[
  {
    "id": "ollama-docs-1",
    "tier": "claimed-docs",
    "url": "https://ollama.com",
    "excerpt": "Ollama lets you use open models with your coding agents so you can spend less while keeping your data private.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-docs-2",
    "tier": "claimed-docs",
    "url": "https://ollama.com",
    "excerpt": "Launch Claude Code, Codex, and more with one command.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-docs-3",
    "tier": "claimed-docs",
    "url": "https://ollama.com",
    "excerpt": "Switch models without changing your workflow.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-docs-4",
    "tier": "claimed-docs",
    "url": "https://ollama.com",
    "excerpt": "Dedicated capacity so throughput holds up when you are running several agents at once.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-docs-5",
    "tier": "claimed-docs",
    "url": "https://ollama.com",
    "excerpt": "Frontier capability with more usage. The latest open models match the best closed ones, at a fraction of the cost.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-docs-6",
    "tier": "claimed-docs",
    "url": "https://ollama.com",
    "excerpt": "Your prompts are never tracked or trained on.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-docs-7",
    "tier": "claimed-docs",
    "url": "https://ollama.com",
    "excerpt": "Nothing you run locally ever leaves your machine.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-docs-8",
    "tier": "claimed-docs",
    "url": "https://ollama.com/docs",
    "excerpt": "Run larger models on Ollama's Cloud without the download.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-docs-9",
    "tier": "claimed-docs",
    "url": "https://ollama.com/docs",
    "excerpt": "Learn the local and cloud base URLs, then send a request with curl.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-docs-10",
    "tier": "claimed-docs",
    "url": "https://ollama.com/docs",
    "excerpt": "Use Ollama from Python.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-docs-11",
    "tier": "claimed-docs",
    "url": "https://ollama.com/docs",
    "excerpt": "Use Ollama from JavaScript or TypeScript.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-gh-1",
    "tier": "github",
    "url": "https://github.com/ollama/ollama",
    "excerpt": "connect Ollama to your existing agents or applications such as `Claude Code`, `OpenClaw`, `OpenCode` , `Codex`, `Copilot`,  and more.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-gh-2",
    "tier": "github",
    "url": "https://github.com/ollama/ollama",
    "excerpt": "Use OpenClaw to turn Ollama into a personal AI assistant across WhatsApp, Telegram, Slack, Discord, and more",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-gh-3",
    "tier": "github",
    "url": "https://github.com/ollama/ollama",
    "excerpt": "Run and chat with [Gemma 4](https://ollama.com/library/gemma4):",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-gh-4",
    "tier": "github",
    "url": "https://github.com/ollama/ollama",
    "excerpt": "Ollama has a REST API for running and managing models.",
    "fetchedAt": "2026-08-29T01:24:26.837Z"
  },
  {
    "id": "ollama-comm-1",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=47582482",
    "excerpt": "Ollama was basically shelling out to llama.cpp on mac before, so native mlx should mean better memory handling on apple silicon.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-2",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=47582482",
    "excerpt": "Why are people still using Ollama? Serious. Lemonade or even llama.cpp are much better optimised and arguably just as easy to use.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-3",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=47582482",
    "excerpt": "User benchmark on M4 Pro 48GB: qwen3.5:35b-a3b-q4_K_M eval rate 30.0, nvfp4 66.5, int4 84.4 tokens/sec via 'ollama run' with --verbose.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-4",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=47788385",
    "excerpt": "The biggest advantage for me with ollama is the ability to 'hotswap' models with different utility instead of restarting the server, combined with simple 'ollama pull model'—very convenient for a discord bot with different models per feature.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-5",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=47788385",
    "excerpt": "I prefer Ollama over the suggested alternatives. A new model on HF or Ollama registry? One 'ollama pull' and it's available. Underwhelming? 'ollama rm'.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-6",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=47788385",
    "excerpt": "No mention of the fact that Ollama is about 1000x easier to use. Llama.cpp is a great project but one of the least user friendly pieces of software I've used.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-7",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=47788385",
