OpenAgents

Browser automation via Playwright MCP (official Microsoft headless browser)

Image generation and manipulation via MCP

PDF parsing and extraction via MCP

Autonomous tool discovery, evaluation, and integration for agent self-enhancement

Route OpenOS tasks to the correct product skill.

Enrich CRM contacts with LinkedIn and décideur data.

CRM read + staged follow-up via orchestrator approval.

W4: PO ticket → Dev OpenCode → QA integrator.

Submit goals, auto-plan, dispatch OpenAgents runs.

Rewrite rough asks into ready OpenTicket stories.

OpenTicket MCP: create, read, transition tickets.

Axon MCP: search OpenOS docs and graph knowledge.

High-contrast Mermaid mesh diagrams for OpenBrain chat and RAG replies.

QA sign-off: AC, tests, regression, integrator.

Spawn OpenOS OpenCode via invoke_opencode tool.

Default OpenOS agent loop when no skill fits.

Wire mesh hops: CC-*, env, compose, MCP parity.

Industrial orchestrator: gates, approvals, DLQ.

Author and run OpenAgentUI YAML workflows headlessly.

OpenAgents CLI, TUI, desktop, dashboard surfaces.

Brain missions, ticket ETA, ask_brain status queries.

Human GUI shell composing OpenOS module APIs.

Register CC-* hops and sign ContractEnvelope payloads.

DALL-E images and Brain deliverable handoff.

Add MCP tools with REST parity and CC-* first.

OpenAgents session memory, Honcho, Brain bridge.

Meeting audio intel; observations to Brain and CRM.

NL goals to NormalizedGoal JSON for orchestrator.

Flutter OpenPro-Mobile hiring app development.

Emit and query RecEvents with correlation_id audit.

Triage findings; bridge OpenSec to OpenTicket.

OpenTeam harvests, market intel, and agent dispatch.

HinSchG whistleblower deploy and SDK integration.

TikTok harvest leads into OpenPro accounts.

Branch, code via OpenCode, push, handoff to QA.

Verify agent branch, squash merge main, cleanup.

Configure, extend, or contribute to OpenAgents.

Operate the Antigravity CLI (agy): plugins, auth, sandbox.

Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.

Delegate coding to xAI Grok Build CLI (features, PRs).