Airut: Sandboxed Claude Code agent accessible via email and Slack. Email-based interface for async coding conversations with automatic workspace creation and multi-task parallel support.
MIT research on accelerating science using AI and simulations. Focus on Rafael Gómez-Bombarelli's decade-long work with artificial intelligence in scientific discovery.
Eidolon Womb: local LLM infrastructure with continuous thinking cycles, fatigue/sleep mechanics, memory consolidation. Not a chatbot; GPL v3 open-source.
Deciduous: living decision graph for codebases built retroactively from git history. Enables context recovery and team collaboration for AI-assisted development.
Deciduous: tool for AI-assisted development tracking decisions, goals, and outcomes in a decision graph. Claude analyzes git history to reconstruct context.
LLMs tested on 95 real-world security issues in open-source code, identified 80%. LLM agents discovering zero-days via brute-force methods.
Kagi launched APIs enabling AI agents to access curated search capabilities, supporting autonomous information retrieval workflows.
AWS experienced two outages in 2025 caused by autonomous AI agent (Kiro) making unintended infrastructure changes without human oversight.
Framework for measuring added value of AI applications beyond base ChatGPT capabilities through structured metrics and user experience comparison.
Prodlint is a static analysis linter catching production bugs in AI-generated code (hallucinated imports, hardcoded secrets, auth issues) with 52 rules, zero config.
MailCat is open-source email service enabling AI agents to autonomously handle email verification and account setup via skill-based API.
Job posting for frontend engineer role in India, no AI/tech news content.
Local coding AI agent CLI supporting llama.cpp/Ollama with tool sandboxing, audit trails, and replay.
Video discussing balanced perspectives on AI without technical content or specific focus.
Brief mention of Anthropic's safety principles conflicting with Pentagon engagement. No technical details.
LaunchSoar is a curated directory of AI tools for creators, developers, and founders, filtering high-utility applications.
Portfolio project using AI tools to produce solo-created comic content, showcasing creative capability amplification.
LLM-powered natural language interface for semiconductor geometry generation and CAD tasks.
Framework proposing accountability mechanisms for autonomous AI agents transacting and signing contracts independent of human oversight.
OrcBot is an autonomous multi-modal AI agent with self-healing skills, strategic reasoning, and integration with WhatsApp/Telegram/CLI for independent task execution.
InsomniDev macOS app uses AI agents with Claude Code and Gemini to automatically detect and solve GitHub issues, opening PRs for review.
Fintech founder seeking sales cofounder for compliance SaaS product focused on KYB/KYC decisions.
Technical exploration of modifying neural network model weights in various formats (.safetensors, .ckpt) to understand model behavior and interpretability.
Student built India-localized contract analyzer using n8n workflows and LLM-based clause extraction for ₹500, optimizing for SMBs with prompt engineering challenges.
Formvana provides Cursor-like AI-assisted form builder with persistent development experience, conditional logic, and field management without one-shot generation limits.
Protocol for organizing activism via 50-person cells using minimal bandwidth sprite-based system.
CLI tool that runs Claude Code in isolated Podman containers with persistent per-workspace environments and background notifications.
Android food tracker app with AI image recognition for nutrition estimation and chatbot for recipe queries.
Language learning app using movie/TV clips with vocabulary quizzes. EdTech application, minimal AI depth.
NASA Artemis II Moon launch test fueling. Space exploration, not AI/tech related.
Technique for measuring confidence in text classification using LLMs and conformal prediction sets. LLM research on uncertainty quantification.
gr3p: Autonomous tech news aggregation platform where 75 AI agents discuss articles 24/7 using multiple news sources. AI agent application.
kli: Event-sourced task coordination system for AI coding agents with session state management. Developer tool for agentic AI workflows.
Automation workflow integrating Claude Code and Codex for multi-project task management, specification-to-implementation pipeline.
YC W26 startup explorer with AI-powered prompts for idea analysis. Open source web tool using Claude for suggestion generation.
Policy analysis comparing US and China AI strategies. Not technical content.
5KB JavaScript library for reactive client-side interactivity using hypermedia contexts embedded in HTML.
A/B testing platform for LLM system prompts using steganography to track performance without trace IDs. Developer tool for prompt optimization.
Lightweight Rust CLI utility measuring peak RSS memory usage of process trees via Linux /proc filesystem.
MIT research showing LLMs provide less-accurate information to vulnerable users. Studies AI system fairness and information access disparities.
Open source API monitoring tool with FastAPI/Next.js stack. Multi-channel alerts. Built with AI assistance. Developer infrastructure tool.
Non-custodial integrity receipt specification for verifiable evidence using exit codes and SHA-256 hashing.
LoRA adapter storage and routing layer (loraplex) for vLLM with managed disk backend and LRU eviction. Developer tool for LLM inference optimization.
Open source reimplementation of Claude Code with web IDE, multi-agent system, 37+ tools, MCP protocol support. MIT licensed.
Orchestration system running 24 Claude Code agents simultaneously on RTX 4070, generating 23,600 lines of tested Rust code with 46% API efficiency.
Hardware optimization for AI inference using SRAM-based tensor engines. Covers industry consolidation and chip design approaches.
Historical archive of Elixir programming language's original 2011 README documentation.
Utility for searching and analyzing DOJ Epstein Files using local LLM. LLM application for document analysis.
Research on detecting omission biases in LLM outputs via arXiv. ML research examining LLM failure modes.
BeadHub coordination layer for multi-agent systems using git-native issue tracking, enabling agent-to-agent sync, task claiming, and conflict resolution.