    "excerpt": "I switched to llama.cpp for everything maybe 6 months ago because of how frustrating every interaction with ollama (the organization) was... llama.cpp does almost everything ollama does better except model management.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-8",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=47788385",
    "excerpt": "Claims Ollama creates lock-in via a proprietary model registry format with hashed filenames that don't work with other tools, and minimizes attribution to llama.cpp.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-9",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39718558",
    "excerpt": "It's pretty funny to see this blog post, when I have been running Ollama on my AMD RX 6650 for weeks. They have shipped ROCm containers since 0.1.27.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-10",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39718558",
    "excerpt": "Ollama runs really, really slow on my MBP for Mistral - as in just a few tokens a second and it takes a long while before it starts giving a result... LM Studio does not have such issues.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-11",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39718558",
    "excerpt": "amdgpu detected, but no compatible rocm library found... unable to verify rocm library, will use cpu: no suitable rocm found, falling back to CPU.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-12",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39718558",
    "excerpt": "There's a thing somewhat conspicuous in its absence - why isn't llama.cpp more directly credited and thanked for providing the base technology powering this tool? GPT4All and LM Studio both credit appropriately, Ollama seems to bend over backwards so they don't have to.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-13",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39125477",
    "excerpt": "What I hate about ollama is that it makes server configuration a PITA. ollama relies on llama.cpp which can keep the model in memory using mlock, but ollama simply won't let you do that. They hide all the server configs in favor of their own 'sane defaults'.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-14",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39125477",
    "excerpt": "So cool! I have been using Ollama for weeks now and I just love it! Easiest way to run local LLMs, we are actually embedding them into our product right now and super excited about it!",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-15",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39125477",
    "excerpt": "Ollama is definitely the easiest way to run LLMs locally... It's like how Docker made it so any application can execute something portably on any machine.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-16",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44739632",
    "excerpt": "Ollama's new app is now available for macOS and Windows... linux sounds out for now. No Linux, that's a bummer. I've been using it in Linux for inference for ages.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-17",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44739632",
    "excerpt": "I am somewhat surprised that this app doesn't seem to offer any way to connect to a remote Ollama instance. The most powerful computer I own isn't necessarily the one I'm running the GUI on.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-18",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44739632",
    "excerpt": "I like the simplicity. This would be perfect for setting up a non-technical friend or family member with a local LLM with just a couple clicks... Multimodal and Markdown support works as expected.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-19",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44739632",
    "excerpt": "completely useless move. there are already tons of good clients for Ollama. The Ollama devs need to focus on being a better llama.cpp, not building clients.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-comm-20",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44739632",
    "excerpt": "Well, they gotta do what they gotta do. But as a developer, this kills the positioning and trust it had for me. I do not see it as a developer tool project anymore.",
    "fetchedAt": "2026-08-29T01:35:59.188Z"
  },
  {
    "id": "ollama-probe-1",
    "tier": "probe",
    "url": "https://ollama.com/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://ollama.com/llms.txt # Ollama\n\n> Ollama is the easiest way to run open AI models locally or in the cloud, with a simple API and 40,000+ integ",
    "fetchedAt": "2026-08-29T01:38:25.116Z"
  },
  {
    "id": "ollama-probe-2",
    "tier": "probe",
    "url": "https://ollama.com/docs.md",
    "excerpt": "PROBE docs-md: HTTP 404 at https://ollama.com/docs.md",
    "fetchedAt": "2026-08-29T01:38:25.116Z"
  },
  {
    "id": "ollama-probe-3",
    "tier": "probe",
    "url": "https://ollama.com/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://ollama.com/openapi.json, https://ollama.com/swagger.json, https://ollama.com/api/openapi.json, https://ollama.com/.well-known/openapi.json)",
    "fetchedAt": "2026-08-29T01:38:25.116Z"
  }
]