ForProduction

// WildDet3D: Scaling Promptable 3D Detection in the Wild // A framework for scaling promptable 3D object detection in real-world environments, enabling flexible and adaptive detection across diverse scenarios. Key highlights: Promptable 3D detection architecture, scales to wild real-world conditions, supports flexible querying of 3D objects, and improves detection accuracy across varied environments and object categories. By introducing prompt-based interaction for 3D detection, it enables more flexible and context-aware object detection systems that adapt to specific use cases without extensive retraining. 📄 Paper arxiv.org/pdf/2604.08626 💻 Code github.com/allenai/WildDe…

// OpenHarness: Open Agent Harness with Built-in Personal Agent Ohmo // A lightweight, open-source agent infrastructure providing the complete harness layer around LLMs—delivering tool-use, skills, memory, permissions, and multi-agent coordination. Key highlights: 9k stars, 29 contributors, 43+ built-in tools (file, shell, search, web, MCP), on-demand skill loading compatible with anthropics/skills, CLAUDE.md context injection, MEMORY.md persistent memory, multi-level permission governance, subagent spawning and team coordination; includes ohmo personal agent for Feishu/Slack/Telegram/Discord integration. By treating the agent harness as inspectable infrastructure rather than a black box, it enables researchers and builders to understand, extend, and customize how production AI agents actually work—while ohmo provides a ready-to-use personal assistant that runs on existing Claude Code or Codex subscriptions. 🔗 Repo github.com/HKUDS/OpenHarn…

// awesome-design-md: Collection of DESIGN.md Files for Coding Agents // A curated collection of DESIGN.md files from popular open-source projects, designed to help coding agents learn system architecture and design patterns. Key highlights: 46k stars, 257 issues, 4 contributors, aggregates high-quality design documentation, and provides real-world examples of system architecture for AI training. By exposing coding agents to well-documented design patterns from successful projects, it enables better understanding of software architecture and improves AI-assisted code generation and system design capabilities. 🔗 Repo github.com/VoltAgent/awes…

// llm-internals: Understanding Large Language Model Architecture // An educational resource that breaks down the internal architecture and mechanisms of large language models for deeper technical understanding. Key highlights: Visual diagrams of LLM components, explains transformer internals, covers attention mechanisms and data flow, and designed for Outcome School curriculum. By providing clear visualizations and explanations of complex LLM architectures, it enables developers and researchers to understand the fundamental building blocks of modern language models. 🔗 Repo github.com/amitshekhariit…

// Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models // A framework for developing meta-cognitive capabilities in multimodal agents, enabling them to strategically select and use tools based on task requirements. Key highlights: Cultivates meta-cognitive tool selection, improves strategic decision-making in multimodal agents, enables adaptive tool usage based on context, and enhances agent autonomy in complex tasks. By training agents to reflect on their own capabilities and limitations, it enables more intelligent tool selection and reduces reliance on hardcoded workflows or human intervention. 📄 Paper arxiv.org/pdf/2604.08545 💻 Code github.com/Accio-Lab/Metis

// FP4 Explore, BF16 Train: Diffusion Reinforcement Learning Rollout Scaling // A novel approach to diffusion RL that uses FP4 precision for exploration and BF16 for training, addressing computational bottlenecks in rollout scaling. Key highlights: Combines FP4 exploration with BF16 training, reduces computational overhead in diffusion RL rollouts, maintains training stability while accelerating inference, and optimizes the trade-off between precision and performance. By decoupling exploration precision from training precision, it achieves faster rollout generation without sacrificing training quality or model convergence. 📄 Paper arxiv.org/pdf/2604.06916 💻 Project Page nvlabs.github.io/Sana/Sol-RL/

// nezha: Run Multiple AI Coding Agents Across Projects // A framework for running multiple AI coding agents across different projects simultaneously, supporting both Claude Code and Codex. Key highlights: 86 stars, 1 contributor, orchestrates multiple coding agents in parallel, supports Claude Code and Codex, and enables distributed development workflows across multiple codebases. By coordinating multiple AI agents across different projects, it enables parallel development and code review without manual context switching or agent reconfiguration. 🔗 Repo github.com/hanshuaikang/n…

// MiniMax-M2.7: Next-Generation Multimodal Language Model // An advanced multimodal language model from MiniMaxAI featuring improved reasoning capabilities, enhanced visual understanding, and optimized performance for diverse applications. Key highlights: Enhanced multimodal processing, improved reasoning and instruction following, optimized for both chat and complex task completion, and designed for efficient deployment across various use cases. By combining advanced architecture with comprehensive training on diverse multimodal data, it delivers stronger performance on reasoning, coding, and visual tasks while maintaining efficient inference for production workloads. 🤗 Model huggingface.co/MiniMaxAI/Mini…

