MCPHub LabRegistrysympozium-ai/sympozium
sympozium-ai

sympozium ai/sympozium

Built by sympozium-ai 378 stars

What is sympozium ai/sympozium?

Run a fleet of AI agents on Kubernetes. Administer your cluster agentically

How to use sympozium ai/sympozium?

1. Install a compatible MCP client (like Claude Desktop). 2. Open your configuration settings. 3. Add sympozium ai/sympozium using the following command: npx @modelcontextprotocol/sympozium-ai-sympozium 4. Restart the client and verify the new tools are active.
🛡️ Scoped (Restricted)
npx @modelcontextprotocol/sympozium-ai-sympozium --scope restricted
🔓 Unrestricted Access
npx @modelcontextprotocol/sympozium-ai-sympozium

Key Features

Native MCP Protocol Support
Real-time Tool Activation & Execution
Verified High-performance Implementation
Secure Resource & Context Handling

Optimized Use Cases

Extending AI models with custom local capabilities
Automating system workflows via natural language
Connecting external data sources to LLM context windows

sympozium ai/sympozium FAQ

Q

Is sympozium ai/sympozium safe?

Yes, sympozium ai/sympozium follows the standardized Model Context Protocol security patterns and only executes tools with explicit user-granted permissions.

Q

Is sympozium ai/sympozium up to date?

sympozium ai/sympozium is currently active in the registry with 378 stars on GitHub, indicating its reliability and community support.

Q

Are there any limits for sympozium ai/sympozium?

Usage limits depend on the specific implementation of the MCP server and your system resources. Refer to the official documentation below for technical details.

Official Documentation

View on GitHub
<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/assets/brand/logo-plate-dark.svg"> <img src="docs/assets/brand/logo-plate-light.svg" alt="Sympozium — agentic control plane, K8s-native" width="540"> </picture> </p> <p align="center"> <em> Agents don't need better prompts. They need shared situational awareness.<br> Sympozium is a <b>coordination layer</b> for multi-agent AI systems on Kubernetes &mdash;<br> selective permeability, structured handoffs, and shared memory.<br> Every agent is a Pod. Every policy is a CRD. Every execution is a Job.</em><br><br> From the creator of <a href="https://github.com/k8sgpt-ai/k8sgpt">k8sgpt</a> and <a href="https://github.com/AlexsJones/llmfit">llmfit</a> </p> <p align="center"> <b> This project is under active development. API's will change, things will break. Be brave. <b /> </p> <p align="center"> <a href="https://github.com/sympozium-ai/sympozium/actions"><img src="https://github.com/sympozium-ai/sympozium/actions/workflows/build.yaml/badge.svg" alt="Build"></a> <a href="https://github.com/sympozium-ai/sympozium/releases/latest"><img src="https://img.shields.io/github/v/release/sympozium-ai/sympozium" alt="Release"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue" alt="License"></a> </p> <p align="center"> <img src="demo.gif" alt="Sympozium dashboard" width="800px;"> </p>

Full documentation: deploy.sympozium.ai/docs

The problem this solves: The Sticky-Note Problem — why message-passing between agents breaks down, and what to build instead.


The Problem

Most multi-agent systems communicate through messages — strings of tokens that one agent serialises and another deserialises. A detection agent spots a threat while a containment agent takes the server offline for maintenance. Neither knows what the other is doing. The breach is missed.

This is the sticky-note problem: agents passing notes instead of sharing a situational board. Kubernetes solved this for containers with a shared control plane. Agents need the same thing — not better message-passing, but shared coordination infrastructure.

Sympozium provides that infrastructure: a synthetic membrane that wraps agent teams with selective permeability, shared memory, structured handoffs, and circuit breakers — all expressed as Kubernetes-native CRDs.


Quick Install (macOS / Linux)

Homebrew:

brew tap sympozium-ai/sympozium
brew install sympozium

Shell installer:

curl -fsSL https://deploy.sympozium.ai/install.sh | sh

Then deploy to your cluster and activate your first agents:

sympozium install          # deploys CRDs, controllers, and built-in Ensembles
sympozium                  # launch the TUI — go to Personas tab, press Enter to onboard
sympozium serve            # open the web dashboard (port-forwards to the in-cluster UI)

Advanced: Helm Chart

Prerequisites: cert-manager (for webhook TLS):

kubectl apply -f https://github.com/cert-manager/cert-manager/releases/download/v1.17.1/cert-manager.yaml

Sympozium can be installed as two charts: sympozium-crds (the CRDs, so they can be upgraded) and sympozium (the control plane). Install the CRDs first, then the control plane:

helm repo add sympozium https://deploy.sympozium.ai/charts
helm repo update

helm upgrade --install sympozium-crds sympozium/sympozium-crds \
  --namespace sympozium-system --create-namespace

helm upgrade --install sympozium sympozium/sympozium \
  --namespace sympozium-system \
  --skip-crds --set createNamespace=false

--skip-crds on the second command assumes you installed sympozium-crds first. If you skip the CRDs chart, drop --skip-crds so the bundled CRDs in the sympozium chart are applied instead.

