LearnHarness: agent harness for learning
LearnHarness uses AI agents to plan and teach from your current understanding. A knowledge graph carries lessons across sessions. AGPL-3.0.
Key features
- Measures where understanding ends, then plans a dependency map from there to the goal
- Teaches one reasoning step at a time, then runs separate practice sessions
- Stores propositions and reasoning chains in a knowledge graph across sessions
- Chats, the graph, settings, and API keys are stored on your machine
- Supports 30+ providers, including OpenAI, Anthropic, Google, DeepSeek, and OpenRouter
- Apple Silicon macOS build is signed and notarized. Windows x64 installer is unsigned
- Linux x64 ships as an AppImage or a Debian/Ubuntu deb. All three platforms support in-app updates
- AGPL-3.0. System prompts are visible and editable. You pay providers for model use
- Category
- Agents
- Who it's for
- People who want an agent to teach a subject from what they already understand.
- Tags
- agentlearningopen-modelslocal-inferenceauthsecretsfonts-iconsimage-video
- Website
- github.com
- Listed
- 2026-10-26
Frequently asked questions
Is LearnHarness free?
Yes. LearnHarness is open source and free to use.
What is LearnHarness used for?
Agent harness that plans and teaches from your current understanding, then keeps a knowledge graph. AGPL-3.0. Typical uses: measures where understanding ends, then plans a dependency map from there to the goal; teaches one reasoning step at a time, then runs separate practice sessions; stores propositions and reasoning chains in a knowledge graph across sessions.
What are the best LearnHarness alternatives?
Alternatives in the same category include Agensh, Harness², OpenShell, Haystack, Browser Use.
Related in Agents
See all →- Agensh Self-organized multi-agent harness. Agents claim sub-tasks and merge progress without a central orchestrator. MIT.
- Alter Privileged access for AI agents. Vaulted credentials, per-call policy, and an audit log. Free tier is 10,000 API calls a month.
- Harness² Framework that refines an agent harness on new tasks while model weights stay fixed. Apache 2.0.
- Omnara Open-source agent API for any model and machine. Self-host free under Apache 2.0, or use the cloud with a $0 platform fee.
- OpenShell Safe, private runtime for fleets of autonomous AI agents. Sandboxes enforce file, syscall, and network policy. Apache 2.0.
- Agentic Batch Changes Describe a change in plain language. The agent scopes it across your indexed codebase and tracks it through to merge.