Agent harness for learning difficult things.

★ 9,652⑂ 1,292👁 31⑃ 338● 380▤ 13
TypeScriptAGPL-3.0Created 2026-10-16
TA的项目
下载:0.6.10.6.1 ↓0.6.12026-11-12
+167
日增长
+2,794
周增长
9,652
stars
1,292
forks
31
watchers
338
prs
380
issues
13
releases

README

An agent harness for learning.


  Download ·
  How it works ·
  Documentation ·
  Issues ·
  Discord


LearnHarness uses AI agents to plan and teach lessons from your current understanding to your goal. It builds a detailed picture of what you understand and how you reason. That picture is updated as you learn.

Instead of just giving you an explanation, it uses your answers and thinking to decide what you need next. Teaching builds understanding one reasoning step at a time. Practice makes it usable. A persistent knowledge graph carries it across sessions.

!LearnHarness teaching session

 How it works

1. Measure. Before teaching, the agent finds where your understanding ends on each part the lesson depends on. Your answers, confidence, and thinking show it where to start.
2. Plan. It works out a dependency map from that starting point to your goal. You can see the plan, and the lesson adapts when your understanding turns out different.
3. Teach. Each step builds on something you already understand. You predict, get an explanation, and check your understanding. Confusions are repaired before anything is built on them. The aim is for the goal to feel obviously true, not merely familiar.
4. Practice. Separate sessions pose varied problems that require the right knowledge to come to mind without being named first. Problems and hints adapt to your reasoning.

Think out loud. The thinking fields let you explain your reasoning, uncertainties, and reactions in your own words. This is how the agent gets a detailed picture rather than just a record of right and wrong answers. You can type or use dictation.

Bring your files. In the desktop app, attach PDFs, photos, or any other file with the paperclip, or drag them in. The file stays where it is: the message carries its path, and the agent reads it from there.

The agent can also research questions in the background, create visual explanations, show your own images in the lesson and mark them up with arrows and labels, and build interactive demonstrations.

 Knowledge that carries forward

What you are taught accumulates as propositions and reasoning chains: individual claims and the premises that lead to them. The graph shows this structure, with links back to the source sessions. You can also import notes.

Future teaching sessions can read the graph instead of starting from scratch. Practice sessions can draw their material from it. It stores the ideas and their connections, not ratings of your ability.

!LearnHarness knowledge graph

 Download and get started

Download from learnharness.ai · GitHub Releases

- macOS (Apple Silicon): signed and notarized DMG. Drag the app to Applications.
- Windows (x64): run the installer. It is currently unsigned; Windows may show an “unknown publisher” or SmartScreen warning.
- Linux (x64): make the AppImage executable and open it, or install the Debian/Ubuntu .deb.

Choose your models, then start a session with what you want to understand. You can use provider A

Top issues

Discussions

Latest release

0.6.1 v0.6.1 2026-11-12
Fixes

- Fix typing delays in answer and thinking fields during lessons.
- Fix Flashcards generation failing on OpenCode Go with MissingSessionID.
- Fix compaction overwriting newly saved skips, question dismissals, direction changes and pause state.
- Recover over-escaped code blocks while leaving normal code and mixed or incomplete fences unchanged.
- Read llama.cpp context limits from nested model metadata when necessary.
- Add common Nix profile directories to Claude Code discovery.

 Reading and performance

- Render Markdown, LaTeX and code in graph cards and expanded Chains s

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON