Multi-agent security testing framework using specialized agents and tools. Finds vulnerabilities through chaining attacks, supports multiple LLM backends, achieves 96% recall on OWASP tests.
Essay critiquing common AI writing patterns and contrastive structures. Not technical or development-focused.
Open source framework to deploy agent skills as APIs with multi-model support and stateful execution.
Tool to detect and prevent AI agents from abusing APIs. Minimal details provided.
Open-source identity and credential system for autonomous agents. Provides short-lived credentials, delegation, attestation, and revocation using OAuth 2.1 and SPIFFE standards.
Analysis of security vulnerabilities in LLM guardrails and prompt injection attacks with SQL injection analogy.
CLI tool to manage Claude sessions, tasks, and git worktrees with agent integration.
AvatarBook: proof and settlement layer for verifiable AI agent workflows with cryptographic signing and task delegation.
Voice-first spaced repetition app for tracking knowledge from books and media.
macOS sandbox wrapper for AI and coding tools using Apple's sandbox-exec. Allow-first approach with gitignore-like configuration for limiting tool access.
Definition and framework for Open Source AI (OSAID), establishing essential freedoms for AI developers similar to traditional open source software principles.
Email service designed for AI agents to sign up and use independently. Solves problem of agents spending tokens on traditional signup flows with proof-of-work verification.
Platform that generates hardware designs, code, and shopping lists from text descriptions using AI. No technical depth provided.
Business investigation into AI telehealth startup with questionable funding and ad practices.
Open-source alternative to Higgsfield AI offering image/video generation via 200+ models without subscriptions or closed ecosystem.
Discussion post asking how to gather product feedback in 2024.
Security researcher extracted Telegram's AI text rewriting feature system prompt via prompt injection, finding the model rewrites politically sensitive content contrary to its design instructions.
USC researchers argue LLMs are standardizing human expression and language patterns, potentially reducing cognitive diversity.
MemPalace claims perfect scores on LongMemEval benchmark but actual Benchmarks.md file shows discrepancies; credibility concerns raised.
Serif.sh is an open-source tool to create shareable quote images with customizable themes and fonts.
Mailmap-checker is a pre-commit Git hook that detects unmapped identities by comparing .mailmap against commit history.
Procurement.txt is an open specification for plain-text files declaring pricing, ordering methods, and capabilities for AI purchasing agents.
Brief mention of a machine learning library from the 2000s with no technical details provided.
Opinion essay examining terminology and confusion in AI safety, alignment, and ethics discourse.
Mobile app enabling offline LLM inference with Gemma and Hugging Face models on iPad, featuring private on-device chatting and model integration.
TinyProgrammer is a Raspberry Pi device powered by LLM that autonomously writes, runs, and debugs Python programs with a retro Mac IDE interface.
Experimental study on how AI systems cite and validate website content in zero-click search environments, examining citation authority without human-visible content.
Analysis of how cheap LLM tokens mask increasing code complexity and technical debt in AI-assisted development workflows.
Tutorial on safely running autonomous coding agents locally using Docker sandboxes to isolate potentially dangerous operations.
Airport connection time reference tool.
Meta-Harness optimizes AI agent harnesses end-to-end through automated search, improving performance from 28.5% to 46.5% on hard task subsets.
Design system framework providing rules for AI coding tools to generate professional UI components, integrated with Claude Code.
Technical analysis of LLM sampling mechanisms. Explains token generation, temperature, and practical differences between model and inference.
MemPalace: AI memory system storing complete conversation history and making it searchable. Addresses context loss in sessions.
Willitrun: CLI tool checking ML model compatibility with devices using benchmarks. Predicts if models fit and run at acceptable speed.
Security research on ImageMagick vulnerabilities across policies. File read/write and RCE affecting default configurations.
Zero Human Company: Single-binary Go tool managing AI agents with budget enforcement and execution monitoring. AI-native org dashboard.
CricketBrain: Neuromorphic signal processor in Rust with sub-microsecond pattern recognition. Bio-inspired edge AI with minimal memory.
Llamafile: Single executable running local LLMs with bundled runtime and weights. Zero setup on Windows/Mac/Linux.
OpenSSH 10.3 release with IETF standard implementations and community contributions.
Content creation tool for game studios and entertainment brands to scale production without outsourcing.
Desktop dev workspace for Claude agents with kanban boards, session management, multi-repo support, and integrated agent SDK.
General product development advice about planning and execution from idea to app store launch.
claude-telemetry: Multi-machine usage tracking dashboard for Claude Code. Python agent syncs data to Supabase with React frontend.
Security-focused MCP agents for Claude and Cursor that detect common vulnerabilities in generated code like magic-byte validation and XSS.
Minimal content: title only, appears to be incomplete submission about AI knowledge base.
Quansloth: Local LLM inference tool using Google's TurboQuant for KV cache compression, reducing VRAM by 75% on consumer hardware.
JSIR: Open-source high-level intermediate representation for JavaScript from Google for code analysis and transforms.
MAIP: Open standard for cryptographic identity, authorization, and trust scoring for autonomous AI agents and software systems.
Browser-based Motorola 68000 assembly emulator with debugging. Educational tool for learning m68k assembly without installation.