Skip to content
Fossfits

Categories.

  1. 1. Coding agentsAgents and editors that read a repo, run tests, and propose patches. Fit depends on OS, terminal comfort, and whether you want a GUI.14
  2. 2. Local AIRun language models on a laptop or a home GPU. Chat, complete, and serve weights without sending prompts to a vendor.13
  3. 3. RAG and app buildersDocument Q&A workspaces and visual LLM app studios. Chat with your files, ship a workflow UI, keep the models you already run.11
  4. 4. Image AIDiffusion UIs and local image generation. Almost all of them want a GPU. A few degrade to CPU with patience.9
  5. 5. Speech AILocal speech-to-text and text-to-speech. Transcription, dictation, and voice synthesis you can run on your machine.9
  6. 6. Vector databasesSelf-hosted stores for embeddings and similarity search. The retrieval layer under RAG, not the chat UI.9
  7. 7. Video AILocal text-to-video and image-to-video generators. Expect a serious GPU. Fit is VRAM first, then workflow.8
  8. 8. Video editorsDesktop editors for cut, timeline, and export. CapCut-class jobs on your machine without a cloud account.8
  9. 9. Fine-tuningTrain or adapt open models on your own GPU. LoRA, full fine-tunes, and tooling around datasets and recipes.8
  10. 10. AutomationSelf-hosted workflow engines that glue APIs, webhooks, and AI steps together without a Zapier bill.8
  11. 11. LLM infrastructureServing, gateways, and observability around models. Heavier than a chat UI. Closer to production traffic.8