Optimizing inference proxy for LLMs

A machine learning package for streaming data in Python. The other ancestor of River.

Running Mixture of Agents on CPU: LFM2.5 Brain (1.2B) + Falcon-R Reasoner (600M) + Tool Caller (90M). CPU-only, 16GB RAM. Lightweight AI Legion.

Mixture-of-Ollamas

An external pipeline filter for Open WebUI that refactors aggregate requests with collective wisdom to output structured expert analysis reports.

This Streamlit application showcases the Mixture of Agents (MOA) architecture proposed by Together AI, powered by Groq LLMs. It allows users to interact with a configurable multi-agent system for enhanced AI-driven conversations.

A simplified agentic workflow process based on the Mixture of Agents (MoA) system for Large Language Models (LLMs)

Official repo for DK904 - IOT Stream Data Mining

Trabalho de matéria de Modelagem e Otimização de Algoritmos

Local-First Multi-AI agent Control Platform: Next.js UI, FastAPI backend, optional Local Bridge, agent fleet, skills, memory, and file workflows

Pythonic wrapper around Massive Online Analysis (MOA)

Combine multiple LLMs for better outputs.

本地文件式 MOA（多模型协作）Skill：工作者在显式权限边界内产出有界证据，协调者比对证据并保留 GO / PARTIAL / RED 终裁；先按 ROI 路由（DIRECT/LITE/FULL/SPLIT）再付协作成本。

工业级多模型协作网关 — 智能 auth-fallback / 桌面 UI (flet) / Together AI MoA 论文对齐 (9 strategy) / 4 国产预设 / Benchmark Suite / 端到端可跑

A curated benchmark collection for machine learning on streaming data (classification, regression, clustering, anomaly detection under concept drift)

Phenomics perturbation profiling and MoA retrieval from morphological cell-painting profiles (UMAP + HDBSCAN + cosine similarity). POC: LINCS Cell Painting — recall@5 = 3.0× random baseline on 111 compounds across 20 MoA classes.

Multi-model committee (Mixture-of-Agents) for Claude Code — your agent chairs up to 4 heterogeneous LLMs to blind-review, decide & brainstorm in parallel, with evidence-driven convergence for more reliable conclusions.

Visualiseur MOA en Python/CustomTkinter pour estimer la dispersion theorique d'un groupement et la projeter sur une cible de reference

Multi-step sequential thinking MCP server powered by large language models — structured reasoning with self-MoA and iterative thinking modes