[
  {
    "id": "morph-docs-1",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/introduction",
    "excerpt": "Point any OpenAI SDK at `https://api.morphllm.com/v1`. One API key covers the open-weight chat models and the specialized tools",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-2",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/introduction",
    "excerpt": "Small text classifiers that label a turn in ~90ms — jailbreaks, NSFW, stuck-in-a-loop, user frustration.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-3",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/quickstart.md",
    "excerpt": "Move a production agent off Anthropic or OpenAI onto Kimi K3 — a 5% traffic trial or a full migration, gated by Reflexes.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-4",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/quickstart.md",
    "excerpt": "A canary keeps your current provider, sends a slice of production traffic to Kimi K3, and compares Reflex results before you switch.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-5",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/quickstart.md",
    "excerpt": "Install the Morph MCP so Claude Code can read it",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-6",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/sdk/components/reflexes/custom.md",
    "excerpt": "A small Reflex trains in about 30 seconds.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-7",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/guides/coding-agents.md",
    "excerpt": "Claude Code speaks the Anthropic Messages API, which Morph serves natively at `/v1/messages`.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-8",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/guides/coding-agents.md",
    "excerpt": "Keep your current Codex model and give it `edit_file` backed by `morph-v3-fast` at 10,500+ tok/s",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-9",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/guides/mcp.md",
    "excerpt": "Connect your favorite AI tools to Morph's blazing-fast file editing via Model Context Protocol.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-10",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/guides/mcp.md",
    "excerpt": "Use Morph's Warp-Grep for fast, local code search alongside your MCP setup.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-11",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/sdk/components/fast-apply.md",
    "excerpt": "Fast Apply merges just the changed lines at 10,500 tok/s, 98% accuracy.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-12",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/sdk/components/compact.md",
    "excerpt": "Drop filler from chat history and code context at 33,000 tok/s. 50-70% reduction, every surviving line byte-for-byte identical to input.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-13",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/sdk/components/batch.md",
    "excerpt": "Run thousands of chat completions offline at half price.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-14",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/sdk/components/caching.md",
    "excerpt": "Prefix caching is on for every open source model. No configuration, no cache-write surcharge.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-15",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/dedicated-endpoints.md",
    "excerpt": "Reserve model capacity by choosing a model and plan. Morph provisions and operates it",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-docs-16",
    "tier": "claimed-docs",
    "url": "https://docs.morphllm.com/endpoints.md",
    "excerpt": "Anthropic Messages supports the same open source chat models, token billing, and rate limits.",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-gh-1",
    "tier": "github",
    "url": "https://github.com/morphllm/morph-demos",
    "excerpt": "Use Morph's API to intelligently modify existing code at 4,500+ tokens/sec",
    "fetchedAt": "2026-09-14T23:38:45.176Z"
  },
  {
    "id": "morph-comm-1",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44490863",
    "excerpt": "Have been using morph for a while (I am one of the authors of goose) and was surprised when introduced at the boost it gave me (much less iteration with the main expensive LLM). Used it with claude 3.5, 3.7, 4 and currently with o3/openai and anthropic/claude4 + morphllm combo today.",
    "fetchedAt": "2026-09-14T23:39:11.335Z"
  },
  {
    "id": "morph-comm-2",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44490863",
    "excerpt": "Seems completely broken. I used the provided HTML example on morphllm.com playground. Without editing anything, I pressed apply. Your model added a bunch of CSS even though that wasn't in the update instructions, plus a contact section that wasn't requested.",
    "fetchedAt": "2026-09-14T23:39:11.335Z"
  },
  {
    "id": "morph-comm-3",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44490863",
    "excerpt": "Really like this. I've been trying microsoft's copilot and it's so clunky, particularly when applying edits. One would assume they have the resources to train the model.",
    "fetchedAt": "2026-09-14T23:39:11.335Z"
  },
  {
    "id": "morph-comm-4",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44490863",
    "excerpt": "Sounds interesting, but I imagine all the big players (Cursor, Windsurf, and maybe even OpenAI/Anthropic) will achieve something similar very quickly in their tools first-party, which will decimate the company... I don't see developers/companies want to send their code to yet another endpoint.",
    "fetchedAt": "2026-09-14T23:39:11.335Z"
  },
  {
    "id": "morph-comm-5",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44490863",
    "excerpt": "This uses an OpenAI-compatible endpoint, so got this working with my llm.datasette.io CLI tool... One thing that worries me: since it's using XML-style tags <code> and <update>, if my own source code contains those tags I expect it may get confused.",
    "fetchedAt": "2026-09-14T23:39:11.335Z"
  },
  {
    "id": "morph-comm-6",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44490863",
    "excerpt": "Please clarify your privacy policy. If my interpretation is correct, paying users will have their data retained and trained on? ... Free Tier: We may use your submitted code data to train our models... Enterprise Tier: We do not use your submitted code data for any purpose other than processing your immediate request.",
    "fetchedAt": "2026-09-14T23:39:11.335Z"
  },
  {
    "id": "morph-comm-7",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44490863",
    "excerpt": "Does Claude Code have a similar apply model? It does create diffs for you to accept/reject but then I feel like it's always using a find/replace tool to apply it rather than a model that rewrites the whole file... the accuracy feels great.",
    "fetchedAt": "2026-09-14T23:39:11.335Z"
  },
  {
    "id": "morph-comm-8",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44490863",
    "excerpt": "Last time I looked into Morph, I noticed you weren't yet on OpenRouter. I see that's changed, but it looks like only an older model is listed. Any plans to be more active there?",
    "fetchedAt": "2026-09-14T23:39:11.335Z"
  },
  {
    "id": "morph-probe-1",
    "tier": "probe",
    "url": "https://docs.morphllm.com/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://docs.morphllm.com/llms.txt # Morph API Documentation\n> https://docs.morphllm.com\n> Base URL: https://api.morphllm.com/v1\n> OpenAI-compatible. Use a",
    "fetchedAt": "2026-09-14T23:40:29.121Z"
  },
  {
    "id": "morph-probe-2",
    "tier": "probe",
    "url": "https://docs.morphllm.com/introduction.md",
    "excerpt": "PROBE docs-md: HTTP 200 at https://docs.morphllm.com/introduction.md > ## Documentation Index\n> Fetch the complete documentation index at: https://docs.morphllm.com/llms.txt\n> Use this file",
    "fetchedAt": "2026-09-14T23:40:29.121Z"
  },
  {
    "id": "morph-probe-3",
    "tier": "probe",
    "url": "https://docs.morphllm.com/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://docs.morphllm.com/openapi.json, https://docs.morphllm.com/swagger.json, https://docs.morphllm.com/api/openapi.json, https://docs.morphllm.com/.well-known/openapi.json)",
    "fetchedAt": "2026-09-14T23:40:29.121Z"
  },
  {
    "id": "morph-probe-4",
    "tier": "probe",
    "url": "https://docs.morphllm.com/guides/mcp",
    "excerpt": "official MCP server documented at https://docs.morphllm.com/guides/mcp",
    "fetchedAt": "2026-09-14T23:40:29.121Z"
  }
]