Skip to Content
Capabilities

Capabilities

Agentron provides local AI agent orchestration, workflow automation, and multi-agent design in a single, self-hosted platform: Level 1 (ReAct + tools) for chat/RAG, Level 2 (static multi-agent) for workflows, Level 4 (recursive/self-building) for heap.


Feature matrix

FeatureDescriptionPrimary actions
AgentsCreate, edit, delete node and code agentscreate_agent, update_agent, delete_agent, get_agent
WorkflowsMulti-agent orchestration in graphscreate_workflow, update_workflow, add_workflow_edges, get_workflow
ToolsNative, HTTP, MCP toolscreate_tool, update_tool, list_tools, get_tool
RunsExecute workflows/agents, inspect resultslist_runs, get_run
LLM ProvidersConfigure OpenAI, Anthropic, Ollama, etc.list_llm_providers (config via Settings)
Agentron (Chat)Natural-language chat that creates/edits via tool callsBuilt-in; see Agentron (Chat)
SandboxesContainer-engine sandboxes for code execution (Container engine setup)create_sandbox, execute_code
Custom FunctionsJavaScript/Python/TypeScript as toolscreate_custom_function
Knowledge / RAGDocument ingestion and retrievalUI-based; agents can use RAG collections
FeedbackRate agent outputs for learningUI-based; stored for prompt refinement
FilesUpload context fileslist_files
Remote ServersSSH tunnel to remote LLMs (e.g. Ollama)test_remote_connection, save_remote_server

What users can do

  • Design agents: Node graphs or code-based agents
  • Build workflows: Connect agents, set max rounds
  • Add tools: HTTP, MCP, or custom code
  • Run and debug: Execute workflows, inspect runs
  • Chat with Agentron: Natural-language commands; see Agentron (Chat)
  • Rate and improve: Feedback on assistant responses

Limits and constraints

  • Node agents require llmConfigId when using an LLM node
  • Standard tools (std-*) can only update inputSchema/outputSchema
  • Workflows need maxRounds when using looping edges to avoid infinite runs
  • Diagnose before fix: Always use get_run, get_workflow, get_agent, get_tool before applying updates
Last updated on