Source grounding

Data Sources in Disp8ch: ground agent work in files, docs, and cited context

Data Sources imports files, local markdown folders, scraped pages, crawled docs sites, and notebooks so agents can answer with receipts and turn findings into work.

Install Disp8chRead quickstart
Disp8ch Data Sources library with uploaded sources and notebook actions
What it does

Turns the feature into usable workspace objects.

Disp8ch treats Data Sources as part of the operating loop. The result is visible, editable, and connected to the other surfaces.

  • Uploads PDF, DOCX, PPTX, TXT, Markdown, HTML, local markdown folders, and crawled pages.
  • Builds searchable, citable context that WebChat, notebooks, workflows, Council, and Hierarchy can use.
  • Turns source findings into board tasks, workflows, council sessions, designs, or reviewable skills.
How it works

Context flows through the app instead of being trapped in chat.

The feature reads from the same workspace objects used by the rest of Disp8ch, then writes back through confirmation-gated actions when work changes state.

  • Sources are chunked, indexed, and grouped into notebooks or source packs.
  • Notebook questions stay bounded to selected material, while WebChat can combine source context with the broader app state.
  • Learning from a source produces a pending skill candidate for review, not an automatic install.
What makes it different

Built for operators who need auditability.

The feature is designed around explicit state, reviewable outputs, and practical handoffs to the next place work should go.

  • The same source can drive a cited answer, a board task, a council debate, or a workflow.
  • Notebooks keep narrow source boundaries when you need them.
  • Source-driven learning remains reviewable and evidence-linked.
Works with

Data Sources is strongest when it connects to the rest of the workspace.

A typical job starts with a user request, pulls in sources or app state, creates a plan, asks for confirmation when something changes, and leaves a trace in the right surface.

WebChatNotebooksCouncilHierarchyWorkflowsBoards
Prompt to tryData Sources
Crawl these docs, summarize the supported API paths, and create follow-up tasks for missing coverage.
Related features

Keep moving through the operating loop.

All features
Disp8ch WebChat showing an assistant conversation with app actions and workspace context
Plain English control

Agentic WebChat

WebChat is the command surface for the whole workspace. Ask questions, build workflows, inspect state, create tasks, run research, and hand work to agents without losing the audit trail.

Disp8ch Memory screen showing stored context, candidates, and review controls
Durable context

Memory

Memory in Disp8ch is local, scoped, searchable, and reviewable. The agent can propose what it learned, but you stay in charge of what becomes durable.

Disp8ch workflow canvas with connected automation nodes
Automation canvas

Visual Workflows

The workflow canvas turns repeatable work into connected nodes for triggers, agents, files, HTTP, RSS, documents, memory, logic, boards, channels, and response handling.

Install

Try Data Sources on your own machine.

Start local, connect only the providers and channels you want, and keep risky actions approval-gated.

Linux, macOS, or WSL
curl -fsSL https://raw.githubusercontent.com/aaronnat23/disp8ch/main/scripts/install.sh | bash -s -- --repo https://github.com/aaronnat23/disp8ch.git