universelabSCI · CLI · BIO
ESEspañol

Canopy

Canopy

Last updated

Canopy (harness-canopy) is a modern, self-contained MCP (Model Context Protocol) server and terminal UI for orchestrating AI agent sessions, background tasks and file event triggers. One Rust binary, zero runtime dependencies.

It turns a single machine into a small agent operations center:

  • Schedule agents on cron expressions or file-system events.
  • Run interactive agents in real PTYs with full terminal emulation.
  • Coordinate multiple agents working in the same workspace.
  • Remember — a project-scoped knowledge graph that persists facts, patterns and session summaries across sessions.
  • Search your own documents with a local-first RAG pipeline.
  • Automate multi-step processes with a DAG graph engine.

Everything persists in an embedded SQLite database under ~/.canopy/ — no external services, no cloud account.

The pieces

Piece What it does
Daemon MCP server (Streamable HTTP + stdio), scheduler, watcher engine, database
Canopy Hub (TUI) Full-screen terminal UI for agents, graphs and system metrics
36 MCP tools Agent management, harness, intelligence, identity, skills, graphs, crews, config, specs, queues, nodes, catalogue, RAG, projects, sessions, session shelf, remote control, scheduled prompts
Seed identities Persistent, evolvable agent personalities stored as TOML
Gamification 28 missions across 6 categories tracking usage milestones

How the documentation is organized

  • Installation — install and set up the daemon.
  • Quick Start — daemon, setup wizard, first agent.
  • The TUI — Canopy Hub — the interactive terminal interface.
  • Agents — interactive, background and terminal agents; seed identities.
  • Intelligence & Sync — knowledge graph and multi-agent coordination.
  • Graphs — the DAG graph engine: overview and structure.
  • Template Variables — placeholders in agent prompts and check commands.
  • Ensembles — parallel, cascade and round-robin member groups, crews, availability.
  • Execution — commit rights, self-reports, retries, the execution limit, lifecycle, deterministic commits, spec notes.
  • Isolation — sandboxes, concurrency, and named mutexes.
  • Hooks and Queues — event-keyed hooks, the spec backlog, and spec queues.
  • Sharing Graphs — export and import, validate, and install from the catalogue.
  • Node Documents — reusable node documents.
  • Graph Operations — archive and restore, node run history, the event log, engine tuning.
  • Graph patterns — the shapes a graph can take, and where each breaks.
  • Graph catalogue — ready-made graphs to install.
  • RAG Pipeline — personal document search.
  • MCP Tools — all 36 tools by category.
  • CLI Reference — every canopy command.

Part of UniverLab

Canopy is an experiment of UniverLab, an open computational laboratory. It follows the lab’s engineering principles: one tool one job, reproducibility first, offline-friendly design.