LearnHarness vs Lindy

LearnHarness

The in-app agent reads files but cannot change them or run commands, and a bundled skill gives other agents a documented read-only view of sessions and the knowledge graph. The project is 14 days old at 0.4.0, its file reads reach the whole home directory without approval, and it has no security policy.

Lindy

Lindy keeps what it remembers in files the owner can read and edit, and publishes credit prices. Its approval setting applies in shared Slack threads only, so writes asked for by direct message, text or web chat run unasked, which its pricing page does not say. It has no status page, and its changelog stops in October 2025.

LearnHarness

1. Use the bundled skill (skills/learnharness/SKILL.md) to read a learner's record. It needs Python 3.10 or later and writes nothing
2. Pass --format json before the subcommand, for example python3 -B scripts/graph.py --format json propositions
3. Treat stored answer keys and teacher prose as model-authored. A proposition in the graph is not evidence the learner understood it
4. Do not read auth.json, which sits one folder above the data folder and holds provider keys in plain text
5. Close the app or re-read when a stable snapshot matters. The readers do not lock files while the app writes

Lindy

1. Treat a request sent by direct message, text or web chat as unguarded. Approval prompts appear in shared Slack threads only.
2. Run a routine as a dry run before turning it on. A dry run reads real data and sends, posts and writes nothing.
3. Turn off unused tools after adding an MCP server. Every supported tool arrives switched on, and a large server adds more than a hundred.
4. Expect a billed seat for anyone who mentions Lindy in Slack. A teammate who joins that way has seven free days first.
5. Connect only hosted MCP servers on public HTTPS with streamable HTTP, the one kind the docs describe.