{
  "schema_version": "1.1",
  "id": "s9:https://github.com/cactus-compute/needle",
  "slug": "needle-1y2w0se",
  "url": "https://feed7.dev/p/needle-1y2w0se",
  "title": "cactus-compute/needle",
  "why_included": "Needle 3 runs tool calling, typed extraction, and embeddings locally in an 8–29 MB binary, giving agent builders an offline option for constrained devices.",
  "summary": "Needle 3 packages tool calling, schema-constrained extraction, and text embeddings into a **2-bit, 8–29 MB binary**. Its 121M-parameter ladder supports deployable subnetworks from **2 to 20 layers**, with prebuilt engines under 1 MB.",
  "practical_implication": "For device-side agents, test whether its exact tool selection, typed outputs, and confidence score can replace a network round trip. Fine-tune a smaller subnetwork around a narrow tool set, and use the supplied runtime or C API for deployment.",
  "agent_context": "Needle 3 packages tool calling, schema-constrained extraction, and text embeddings into a **2-bit, 8–29 MB binary**. Its 121M-parameter ladder supports deployable subnetworks from **2 to 20 layers**, with prebuilt engines under 1 MB.\n\nFor device-side agents, test whether its exact tool selection, typed outputs, and confidence score can replace a network round trip. Fine-tune a smaller subnetwork around a narrow tool set, and use the supplied runtime or C API for deployment.\n\nThe model deliberately trades away general chat ability, while the published task results use exact-match accuracy and field micro-F1. Local training exports at **4 bits**; the shipped 2-bit quantization uses Cactus infrastructure, and binary telemetry is on by default unless disabled.",
  "source": {
    "name": "GitHub",
    "url": "https://github.com/cactus-compute/needle",
    "published_at": null
  },
  "source_class": "tool",
  "content_type": "GitHub Repo",
  "layer": "model",
  "domains": [
    "coding"
  ],
  "topics": [
    "open-models",
    "tool-use"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "The model deliberately trades away general chat ability, while the published task results use exact-match accuracy and field micro-F1. Local training exports at **4 bits**; the shipped 2-bit quantization uses Cactus infrastructure, and binary telemetry is on by default unless disabled."
  ],
  "connected_context": {
    "meaning": "Needle turns the edge-model argument into a deployable specialist: tool choice, typed extraction, and embeddings can fit in megabytes when general conversation is deliberately excluded. It reinforces fine-tuning tiny models for narrow device functions, while its confidence output overlaps Jev’s typed control-flow role. The remaining decision is operational: validate exact-task accuracy and quantization behavior before replacing a network call.",
    "corpus_size": 823,
    "generated_at": "2026-09-20T09:09:20.227Z",
    "connections": [
      {
        "title": "Why Large? Tiny LMs & Agents on Edge/Robotics — Cormac Brick, Google",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=hacEQHHhu2Q",
        "feed7_url": "https://feed7.dev/p/why-large-tiny-lms-agents-on-edge-robotics-cormac-brick-google-0fjif75",
        "reason": "Needle is a concrete implementation of the candidate’s recommendation to fine-tune tiny models for narrow edge functions where memory, reach, and latency dominate."
      },
      {
        "title": "Jev is the fastest-adopted model in AI Gateway history",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/blog/ai-gateway-jev-model-launch",
        "feed7_url": "https://feed7.dev/p/ai-gateway-jev-model-launch-0rvbmm3",
        "reason": "Both specialize in typed agent decisions rather than general chat, but Needle targets local deployment and also covers extraction and embeddings."
      },
      {
        "title": "jingyaogong/minimind",
        "source_name": "GitHub",
        "source_url": "https://github.com/jingyaogong/minimind",
        "feed7_url": "https://feed7.dev/p/minimind-0j1vfk1",
        "reason": "MiniMind supplies an inspectable small-model training stack, while Needle supplies a much narrower deployment target whose subnetworks can be fine-tuned around a limited tool set."
      },
      {
        "title": "Program-as-Weights: A Programming Paradigm for Fuzzy Functions",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2607.02512v1",
        "feed7_url": "https://feed7.dev/p/2607-02512v1-1dr5458",
        "reason": "Both replace large prompted models with compact task specialists, reinforcing the pattern while using different specialization mechanisms: deployable subnetworks versus adapters for a frozen interpreter."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/needle-1y2w0se",
    "json": "https://feed7.dev/p/needle-1y2w0se.json",
    "markdown": "https://feed7.dev/p/needle-1y2w0se.md"
  }
}