Give your agent a memory, a map, and a health plan.
Long agent sessions bury their best clues in scrollback. Harness Plus keeps the receipts: Task Canvas evidence trails, local semantic recall, and share-ready skills — all optional, all local-first. 🧸
Your agent works hard.
Its best clues deserve better than line 4,000.
A tool call surfaces the golden hint. A test log answers the big question. Ten minutes later, it's all buried — and everyone pays for it.
Forgotten clues
The crucial output scrolls away, and the session quietly loses the shape of the work.
Repeated dead ends
Without a map of what failed, the agent happily tries the same broken path again.
Unverifiable answers
"Trust me" is not a citation. Final answers should point back to real evidence.
Seven little helpers, one happy harness.
Every piece is optional and independent. Take one, take all — Hermes Agent itself is never modified.
Context Canvas
A tiny library that keeps short JSON nodes plus evidence refs — so every finished note has a path back to the facts.
Read the origin story →Canvas MCP sidecar
Native MCP tools for Hermes: canvas_start, canvas_add_ref, canvas_search, canvas_closeout and friends.
Autopilot plugin
Caches full sanitized tool results, then adds only failures, verifications, and state changes to the map. Fail-open, never edits conversation history.
Qdrant recall kit
Index selected skills and recent sessions into your own local Qdrant — with dry-run previews and secret-pattern redaction.
Recall watchdog
Scheduled health checks that stay quiet on green and get specific on failure — plus bounded Docker restart helpers.
Skills & checklists
Drop-in Hermes skills and ops checklists that teach the habits: keep the map, find it again, share cleanly.
Delegation calibrator
Optional complexity × Bayesian evidence for direct versus luna_max — with Baton and the main agent still in charge of judgment.
From zero to first canvas in about a minute.
Three copy-paste steps. The full install guide covers MCP wiring, the autopilot plugin, and Qdrant helpers.
Grab the toolbox
Clone the repo and hop in.
Prove it works
Install and run the smoke tests.
Start a canvas 🎉
Give your first task a memory.
Cute on the outside, careful on the inside.
Good questions, honest answers.
Does it modify Hermes Agent?
Nope! Everything is an optional outer layer — adapters, plugins, sidecars, skills, and checklists. Remove any piece and Hermes keeps running exactly as before.
Where does my data go?
Nowhere. Canvases live under ~/.hermes/context-canvas, and Qdrant recall binds to 127.0.0.1 by default. Session indexing skips system prompts and tool outputs, redacts common secret patterns, and always supports --dry-run previews.
Do I need all seven pieces?
Not at all — they're independent. Lots of value starts with just the Task Canvas CLI. Add the MCP sidecar, autopilot plugin, Qdrant recall, or the optional delegation calibrator whenever your workflow asks for them.
What do I need to run it?
Python 3.10+, plus a working Hermes Agent install for the MCP and plugin pieces. The Qdrant helpers want a local Qdrant (Docker works great) and fastembed. Details live in the install guide.