- 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.
Learnharness by Eero Alvar
Agent harness for learning difficult things.
Recently added on Oct 28, 2026. The description, category and pricing were filled in from public metadata and have not been checked by an editor yet.
On this page
Usage data: latest readings Nov 18 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number
What Learnharness does
It is free and open source (AGPL-3.0); you pay only for the models it calls.
Key facts
| Maker | Eero Alvar |
|---|---|
| First released | October 2026 |
| License | AGPL-3.0 |
| Main language | TypeScript |
| Open issues and PRs | 562 |
Pricing
Open source under the AGPL-3.0 licence; check the website for any paid hosted plans.
Checked Oct 28, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (AGPL-3.0)
- Closest alternativeLangChain · all alternatives
What's new in Learnharness: November 2026 so far
November brought major new learning tools to Learnharness, including flashcards, coding questions, and a drawing pad, alongside expanded customization options and improved file handling across the platform.
- Flashcards can now be generated from your knowledge graph or uploaded documents, or written by hand.
- New Coding Questions tool lets you solve practice problems in a syntax-highlighted editor with optional tests and model solutions.
- Drawing Pad lets you sketch over questions with pressure-sensitive input, and your drawing accompanies your answer.
- Choose from eleven themes including Catppuccin, Rosé Pine, and Gruvbox, with full light-theme support.
3 releases this month · summarised from the official release notes · all months
Add-ons for Learnharness: save tokens, add memory and tools
LiteLLM
One gateway for 100+ models with spend tracking, budgets, rate limits and fallbacks.
Langfuse
Traces every model and tool call with its cost and latency, and runs evaluations.
Firecrawl
Turns websites into clean Markdown or structured data the agent can read.
E2B
Runs agent-written code in isolated cloud sandboxes instead of on your machine.
Composio
Connects the agent to 1,000+ apps and APIs with managed sign-in.
Mem0
Adds long-term memory, so the agent remembers users and past work across sessions.
Listed because each tool documents support for Learnharness or for agent frameworks in general. Savings and results depend on your workload.
Learnharness alternatives
Best Learnharness alternatives compared · All agent frameworks and SDKs
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
LangChainLangChain |
79 | 41.1M | up 5.7% | down 2.7% | 150K+76/day | 1.5.22d ago | Free (OSS) | |||
| 2 |
LangGraphLangChain |
75 | 20.1M | up 5.5% | up 29.2% | 45.1K+48/day | 1.2.23yesterday | Free (OSS) | |||
| 3 |
AI SDKVercel |
68 | 47.2M | up 3.9% | up 38.4% | 28.1K+30/day | 7.0.1772d ago | Free (OSS) | |||
| 4 |
Claude Agent SDKAnthropic |
64 | 29.3M | up 5.9% | up 37.6% | 8,588+9/day | 0.2.185yesterday | Free (OSS) | |||
| 5 |
MastraMastra |
63 | 3.7M | up 14.9% | up 49.9% | 29.6K+23/day | 1.84.02d ago | Free (OSS) | |||
| 6 |
OpenAI Agents SDKOpenAI |
62 | 7.2M | up 4.8% | up 38.9% | 30.8K+21/day | 0.25.02d ago | Free (OSS) | |||
Ratings from people who use Learnharness
No ratings yet. Used Learnharness? Rate it and say what it is good and bad at.
Learnharness news
-
Learnharness passes 10K GitHub stars
-
Learnharness 0.6.1 released
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.
-
Learnharness 0.6.0 released
Flashcards: generate recall cues from selected knowledge-graph propositions or a PDF/text file, or write cards by hand.; Coding Questions: answer teaching questions and practice problems in a syntax-highlighted editor, with optional starter code…
-
Learnharness gained 2,891 GitHub stars in a week
Now at 7,905 stars.
What changed: recent Learnharness releases
13 stable releases in the last 90 days · Monthly summary · Full changelog
- Flashcards: generate recall cues from selected knowledge-graph propositions or a PDF/text file, or write cards by hand.
- Coding Questions: answer teaching questions and practice problems in a syntax-highlighted editor, with optional starter code, tutor-written tests, test output, and model solutions.
- Drawing Pad: work over the current question or practice problem with a pressure-sensitive pen, eraser, undo and a hand tool for panning. Your drawing accompanies the next answer or message.
- Rich Code Blocks: render chemical structures, musical scores and technical diagrams from SMILES, ABC and TikZ notation, including CircuitikZ and PGFPlots.
- Choose from eleven themes in Settings → Appearance, including Catppuccin, Rosé Pine, Gruvbox, Ivory and Pastel, alongside the original dark palette.
