nakama: An AI workspace where teams share agents, skills, and automations that the whole company builds on.
What problem it solves
Teams need a shared environment where AI agents can use organizational tools, skills, memory, and communication channels without being tied to a single operator or machine. Nakama addresses the setup and coordination complexity of deploying such agents through a dashboard, organization and role controls, and isolated agent identities.
Key features
Team and Organization Management — Run one server for multiple organizations with invitations, roles, and isolated agents.
Source: README
Configurable AI Agents — Each agent has its own prompt files, tools, skills, memory, identity, and permissions in a dedicated control center.
Source: README
Channel and Integration Support — Connect agents to common messaging channels and Composio-powered external applications from the Integrations area.
Source: README
Flexible Deployment Options — Start with managed hosting, run locally with Bun, or deploy the application in a Docker container.
Source: README, docker-compose.yaml, Dockerfile
Web Dashboard and API — Use the chat-oriented dashboard to work with agents, while the server exposes interactive API documentation.
Source: README
Quick start
Copied verbatim from the project's README.
# Install dependencies
bun install
# Start the web (starts the server automatically if needed)
bun run dev:web# Pull and run the latest image
docker pull ghcr.io/ahmadrosid/nakama:latest
umask 077
printf 'NAKAMA_SECRETS_KEY=%s\n' "$(openssl rand -base64 32)" > nakama-secrets.env
docker run -d -p 4310:4310 -v nakama-data:/nakama/data --env-file nakama-secrets.env --name nakama ghcr.io/ahmadrosid/nakama:latestWho it may suit
Inference: This may suit teams that want to operate shared AI agents with organizational access controls, reusable skills, and access to messaging channels. It may also suit developers seeking a local or Docker-based setup for an agent platform.
Topics to discuss
Which shared agent skills and tools should teams standardize first?
How should agent memory and permissions be governed across multiple organizations?
Which deployment option best fits a team balancing local control, operational simplicity, and managed hosting?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/ahmadrosid/nakama#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…