise-ready with Docker-based secure code execution - Human supervision - Universal LLM support (OpenAI, Anthropic, DeepSeek, etc.)
If this sounds useful for your AI projects, a star would mean the world to me! Let's build the future of AI agents together.
Comment · 1 year ago
QuantaLogic: A ReAct Framework for Building Advanced AI Agents
QuantaLogic is a Python-based ReAct (Reasoning & Action) framework bridging advanced AI models with practical business applications. It integrates LLMs with a robust tool system, enabling AI agents to understand, reason about, and execute complex tasks through natural language.
Key Features:
Universal LLM Support: OpenAI, Anthropic, DeepSeek, etc. via LiteLLM Secure Tool System: Docker-based code execution and file manipulation Real-time Monitoring: Web interface with SSE events Enterprise Ready: Comprehensive logging, validation and error handling Extensible: Custom tools and agents via Python SDK
https://www.quantalogic.app