{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidstm5bdtvdjjdemqcykij73rl27bnopusmmdbe3liojiv6yjf4lm",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mkiu7n2sxr62"
  },
  "path": "/t/jneopallium-biologically-grounded-java-framework-for-natural-neuron-networks-safety-first-autonomous-ai/175605#post_1",
  "publishedAt": "2026-04-27T18:02:30.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "https://github.com/rakovpublic/jneopallium"
  ],
  "textContent": "Hi everyone,I’m Dmytro Rakovskyi, independent researcher. For the last few months I’ve been developing Jneopallium — an open-source Java framework for modeling biologically realistic neuron networks at customizable levels of detail.Core features:\n\n  * Typed signals with explicit fast/slow loop frequencies (bioelectric + neuromodulatory timescales)\n\n  * Multi-receptor neurons (each neuron can implement multiple interfaces with dedicated processors)\n\n  * Full autonomous-AI architecture with 28 neuron classes, including:\n\n    * Harm discriminator (consequence-model safety gate with asymmetric caution learning and hard ethical invariants)\n\n    * Loop-prevention subsystem (detects and gently breaks runaway cycles without permanent damage)\n\n    * Embodiment, affect, curiosity, glia, sleep, and working memory modules\n\n  * Optional non-blocking LLM integration with strict verification\n\n  * Designed for real-world deployment (JVM + planned FPGA/gRPC backend)\n\n\n\n\nThe goal is to build safe, interpretable, biologically-plausible autonomous systems for robotics, BCI, industrial control, and clinical decision support.I’m looking for:\n\n  * People interested in using Jneopallium in their projects\n\n  * Collaborators (code, testing, new modules, hardware integration)\n\n  * Feedback from the SNN / neuromorphic / AI-safety / embodied-AI communities\n\n\n\n\nRepo: https://github.com/rakovpublic/jneopallium would love to hear your thoughts or discuss possible collaboration. Even simple feedback on architecture or use-cases is very welcome.Thank you!\nDmytro Rakovskyi",
  "title": "Jneopallium – Biologically-grounded Java framework for natural neuron networks (safety-first autonomous AI)"
}