Skip to content

Knuckles-Team agent platform

A governed runtime for building agents, connecting operational systems, and turning every action into durable, explainable knowledge.

Platform documentation Run GraphOS GitHub repositories

Knuckles-Team platform runtime architecture

One platform, clear responsibilities

People use Agent Web UI, Agent Terminal UI, Geniusbot, or Graph OS-hosted messaging channels. MCP, REST, and A2A clients use the same governed Graph OS boundary. Graph OS composes the runtime and delegates agent work to the Agent Utilities control plane. Epistemic Graph commits durable knowledge, evidence, provenance, and reasoning results. Source systems connect through the governed Agent Connector SDK contract.

The public runtime gateway: MCP, REST, A2A, identity, policy, fleet composition, and WebUI hosting.

Documentation · Build status

The browser operator experience for conversations, approvals, tool activity, and graph-backed work.

Documentation · Build status

The agent control plane: agents, workflows, evaluation, skills, and governed execution.

Documentation · Build status

The reasoning and durable knowledge engine for graph, RDF, SQL, vectors, time, blobs, evidence, and provenance.

Documentation · Capability status

The governed source-integration boundary for connector identity, discovery, synchronization, replay, and write-back.

Documentation · Build status

Start at the runtime door

Graph OS is the governed runtime entry point. With Python 3.12+ and uv installed, launch the zero-infrastructure local profile:

uvx --from graph-os setup-config generate --profile tiny
uvx --from graph-os graph-os --transport stdio

The generated profile starts with local, bounded defaults. Continue with the Graph OS quick start for provider configuration, Agent Web UI hosting, messaging, and authenticated network transports.

Follow the flow

If you want to… Start here
Run the platform or connect an MCP/A2A client Graph OS documentation
Use the browser experience Agent Web UI documentation
Build agents, workflows, evaluations, or skills Agent Utilities documentation
Query or operate the knowledge engine directly Epistemic Graph documentation
Build or certify a source connector Agent Connector SDK documentation

Every repository documents its own contract and links back to this same runtime map. The boundaries are deliberate: Graph OS is the door, Agent Utilities controls agent behavior, Epistemic Graph owns durable knowledge and reasoning, Agent Web UI presents the browser surface, and Agent Connector SDK governs source integration.

Project health

Build and release evidence lives with the component that owns it. Use each repository's Actions page for current CI and its Pages Status or Capabilities section for shipped behavior. Public issues and pull requests are tracked in the owning repository so operational and design discussions retain their architectural context.

All five core projects are released under the MIT License.

Pinned Loading

  1. agent-utilities agent-utilities Public

    An agent factory leveraging Pydantic AI and Pydantic AI Harness

    Python 7

  2. epistemic-graph epistemic-graph Public

    A multi-modal agent memory, context, inferencing, analytics engine and database.

    Rust 11 2

  3. agent-webui agent-webui Public

    Forked from pydantic/ai-chat-ui

    Agent Control Plane for Graph OS ecosystem.

    TypeScript 3

  4. agent-terminal-ui agent-terminal-ui Public

    Agent CLI Terminal for Agent Utilities

    Python 1

  5. geniusbot geniusbot Public

    The Ever-learning and ever-improving tool! Click the arrows on the left of each of the items below to see more information about them.

    Python 7

  6. universal-skills universal-skills Public

    Universal Agent Skills

    Python 4 1

Repositories

Showing 10 of 105 repositories

Top languages

Loading…

Most used topics

Loading…