Every agent is an ephemeral Pod.
Every policy is a CRD. Every execution is a Job.
Orchestrate multi-agent workflows and let agents diagnose, scale, and remediate your infrastructure.
Multi-tenant. Horizontally scalable. Safe by design.

From the creator of k8sgpt and llmfit

This project is under active development. API's will change, things will be break. Be brave.

---

Full documentation: deploy.sympozium.ai/docs

---

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 PersonaPacks
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

Deploy the Sympozium control plane:

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

See charts/sympozium/values.yaml for configuration options.

---

Why Sympozium?

Sympozium serves two powerful use cases on one Kubernetes-native platform:

1. Orchestrate fleets of AI agents — customer support, code review, data pipelines, or any domain-specific workflow. Each agent gets its own pod, RBAC, and network policy with proper tenant isolation.
2. Administer the cluster itself agentically — point agents inward to diagnose failures, scale deployments, triage alerts, and remediate issues, all with Kubernetes-native isolation, RBAC, and audit trails.

Key Features

PersonaPacks	Helm-like bundles for AI agents — activate a pack and the controller stamps out a full agent team
Skill Sidecars	Every skill runs in its own sidecar with ephemeral least-privilege RBAC, garbage-collected on completion
Multi-Channel	Telegram, Slack, Discord, WhatsApp — each channel is a dedicated Deployment backed by NATS JetStream
Persistent Memory	SQLite + FTS5 on a PersistentVolume — memories survive across ephemeral pod runs
Scheduled Heartbeats	Cron-based recurring agent runs for health checks, alert triage, and resource right-sizing
Agent Sandbox	Kernel-level isolation via kubernetes-sigs/agent-sandbox — gVisor or Kata with warm pools for instant starts
MCP Servers	External tool providers via Model Context Protocol with auto-discovery and allow/deny filtering
TUI & Web UI	Terminal and browser dashboards, or skip the UI entirely with Helm and kubectl
Any AI Provider	OpenAI, Anthropic, Azure, Ollama, or any compatible endpoint — no vendor lock-in

---

Documentation

Topic	Link
Getting Started	deploy.sympozium.ai/docs/getting-started
Architecture	deploy.sympozium.ai/docs/architecture
Custom Resources	deploy.sympozium.ai/docs/concepts/custom-resources
PersonaPacks	deploy.sympozium.ai/docs/concepts/personapacks
Skills & Sidecars	deploy.sympozium.ai/docs/concepts/skills
Persistent Memory	deploy.sympozium.ai/docs/concepts/persistent-memory
Channels	deploy.sympozium.ai/docs/concepts/channels
Agent Sandboxing	deploy.sympozium.ai/docs/concepts/agent-sandbox
Security	deploy.sympozium.ai/docs/concepts/security
CLI & TUI Reference	deploy.sympozium.ai/docs/reference/cli
Helm Chart	deploy.sympozium.ai/docs/reference/helm
Ollama & Local Inference	deploy.sympozium.ai/docs/guides/ollama
Writing Skills	deploy.sympozium.ai/docs/guides/writing-skills
Writing Tools	deploy.sympozium.ai/docs/guides/writing-tools
LM Studio & Local Inference	deploy.sympozium.ai/docs/guides/lm-studio
Writing PersonaPacks	deploy.sympozium.ai/docs/guides/writing-personapacks
Your First AgentRun	deploy.sympozium.ai/docs/guides/first-agentrun

---

Development

make test        # run tests
make lint        # run linter
make manifests   # generate CRD manifests
make run         # run controller locally (needs kubeconfig)

License

Apache License 2.0