Live-Memory is Claude Code MCP plugin providing persistent codebase memory using large-context models to distill repo structure, enabling agents to avoid re-reading code.
Agent skills plugin for creating interactive HTML explainers of topics and codebases using coding agents. Open-source skill for Claude Code.
MochiAnalytics is a cheaper analytics tool for tracking campaigns and revenue channels. Not AI/ML focused.
Survey of prompt-injection defense mechanisms for LLM agents. Research on securing autonomous agent systems against adversarial inputs.
Research on self-sovereign agents (SSAs): AI systems capable of autonomous economic sustainability and self-replication through improved decision-making and revenue generation.
Research article on negative effects of unguarded generative AI on high school math learning. Educational impact study with paywalled content.
Claude Code deletes conversations after 30 days by default. Technical note on data retention settings and potential workaround in settings.json.
Hacker News discussion on prompts to demonstrate AI failures and hallucinations. Community crowdsourced examples.
Kiwi enables running autonomous developer agent workflows in cloud while keeping secrets local via reverse tunnel. Enterprise-ready secure execution engine for agentic loops.
arXivLabs framework information. Content does not discuss agentic AI despite title.
GIS utility package for raster and vector geospatial data processing built on GDAL. Not AI/ML focused.
Compressor V2 reduces LLM agent inference costs by 50% through three compression layers, addressing economic pressures in long-running coding agents that consume millions of tokens per task.
Local-first DJ library manager built with Rust + Tauri for exporting to USB drives. Not AI/ML related.
MCP-test-harness 2.0.0: CI/CD testing tool for Model Context Protocol servers with 690+ tests and 100% code coverage, available on PyPI and GitHub Container Registry.
LoomaDesign is an AI-powered product photography service for Amazon sellers using image generation to create marketing assets.
Excalibur is an open-source AI coding agent for product engineers covering full product lifecycle (discover, build, verify, ship) with immutable event logs and replay capabilities.
Interdict is a safety layer for AI agents accessing Postgres, preventing destructive SQL statements through permission-aware validation and rollback capabilities.
Analysis of Anthropic's compute spending ($2.3x payroll) versus industry averages, examining how AI lab economics differ from traditional software companies.
Experimental blockchain using GPT-2 inference as proof-of-work, with miners running pinned transformers and compressing attention distributions using glyph compression algorithm.
EdgeBench is a benchmark of 134 real-world tasks evaluating autonomous AI agents' learning capabilities with 12+ hours iteration per task, tracking improvement trajectories.
Chinese LLM services Doubao and Qwen shutting down personalized AI agents following new government regulations.
Demonstration of AI shopping agent system that autonomously selects and recommends products based on data.
Agency tool using AI to generate e-commerce video ads by automating storyboard and animation workflows.
ByteDance claims discovery of new AI scaling law that could extend AI capability improvements beyond current models.
ByteDance and Alibaba disabling humanlike AI custom agents due to new Chinese regulatory rules.
Self-hosted LLM gateway with OpenAI-compatible API, RBAC, server-side tool execution, built-in chat UI. Single binary deployment.
GPU-accelerated UI framework for building high-performance user interfaces.
Tool for generating and exploring quasiperiodic tiling patterns.
Windows video player with real-time frame interpolation using ML.
DonnyClaude: workflow engine for executing verified Claude Code workflows with guarantees.
Open Science: MIT-licensed open-source alternative to Claude Science for AI research. Local-first, model-agnostic workbench.
Open-source fork of Chrome Dino game enabling AI prompts to modify gameplay mechanics and features dynamically.
Study claiming AI-generated text lacks narrative complexity and mystery compared to human writing.
Meta technical report on large-scale AI storage infrastructure requirements for training. Storage as critical to model performance as compute.
SkillOpt: method for AI agents to autonomously evolve and optimize their own capabilities.
HTTP API design best practices guide.
Video about building a custom GPU at home.
Evolution of AI agent architectures from context engineering approaches to persistent long-running systems.
ChorusGraph: independent agent graph runtime with built-in caching for orchestrating AI agents.
Definition and framework for AI-native development distinguishing it from AI-assisted development tools.
arXiv research paper on underspecification in LLM code generation and coherence implications. Technical machine learning research.
Marketing for AI tutoring platform with personalized lessons and quiz generation.
Video title without substantive content on AI and creativity.
Minimal stub for multimodal AI assistant product.
Whyline is a company memory engine combining SQLite, BM25 search, and MCP protocol for integration with Cursor code editor.
Technical guide on designing GPU-accelerated query engines using NVIDIA GQE for database performance optimization.
Analysis of corporate AI spending exceeding costs of replaced workers with limited productivity gains.
LLM API service offering flat-rate pricing ($6/month) with unlimited token usage, positioning smaller models for bulk/repetitive work.
UNICEF report shows children adopt AI 3x faster than adults, raising governance and safety concerns.
Video stub about Midjourney applications in medical research.