← Back to directory

Trinity

Community

Sovereign AI Agents Platform supporting Claude Code, Codex, Gemini agents. Apache 2.0.

GitHub source repository ↗

★ 488 Stars Category · Dev Tools Very popular Source revision 802965718087

62FMRS · C

Reliability

9/20

Security and permissions

12/20

Maintenance

15/20

Documentation

14/20

Setup experience

12/20

Trinity is a feature-rich self-hosted AI agent orchestration platform. It provides extensive MCP tools for agent management, scheduling, communication, monitoring, and governance. Suitable for production use, but requires Docker and self-hosting infrastructure. MCP integration is via streamable-http and requires authentication.

Read the FMRS scoring method →

Trinity is a sovereign AI agents platform that lets you build and run proprietary systems, from fully autonomous businesses to self-improving cognitive systems, all governed, auditable, and on infrastructure you control. Each agent runs in its own isolated Docker container with real-time observability, fleet-wide scheduling, agent-to-agent delegation, and a tamper-evident audit trail. It supports multiple runtimes: Claude Code (Anthropic), OpenAI Codex, and Gemini CLI (Google). The platform includes a Vue.js frontend, FastAPI backend, and an MCP server (port 8080) exposing 90+ tools for external orchestration.

Tools

list_agents

List all agents with status.

get_agent

Get detailed agent information.

get_agent_info

Get agent template metadata (capabilities, commands, etc.).

create_agent

Create a new agent from template.

deploy_local_agent

Package and deploy a local agent directory.

start_agent

Start an agent container.

stop_agent

Stop an agent container.

rename_agent

Rename an agent.

delete_agent

Delete an agent.

initialize_github_sync

Initialize GitHub sync.

set_agent_github_pat

Set per-agent GitHub PAT.

chat_with_agent

Send a message and get response (supports parallel and async modes).

get_chat_history

Retrieve conversation history.

get_agent_logs

View container logs.

fan_out

Dispatch N parallel tasks to an agent and collect results.

send_message

Proactive user message by verified email (agent-initiated).

send_group_message

Proactive group messaging.

list_channel_groups

List channel groups.

deploy_system

Deploy multi-agent system from YAML manifest.

list_systems

List deployed systems with agent counts.

restart_system

Restart all agents in a system.

get_system_manifest

Export system configuration as YAML.

list_templates

List available templates.

inject_credentials

Inject credential files directly to agent.

get_credential_status

Check credential files.

get_agent_ssh_access

Generate ephemeral SSH credentials for direct terminal access.

list_schedules

List all schedules.

create_schedule

Create a new schedule.

update_schedule

Update a schedule.

delete_schedule

Delete a schedule.

enable_schedule

Enable a schedule.

disable_schedule

Disable a schedule.

trigger_schedule

Trigger a schedule manually.

list_executions

List recent executions.

poll_async_result

Poll for async results.

get_agent_activity

Get agent activity summaries.

list_tags

List all agent tags.

get_tag

Get a tag.

set_tag

Set a tag.

add_agent_tag

Add a tag to an agent.

remove_agent_tag

Remove a tag from an agent.

list_subscriptions

List subscriptions.

register_subscription

assign_subscription

Assign a subscription to an agent.

unassign_subscription

Unassign a subscription from an agent.

list_skills

List skills.

create_skill

Create a skill.

update_skill

Update a skill.

delete_skill

Delete a skill.

assign_skill

Assign a skill to an agent.

get_fleet_health

Get fleet health.

get_agent_health

Get agent health details.

trigger_health_check

Trigger health checks.

configure_payments

Configure Nevermined x402 payments.

toggle_payment

Toggle payment.

view_payment_history

View payment history.

send_notification

Send structured notifications from agents to platform.

emit_event

Emit events.

subscribe_to_events

Subscribe to agent events.

list_event_subscriptions

List event subscriptions.

delete_event_subscription

Delete an event subscription.

git_status

Get Git status.

git_sync

Sync Git.

git_log

Get Git log.

git_pull

Pull Git changes.

git_sync_state

Get sync state.

git_recovery_reset

Recovery reset.

list_operator_queue

Read human-in-the-loop approval items.

respond_to_approval

Respond to approval items.

run_loop

Run bounded sequential task loops.

monitor_loop

Monitor loops.

stop_loop

Stop loops.

publish_report

Publish structured agent reports to dashboard.

write_memory

Write per-user memory for channel sessions.

list_pipelines

Introspect agent-defined long-running pipelines.

inspect_pipeline

Inspect pipeline.

make_phone_call

Place an opt-in outbound phone call.

Setup

Clone the repository: git clone https://github.com/abilityai/trinity.git && cd trinity
Copy .env.example to .env and set SECRET_KEY (openssl rand -hex 32) and ADMIN_PASSWORD.
Run ./scripts/deploy/build-base-image.sh to build the base image.
Run ./scripts/deploy/start.sh to start all services.
Open http://localhost to complete the setup wizard, set admin password, and configure API keys.
Configure MCP clients with 'mcpServers' pointing to http://localhost:8080/mcp, using 'Authorization: Bearer YOUR_API_KEY' header.

claude_desktop_config.json

{
  "mcpServers": {
    "trinity": {
      "type": "streamable-http",
      "url": "http://localhost:8080/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Generate and validate client config

Fit and risk

Best for

Organizations needing self-hosted AI agent deployment with data residency and audit.
Development teams wanting to run agents with Claude Code, Codex, or Gemini.
Production-grade agent orchestration with isolation, scheduling, and observability.

Not for

Users needing zero-configuration hosted solutions (requires Docker and self-hosting).
Those seeking a lightweight agent framework without Docker.
Teams not interested in managing the platform themselves.

Required permissions

MCP server requires an API key (Bearer token) for authentication.
Agents themselves run in Docker containers and may require network access to APIs and external endpoints.
The platform stores credentials (encrypted) and Git data.
Admins and users control access through role hierarchy (admin, creator, operator, user).

Risks and side effects

Self-hosting requires infrastructure management; misconfigurations could lead to security issues.
Agent-run code may be untrusted; Docker isolation is essential.
Credentials are stored via Git and encrypted, but need proper protection.
Webhooks may expose public endpoints, mitigated with HMAC signatures.

Troubleshooting

Ensure Docker daemon is running and you have permissions.
Check backend logs: docker compose logs -f backend.
Verify SECRET_KEY and ADMIN_PASSWORD are set in .env.
Ensure ports 80, 8000, 8080 are not in use.
Test MCP connection: curl http://localhost:8080/mcp.

Use cases

Deploy autonomous AI agents on your own infrastructure with governance and audit.

Manage a fleet of agents including scheduling, delegation, and monitoring.

Run agents written with Claude Code in production.

Coordinate multi-agent systems from a single YAML manifest.

Supported clients

Claude DesktopFull support

Claude CodeFull support

Related MCP servers

Compare with other MCP servers