See charts/sympozium/values.yaml for configuration options, or the Helm Chart docs for the full guide.


Why Sympozium?

Containers needed orchestration. Agents need coordination.

Sympozium is a Kubernetes-native coordination layer for multi-agent AI systems. It solves the same problem Kubernetes solved for containers — but for agents that need to share context, hand off tasks, and maintain shared situational awareness.

And that is the whole product. Sympozium decides what agents do. Where compute happens is the job of a capability layer — llmfit-dra, a Kubernetes DRA driver that places models by physics through the stock scheduler. How tokens move is the serving engine's job (vLLM, SGLang, llama.cpp). When an agent needs a model, Sympozium claims one the way an application claims a PersistentVolume — it never decides where it runs. See Positioning for the boundary and what's deliberately out of scope.

Agent Coordination

Synthetic MembraneSelective permeability for agent teams — control what agents share via trust groups, visibility tags, and field-level gating. Read the paper
Agent WorkflowsDelegation, sequential pipelines, supervision, and stimulus triggers between personas — visualised on an interactive canvas
Shared Workflow MemoryPack-level SQLite memory pool for cross-persona knowledge sharing with per-persona access control and time decay
EnsemblesHelm-like bundles for AI agent teams — activate a pack and the controller stamps out instances, schedules, and memory

Platform Infrastructure

Model Endpoints for AgentsDeclare GGUF models as CRDs — weights are downloaded, llama-server deployed, and OpenAI-compatible endpoints exposed for your personas. No API keys required. Placement is claimed, not decided here: with llmfit-dra installed, the stock scheduler places models by physics
Skill SidecarsEvery skill runs in its own sidecar with ephemeral least-privilege RBAC, garbage-collected on completion
Multi-ChannelTelegram, Slack, Discord, WhatsApp — each channel is a dedicated Deployment backed by NATS JetStream
Persistent MemorySQLite + FTS5 on a PersistentVolume — memories survive across ephemeral pod runs
Scheduled TasksCron-based recurring agent runs for periodic workflows, data syncs, and automated checks
Agent SandboxKernel-level isolation via kubernetes-sigs/agent-sandbox — gVisor or Kata with warm pools for instant starts
MCP ServersExternal tool providers via Model Context Protocol with auto-discovery and allow/deny filtering
TUI & Web UITerminal and browser dashboards with live workflow canvas, or skip the UI entirely with Helm and kubectl
Any AI ProviderOpenAI, Anthropic, Azure, Ollama, or any compatible endpoint — no vendor lock-in

Documentation

TopicLink
Getting Starteddeploy.sympozium.ai/docs/getting-started
Positioning — what Sympozium is (and isn't)deploy.sympozium.ai/docs/positioning
Architecturedeploy.sympozium.ai/docs/architecture
Custom Resourcesdeploy.sympozium.ai/docs/concepts/custom-resources
Ensemblesdeploy.sympozium.ai/docs/concepts/ensembles
Skills & Sidecarsdeploy.sympozium.ai/docs/concepts/skills
Persistent Memorydeploy.sympozium.ai/docs/concepts/persistent-memory
Channelsdeploy.sympozium.ai/docs/concepts/channels
Agent Sandboxingdeploy.sympozium.ai/docs/concepts/agent-sandbox
Securitydeploy.sympozium.ai/docs/concepts/security
CLI & TUI Referencedeploy.sympozium.ai/docs/reference/cli
Helm Chartdeploy.sympozium.ai/docs/reference/helm
Local Modelsdeploy.sympozium.ai/docs/guides/local-models
Ollama & Local Inferencedeploy.sympozium.ai/docs/guides/ollama
Writing Skillsdeploy.sympozium.ai/docs/guides/writing-skills
Writing Toolsdeploy.sympozium.ai/docs/guides/writing-tools
LM Studio & Local Inferencedeploy.sympozium.ai/docs/guides/lm-studio
llama-serverdeploy.sympozium.ai/docs/guides/llama-server
Unslothdeploy.sympozium.ai/docs/guides/unsloth
Writing Ensemblesdeploy.sympozium.ai/docs/guides/writing-ensembles
Your First AgentRundeploy.sympozium.ai/docs/guides/first-agentrun

Development

make test        # run tests
make test-system # run envtest system tests (no cluster needed)
make lint        # run linter
make manifests   # generate CRD manifests
make run         # run controller locally (needs kubeconfig)

License

MIT License

Global Ranking

8.5
Trust ScoreMCPHub Index

Based on codebase health & activity.

Manual Config

{ "mcpServers": { "sympozium-ai-sympozium": { "command": "npx", "args": ["sympozium-ai-sympozium"] } } }