Megadose AI progress, ranked and analyzed.

Uncut

The interesting claim is not another chat interface, but a local workflow for using an LLM as a decision engine without emitting normal tokens. That points at…

Rizzo-AI-Academy/rizzo-flow

#2 · repo · Rizzo-AI-Academy ·

A local Python project for turning LLM outputs into typed decisions instead of free-form generated text.

The interesting claim is not another chat interface, but a local workflow for using an LLM as a decision engine without emitting normal tokens. That points at a more constrained agent architecture, where outputs can be typed, routed, and audited instead of parsed from prose. The metadata is thin, but the framing is coherent and the early GitHub velocity is strong.

GitHub velocity 216.39 stars/day

uncovered in mainstream sources

Source: https://github.com/Rizzo-AI-Academy/rizzo-flow

Recent Uncut picks

  1. bgts-ai-org/bgts-context-engine
    #26 · repo · A deterministic code-context engine that builds code graphs with PostgreSQL, Apache AGE, pgvector, MCP, and REST.
  2. Abiray/Qwen-Image-2.1-viggle-4-steps-turbo-GGUF
    #27 · model · A GGUF-packaged 4-step turbo Qwen Image variant aimed at text-to-image and image-to-image ComfyUI workflows.
  3. nameforjt-afk/session-knowledge
    #21 · repo · Local-first tool that turns Claude Code session history into a searchable knowledge base exposed through MCP tools.
  4. zero11924065-dev/VetarAI
    #22 · repo · Local desktop agent workspace with isolated projects, main/sub-agent orchestration, visual workflows, and built-in RAG.
  5. oc8-ai/oc8
    #23 · repo · Open-source platform for governed AI agents that operate across ERP, CRM, Microsoft 365, and business systems.
  6. Evaluating the Effectiveness of SechKAN on 1D Data
    #24 · paper · Evaluates a hyperbolic-secant KAN variant on 1D classification tasks with parameter counts comparable to MLPs.
  7. PreGS: A Parameter-Transfer-Based Multi-Expert Graph Neural Network for Node Classification
    #25 · paper · Proposes a parameter-transfer multi-expert GNN for node classification across diverse graph structures.
  8. Yinsongxu/LLM2Jev
    #16 · repo · Adapts local language models into structured decision engines using Choice, Score, and Noul outputs.
  9. Targeted Review for AI-Assisted Biodiversity Surveys: Active Continuous-Score Occupancy Modeling
    #17 · paper · Proposes active review methods for correcting ML-generated biodiversity labels before they bias occupancy models.
  10. BELXTR: Biomedical Entity Linking via Contextualized Token Retrieval
    #18 · paper · Introduces a late-interaction embedding model for biomedical entity linking instead of single-vector compression.
  11. unreallabsai/unreal-agent
    #19 · repo · A Go harness for building agents around asynchronous execution rather than request-response loops.
  12. CopilotKit/openmuse
    #20 · repo · A personal agent stack that can use a browser, terminal, and files while continuing work across tasks.
  13. Latest Exact Match Attention
    #11 · paper · Introduces an attention variant where binarized queries attend only to the latest exactly matching key, with word-RAM simulation results.
  14. TriWorldBench: A Tri-View Consistency Perspective on Embodied World Models
    #12 · benchmark · A benchmark for testing whether embodied world models produce consistent predictions across head and wrist camera views.
  15. nokia-applied-research/AnyJev
    #13 · repo · A Python toolkit for making existing LLMs emit typed decisions with calibrated probability-style outputs without retraining.
  16. A Behavioral Trait Leaks into Preferences: Diagnosing Trait Interference in LLM User Simulators
    #14 · paper · Diagnoses how activity traits in LLM user simulators can leak into preference behavior and distort recommender evaluation.
  17. EMGBlend: Heterogeneity-Aware Self-Supervised Pretraining for Gesture and Force Decoding
    #15 · paper · A self-supervised EMG pretraining method designed to handle mismatched channels, electrode layouts, and spectral support.
  18. A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem
    #6 · paper · Shows how attacker-controlled MCP tool metadata and outputs can hijack agents through semantic tool selection.
  19. PERSONAWEAVER: Controllable Diversity Beyond Conventional Archetypes in Procedural Character Generation
    #7 · paper · Introduces a method for generating more behaviorally diverse LLM-created personas for games and simulations.
  20. EquivSVA: A Formally Verified Dataset of Behavioral Assertions Across Equivalent RTL Implementations
    #8 · benchmark · A formally verified dataset for testing whether generated SystemVerilog assertions capture behavior across equivalent RTL designs.
  21. IndustrialVLA-Bench: A Traceable Multi-Axis Evaluation of Open Robot Policy Models
    #9 · benchmark · Benchmarks open robot policy models across capability, robustness, language sensitivity, and deployment-oriented axes.
  22. SambaGraph: Action-Reaction Spatio-Temporal Graphs for Soccer Tactical Response Modeling
    #10 · benchmark · A soccer tactics dataset and benchmark built from World Cup tracking data as player-ball graph sequences.
  23. VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Models
    #1 · benchmark · Benchmarks post-training quantization choices for vision-language-action models across 409 runs and 94,574 episodes.
  24. Continuous Optimization for p-adic Models
    #2 · paper · Proposes native continuous gradient descent for machine learning models with p-adic parameters.
  25. Efficient Iterative Retrieval with Heterogeneous Batching
    #3 · paper · Introduces Orthrus, a serving system that batches embedding and generative retrieval workloads together.
  26. SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentation
    #4 · paper · Combines 2D and 3D priors for geometry-aware multi-view instance segmentation under viewpoint and occlusion changes.
  27. DefaultGNN: A Dual-Perspective GNN Framework for Predicting Corporate Default from Buyer-Seller Transaction Networks
    #5 · paper · Uses buyer-seller transaction networks and a dual-perspective GNN to predict corporate default risk.
  28. AbdelStark/awesome-typesafe-jev
    #21 · repo · A curated, source-backed field guide collecting SDKs, demos, agent tools, and evaluations around TypeSafe's System One model.
  29. SKstars at SHROOM: Visions Agreement-Guided Ensembling of Zero-Shot and LoRA-Adapted Vision--Language Models
    #22 · paper · A SHROOM-Visions system combining zero-shot Qwen2.5-VL-72B with a LoRA-adapted 7B model for span-level hallucination detection.
  30. Estimating Accurate Hand Pose in Camera Space with Vision Transformer
    #23 · paper · A ViT-based method for estimating global hand pose in camera coordinates from monocular RGB input.