- Adjust individual colors, import a custom theme as JSON, or export the palette you are using. Existing color overrides survive theme changes; Reset all restores the selected theme's colors.
Earlier releases
- Attach files or folders from the desktop composer's paperclip menu, or drag and drop them into a session. Attachments insert local path references.
- Tutors can show snapshots of your own images and annotate them in the conversation.
- Import notes… is now Extract files…, with clearer guidance separating graph extraction from attaching material for a lesson.
- Folder imports skip hidden files and dot-directories, including folders such as .obsidian and .git.
- Optionally restrict learner-facing file tools to listed folders and their subfolders. Credential and agent-transcript locations are protected even when broad source access is enabled.
- Choose Exa, Firecrawl, or hosted Ollama search alongside Brave and Tavily. Configure the selected service's key in Settings; Ollama search uses the hosted service, not a local Ollama installation.
- Choose Files or Folder from Import notes to import multiple files through a continuous queue, with per-file results and support for adding more files while imports are running.
- Import PDFs with selectable text alongside Markdown and text files, up to 25 MB per file. PDF text conversion also gives the tutor's PDF reader more readable words, lines, and prose-column ordering.
- Organize sources in persistent folders: rename sources and folders, and drag them between folders.
- Navigate folders, sources, chains, and propositions with the keyboard, and search the chains view with scoped Find.
- Delete selected sources' graph contributions with confirmation. Session conversations are retained unless you explicitly choose to delete them too; original imported files are not deleted.
- Notes extraction guidance now emphasizes substantive knowledge and reasoning supported by the source. Auditor review starts with ranked existing-proposition matches, with targeted follow-up searches.
- Claude Code integration — connect an installed and configured Claude Code CLI, with an explicit opt-in in Settings → Providers. Authentication and billing follow the CLI's native configuration.
- Custom and local endpoints — configure one OpenAI-compatible endpoint with multiple models directly in Setup or Settings.
- Desktop drag-and-drop file references — drop files into the content area to insert editable path chips into the focused learner editor, or the dictation destination when no editor is focused.
- More reliable image processing — bounded image processing for file reads, PDF pages, and visual-maker screenshots, with format/MIME handling, EXIF-aware resizing, and PDF canvas size guards before…
- Custom-model image delivery — image-bearing requests attempt to deliver pixels even when custom-endpoint discovery omits image-capability metadata.
- Keep the question dock and submission engine aligned with the pending question, and preserve answer/reasoning drafts through streaming completion and synchronization. Based on #265.
- Choose your dictation language. Settings → Providers now has a searchable language selector below the Deepgram key, including supported languages/locales and multilingual transcription.
- Retry failed responses without losing your work. A separate Retry action reruns an eligible failed foreground turn while preserving its submitted input, failed attempts and partial output.
- More reliable new-session opening. Opening text is kept out of the URL, accepted sessions use their normal short chat URL, and failed opening submissions can be recovered without leaving duplicate…
- Repair model selections after changing providers. Disconnected or unavailable selections in other model slots no longer prevent repairing the slot you are editing.
- Long questions fit more reliably. Teaching and practice docks budget space using the actual answer controls and toolbar, including very short windows, instead of relying on a fixed allowance.
- Compaction no longer replays superseded summaries. Only the current valid checkpoint is projected into the conversation.
Learnharness popularity and usage data
The GitHub repository has 10.3K stars, 10,303 of them added in the last 30 days. The latest stable release is 0.6.1, published Nov 12, 2026; there were 11 stable releases in the past 30 days. It was mentioned in 3 Hacker News posts and comments over the last 30 days.
Download the raw daily series: learnharness.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| GitHub stars | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Hacker News mentions | Nov 18, 2026 | Nov 19, 06:26 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
Learnharness FAQ
How much does Learnharness cost?
Open source under the AGPL-3.0 licence; check the website for any paid hosted plans.
Is Learnharness open source?
Yes. Learnharness is open source, released under the AGPL-3.0 license.
How popular is Learnharness?
The GitHub repository has 10.3K stars, 10,303 of them added in the last 30 days. The latest stable release is 0.6.1, published Nov 12, 2026; there were 11 stable releases in the past 30 days. It was mentioned in 3 Hacker News posts and comments over the last 30 days.
What is the latest version of Learnharness?
The latest stable release we track is 0.6.1, published on Nov 12, 2026.
What are the alternatives to Learnharness?
The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.
For the makers of Learnharness badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/learnharness/)
[](https://agentgid.com/agents/learnharness/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
GitHub: amosblomqvist/learnharness. Site rank: learnharness.ai on the Tranco list. See data sources for how each one is collected.
Product facts and pricing were checked against: learnharness.ai, github.com.