MCP servers and skills: search, filter by where they run, and compare.
1–24 of 63 tools for “mixture-of-agents”
Clear allDynamic Mixture-of-Agents LLM orchestrator that runs 100% locally on 8GB VRAM (Ollama, no API keys).
SkillApache-2.0★ 1Few starsNo key
🦀⚡ Community skill pack & CLI for Genspark Claw, OpenClaw & Hermes agents — 5 production-ready SKILL.md skills (deep research, reports, slides, browser automation, AI call prep), zero-dependency Node
Node.jsMIT★ 538No key
Governed verification and synthesis for Massive Intelligence (IM) outputs: configurable Thinker, Worker, and Verifier panels, model-as-judge, and Ed25519-signed, SHA-256-chained tamper-evident verdict
Node.jsApache-2.0★ 1Few starsNo key
Mixture of Agents for BB: advisor models answer first, then an aggregator reads their notes and does the work.
SkillMIT★ 2Few starsNo key
SOTA NPM module for agentic processes using local or cloud LLMs.
SkillMIT★ 5No key
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 rel
SkillMIT★ 1Few starsNo key
Metis (μῆτις) — distributed cognitive layer over any LLM. Understanding Council → confidence gate (fail-closed) → layered MoA → verifier-with-retry, with DGPD depth gating, memory, economy metering, a
PythonMIT★ 3Few starsNo key
Multi-step sequential thinking MCP server powered by large language models — structured reasoning with self-MoA and iterative thinking modes
SkillMIT★ 1Few starsNo key
Multi-agent topology patterns for AI agents: orchestrator-worker, planner-executor, evaluator-optimizer, map-reduce, router, debate, swarm. Mirror of topologyindex.com + Agent Skill.
SkillCC-BY-4.0Few starsNo key
Curated collection of LLM apps built with RAG, AI Agents, Multi-agent Teams, MCP, Voice Agents and more
SkillApache-2.0★ 2Few starsNo key
Mixture — a deliberately-small, layered skills + agents framework for Claude Code (skills, session memory, multi-agent task runtime). Install via npx.
SkillLink onlyFew stars
Open-source language model built from scratch in PyTorch. Purpose-built for cybersecurity, with code + general language + math reasoning folded into the v1.0 corpus (516K records, ~363M tokens, six do
PythonMIT★ 5No key
Codex Skills for version-pure PFC2D/PFC3D 5.0 asphalt-mixture modeling, FISH scripting, calibration, Burger contacts, Marshall and rutting tests, and reproducible post-processing.
SkillMIT★ 26No key
PyThermoModels thermodynamic calculations exposed through MCP.
PythonApache-2.0★ 1Few starsNo key
A local LLM chat and lab for llama.cpp and the FLE engine: GGUF model loader, live inference data, launch profiles, MCP tools. No account, no telemetry. macOS, Linux and Windows.
PythonMIT★ 2Few starsNo key
Fully local AI coding workstation: a 35B MoE model (Tiel-Coder) at 200k context on a single 12 GB GPU, 35–40 tok/s, without slowing your desktop. Tuned llama.cpp, MoE expert cache, TurboQuant fix, per
SkillMIT★ 4Few starsNo key
Substrate-based context compaction for Claude Code. Inspectable signal weights, local-only, MCP-ready. Alternative to /compact + hook-based capture (claude-mem, etc.).
PythonMIT★ 5No key
🧪 Experiments with an EU AI Act compliance MCP server and a consensus router for Mixture-of-Experts routing — a designed tally; the consensus-strength claim was retracted 2026-07-29.
PythonApache-2.0Few starsNo key
Risk-scaled software-engineering handbook with sparse mixture-of-experts skill routing.
SkillMIT★ 1Few starsNo key
Solving optimization problems by sampling from generative models rather than iterative solvers. Gaussian mixture models and conditional flow matching applied to root finding, optimization, and paramet
SkillMIT★ 2Few starsNo key
A color consultant for painting, illustration, and design: build palettes, troubleshoot muddy mixtures, and turn descriptions like “dusty blue” into practical guidance. Distinguish how colors interact
SkillMIT★ 2Few starsNo key
MCP and QPU optimization harness for Qwen3 MoE inference on legacy Mac hardware
PythonMIT★ 4Few starsNo key
Free Mac app for running AI on your own computer. It checks what your Mac can handle before you download anything, picks the best model for you, and chats with real tools. All local, nothing sent to t
SkillMIT★ 3Few starsNo key
Agentify any repository in one command. AgentSmith maps a local codebase or GitHub URL and generates a Copilot-native engineering team with a root orchestrator, specialist agents, source-backed skills
SkillMIT★ 17No key
Who stands behind it
