Categories
AI agent platform AI helpdesk Human handoff Customer support Knowledge base Self-hosted AIStars
Forks
Watchers
Developer links
NexusDesk
NexusDesk is a self-hosted agent platform whose first complete application turns customer support conversations into retrieved answers, tool calls, and confirmed tickets on your own infrastructure. An agent takes a request, retrieves context from your knowledge base, decides what to do, calls business tools, asks a human to confirm consequential actions, executes, records everything, and feeds evaluation, all as one visible loop rather than a black-box chat. The Harness around that loop is the engineering control layer: it governs permissions and execution boundaries, manages agent memory, routes human handoffs, and keeps an audit trail, so autonomy stays inside lines you drew. You configure, publish, and roll back agents, manage documents, chunks, indexes, and published knowledge versions, and connect Chat, Embedding, Rerank, OCR, and speech models through versioned profiles. Business APIs plug in as tools with their own credentials, parameters, and permissions, and support staff can take over a conversation, draft a ticket from it, and confirm follow-up work without leaving the flow. Channels and application APIs with server-sent events expose the same capabilities to your other systems, while execution records, model and tool call logs, and evaluation results show what the agent actually did. One PostgreSQL handles storage, job queues, and cross-process messaging, and one Compose file starts the stack. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.
Benefits
- Autonomy with a control layer
- The Harness governs permissions, execution boundaries, memory, human handoff, and audit around the agent loop, so agents act inside limits you set and every consequential step can require human confirmation.
- Support flow, end to end
- Knowledge retrieval, business tool calls, conversation takeover, ticket drafting, and human confirmation connect in one reference application, moving a customer question from first message to tracked follow-up.
- One database, one Compose
- PostgreSQL handles storage, job queues, and cross-process messaging, so the initial deployment starts from a single Compose file with no Redis, message broker, or Kubernetes required.
- Every action on record
- Execution records, model and tool call logs, evaluation results, and operation audits show what the agent decided and did, making behavior reviewable instead of anecdotal.
Features
- ReAct agent execution
- Configure, publish, and roll back agents that reason and call tools through an asynchronous LangGraph ReAct loop with durable task lifecycle and state management.
- Knowledge and retrieval
- Manage documents, chunks, indexes, and published versions with keyword retrieval built in and optional Milvus vector retrieval when semantic search is needed.
- Versioned model profiles
- Manage connections and versioned profiles for Chat, Embedding, Rerank, OCR, and speech models, binding each agent to the models it may use.
- Business tool integration
- Connect business APIs as agent tools with managed credentials, parameters, permissions, and recorded execution results per call.
- Channels and open APIs
- Expose support capabilities through channel APIs, application APIs, and server-sent events, so existing business systems reach the same agents.
