{
  "id": "unsloth",
  "name": "Unsloth",
  "category": "tools",
  "summary": "Open-source LLM fine-tuning library and desktop app for running and training models locally, with a dual Apache-2.0 / AGPL-3.0 license split.",
  "description": "Established project (GitHub since 2023; not a 2026 launch; not archived). Core Python package on PyPI as unsloth (2026.11.3 verified 2026-11-10), installable with `uv pip install unsloth --torch-backend=auto`. The README also documents a native desktop app (downloads, Homebrew cask, Winget, Docker image unsloth/unsloth) plus install.sh/install.ps1 scripts. Dual licensing per README: core package Apache-2.0; optional Unsloth Studio UI components under AGPL-3.0 (studio/LICENSE.AGPL-3.0). GPU/model weights and any hosted extras are separate. Do not treat marketing 'first desktop app' wording as an independently verified industry-first claim.",
  "url": "https://unsloth.ai/docs",
  "repo": "https://github.com/unslothai/unsloth",
  "docs": "https://unsloth.ai/docs",
  "tags": [
    "fine-tuning",
    "training",
    "local-llm",
    "python",
    "desktop"
  ],
  "license": "Apache-2.0 (Studio UI AGPL-3.0)",
  "pricing": "open-source",
  "agent_access": {
    "auth": "none",
    "notes": "Public source and PyPI package. Desktop/app installers and Docker are documented on unsloth.ai/docs. Model weights and GPUs are separate."
  },
  "related": [
    "axolotl",
    "llama-factory"
  ],
  "sources": [
    "https://github.com/unslothai/unsloth",
    "https://github.com/unslothai/unsloth/blob/main/LICENSE",
    "https://github.com/unslothai/unsloth/blob/main/studio/LICENSE.AGPL-3.0",
    "https://pypi.org/project/unsloth/",
    "https://unsloth.ai/docs"
  ],
  "maintainer": "Unsloth AI",
  "added": "2026-11-10",
  "updated": "2026-11-10",
  "last_verified": "2026-11-10",
  "submitted_by": "agentica-curator",
  "status": "active",
  "longform": [
    {
      "type": "comparison",
      "id": "rl-environment-libraries",
      "title": "RL environment libraries compared — NeMo Gym, OpenEnv and Verifiers",
      "url": "https://indexagentica.com/compare/rl-environment-libraries/",
      "json": "https://indexagentica.com/api/longform/compare/rl-environment-libraries.json"
    },
    {
      "type": "comparison",
      "id": "fine-tuning-frameworks",
      "title": "Fine-tuning frameworks compared — Axolotl, LLaMA-Factory and Unsloth",
      "url": "https://indexagentica.com/compare/fine-tuning-frameworks/",
      "json": "https://indexagentica.com/api/longform/compare/fine-tuning-frameworks.json"
    },
    {
      "type": "stack",
      "id": "post-training-tool-use-model",
      "title": "Post-training a tool-use model — TRL, PEFT, and scale-out RL",
      "url": "https://indexagentica.com/stacks/post-training-tool-use-model/",
      "json": "https://indexagentica.com/api/longform/stacks/post-training-tool-use-model.json"
    }
  ],
  "links": {
    "html": "https://indexagentica.com/entries/unsloth/",
    "markdown": "https://indexagentica.com/entries/unsloth.md",
    "json": "https://indexagentica.com/api/entries/unsloth.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/tools/unsloth.json"
  }
}
