Genius Agent

CLI or API | Agent

Version: 4.0.0

Documentation — Installation, deployment, usage across the agent, MCP, and CLI interfaces are maintained in the official documentation.

Overview

Genius Agent is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with GeniusAgent Search Engine for Agentic AI!.

Key Features

• Enterprise-Grade Security: Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
• Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
• Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

CLI or API

This agent wraps the GeniusAgent Search Engine for Agentic AI! API. You can interact with it programmatically or via its integrated execution entrypoints.

Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.

MCP source connector

Run the native MCP surface with genius-mcp. Its signed source tool, genius_ingest_search, searches through the configured provider and idempotently materializes ranked evidence into epistemic-graph. Tool discovery requires no upstream connection; search credentials, graph connectivity, TLS trust, tenant, and policy are all supplied at runtime through AgentConfig and the environment.

uvx --from genius-agent genius-mcp

Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts seamlessly with the Agent Web UI (AG-UI) and Terminal interface.

Running the Agent CLI

To start the interactive command-line agent:

# Optional: override the agent's identity / workspace
export DEFAULT_AGENT_NAME="Genius Agent"
export WORKSPACE_DIR="/path/to/workspace"

# Run the agent server (provider / model / key are CLI args)
genius-agent --provider openai --model-id gpt-4o

Docker Compose Orchestration

The following docker/agent.compose.yml configures the Agent, Web UI, and Terminal Interface together:

version: '3.8'

services:
  genius-agent-agent:
    image: <registry>/genius-agent@sha256:<digest>
    container_name: genius-agent-agent
    hostname: genius-agent-agent
    restart: always
    env_file:
      - ../.env
    command: [ "genius-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9000
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9000:9000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

Graph architecture, governed skill integration, and agent execution guidance are documented in docs/overview.md and docs/usage.md.

Security & Governance

Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:

Access Control & Policy Enforcement

• Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.
• OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
• Scoped Credentials: Execution context runs restricted to the specific caller identity.

Runtime Security Grid

Installation

Pick the extra that matches what you want to run:

# MCP serving runtime
uv pip install "genius-agent[mcp]"

# Full agent runtime (Pydantic AI + epistemic-graph engine) — recommended
uv pip install "genius-agent[agent]"

# Everything (development)
uv pip install "genius-agent[all]"      # or: python -m pip install "genius-agent[all]"

Knowledge-graph database (epistemic-graph)

Every install receives epistemic-graph[full] through the current Agent Utilities base dependency. The [mcp] and [agent] extras add their respective tool and agent runtime layers without changing that database contract. For production — or to share one knowledge graph across multiple agents — run epistemic-graph as its own database service and point the agent at it. Deployment recipes (single-node + Raft HA), connection config, and the full database architecture are documented in the epistemic-graph deployment guide.

Environment Variables

Package environment variables

Inherited agent-utilities variables (apply to every connector)

20 package + 19 inherited variable(s). Auto-generated from .env.example + the shared agent-utilities set — do not edit.

Every variable the agent reads, grouped by purpose.

Agent runtime

Web search providers

Provider is selected in priority order: Searxng > Google > Bing > DuckDuckGo (default, no key required).

Telemetry & governance

See .env.example for a copy-paste starting point.

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

Repository Owners

Contribute

Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:

• Format code using ruff format .
• Lint code using ruff check .
• Validate type-safety with mypy .
• Execute test suites using pytest

Deploy with agent-os-genesis

This package can be provisioned for you — skill-guided — by the agent-os-genesis universal skill (its single-package deploy mode): it picks your install method, seeds secrets to OpenBao/Vault (or .env), trusts your enterprise CA, registers the MCP server, and verifies it — the same machinery that stands up the whole Agent OS, narrowed to just this package. Ask your agent to "deploy genius-agent with agent-os-genesis".

Secrets are read-existing + seeded via vault_sync — you are only prompted for what's missing.

Deploy with agent-utilities-deployment

Provision this package with the consolidated agent-utilities-deployment workflow. It selects an installed-package, editable-source, or immutable-container path; records only runtime secret and TLS-profile references in AgentConfig; and runs doctor, registration, policy, observability, and rollback gates. Ask your agent to "deploy genius-agent with agent-utilities-deployment".

The repository embeds no deployment profile, credential value, certificate path, or environment-specific endpoint. Supply those at runtime through AgentConfig and the configured secret provider.

Governed capability contract

This package ships a compact canonical skill surface with specialist procedures kept as referenced workflows. The current MCP tools, skill metadata, connector_manifest.yml, ontology, mappings, shapes, fixtures, migrations, tool-schema fingerprints, and certification metadata form one versioned capability contract. Validate them together; do not rely on stale tool names or historical per-task skill wrappers.

Runtime endpoints, credentials, certificate trust, tenant identity, retention, and observability policy are deployment inputs and are never packaged values. See Configuration, trust, and privacy before enabling a network transport, connector ingestion, GraphOS delegation, or trace export.