// MolmoWeb: Open Visual Web Agent and Open Data for the Open Web // An open visual web agent framework and dataset for training web automation models on open web data rather than proprietary sources. Key highlights: Open visual web agent architecture, provides open training data for web automation, focuses on publicly accessible web content, and enables reproducible web agent research without proprietary datasets. By providing open datasets and agent architectures for web automation, it democratizes web agent development and enables researchers to build models that interact with the open web without relying on closed, proprietary data sources. 📄 Paper arxiv.org/pdf/2604.08516 💻 Project Page allenai.org/blog/molmoweb

// auto-deep-researcher-24x7: Autonomous Research Agent // An autonomous AI agent that runs deep research tasks 24/7 while you sleep, featuring a zero-config setup and Leader-Worker architecture. Key highlights: Runs continuously without supervision, Leader-Worker architecture for distributed research tasks, 162 stars, 4 issues, and designed to automate literature review and data collection. By delegating research tasks to autonomous agents that work around the clock, it enables comprehensive literature reviews and data gathering without manual effort or time zone constraints. 🔗 Repo github.com/Xiangyue-Zhang…

@NousResearch @Xiaomi Nothing is free, our data is the price of admission. Hope everyone used the free trail responsibly.

We're glad Hermes users have been making use of the free MiMo V2 Pro access via the Nous Portal! You loved it so much that we faced heavier initial usage than anticipated. Thank you to @Xiaomi for helping us improve the stability - update Hermes and it should now be rock solid.

// SkillClaw: Let Skills Evolve Collectively with Agentic Evolver // A framework that enables skills to evolve collectively through an autonomous agentic evolver, addressing the static nature of skills in existing LLM agent systems. Key highlights: Continuous skill aggregation from multi-user interactions, autonomous skill evolution through agent feedback, prevents skill stagnation after deployment, and enables cross-user skill improvement propagation. By treating skill evolution as a first-class concern and implementing an autonomous evolver that refines skills based on real-world usage patterns, it enables LLM agents to continuously improve and adapt rather than remaining fixed after initial deployment. 📄 Paper arxiv.org/pdf/2604.08377

// claude-obsidian: Persistent Knowledge Companion for Claude + Obsidian // A Claude Code plugin that builds and maintains a persistent, compounding wiki vault in Obsidian. Every source you add gets integrated, every question pulls from everything that has been read. Key highlights: Based on Karpathy's LLM Wiki pattern, supports `/wiki` `/save` `/autoresearch` `/canvas` commands, auto-updates hot cache between sessions, and includes pre-configured Dataview dashboards + CSS snippets. By extracting entities, updating cross-references, and maintaining a structured index, it enables knowledge to compound like interest — answers cite specific wiki pages, not training data, and the vault stays healthy without manual cleanup. 🔗 Repo github.com/AgriciDaniel/c…

@kimmonismus Didn't Iran already declined a few days ago?

edit: still waiting on irans reply

Ceasefire with Iran via cnn

// Memory Intelligence Agent: Enhanced Agent Memory Systems // A research framework for improving agent memory systems through structured memory augmentation and retrieval mechanisms for long-term context retention. Key highlights: Proposes novel memory augmentation techniques, enhances long-term context retention, improves agent decision-making through better memory access, and addresses limitations of standard context windows. By implementing structured memory systems that go beyond simple context windows, it enables agents to maintain coherent long-term reasoning and recall relevant information across extended interactions. 📄 Paper arxiv.org/pdf/2604.04503 💻 Code github.com/ECNU-SII/MIA

// knowledge-engine: Bridge Between Human and Machine Memory // A knowledge engine that bridges human-readable wiki patterns with machine-speed memory retrieval, built on Karp Wiki pattern and Memvid architecture. Key highlights: 26 stars, 2 contributors, combines human-readable documentation with fast machine access, and implements wiki-style knowledge organization with optimized retrieval. By translating between human-readable wiki formats and machine-optimized memory structures, it enables rapid knowledge access while maintaining human-friendly documentation standards. 🔗 Repo github.com/tashisleepy/kn…

// Self-Execution Simulation Improves Coding Models // A training approach that improves coding models by simulating code execution during training, enabling models to better understand program behavior and correctness. Key highlights: Simulates program execution during training, improves competitive programming performance, combines execution feedback with natural language explanations, and addresses the gap between code generation and actual program behavior. By incorporating execution simulation into the training process, it enables models to learn from the actual outcomes of generated code rather than just surface-level patterns, leading to more reliable and correct code generation. 📄 Paper arxiv.org/pdf/2604.03253

// claw-code: Claude Code Snapshot for Research // A snapshot of Claude Code preserved for research purposes, providing access to the original source code for academic study and analysis. Key highlights: 123 stars, 247 forks, research-focused snapshot, preserves original Claude Code implementation, and enables comparative analysis of AI coding assistants. By maintaining an archived version of Claude Code, it enables researchers to study the evolution of AI coding tools and conduct reproducible experiments on code generation models. 🔗 Repo github.com/emmarktech/cla…