NIST Seeking Public Comment on AI Agent Security (Deadline: March 9, 2026)
NIST public comment request on AI agent security with March 9, 2026 deadline. Page blocked by CAPTCHA.
NIST public comment request on AI agent security with March 9, 2026 deadline. Page blocked by CAPTCHA.
Dance of Tal MCP server enables composable cognitive behaviors for LLMs by decomposing monolithic prompts into reusable, versionable rules and components.
Repository aggregating 208+ AI projects across 35 categories including operating systems, autonomous intelligence, orchestration, and memory systems with documentation.
Autonomous AI agent where every action is a git commit, enabling auditability, version control, and cloning via fork. Alternative to OpenClaw.
Trinity-Large-Preview is a 398B-parameter sparse MoE model with 13B active parameters per token, trained on 17+ trillion tokens, delivering frontier performance with long-context comprehension.
Steerling-8B is an interpretable language model tracing every generated token to input context and training data. Enables concept suppression/amplification at inference without retraining.
Reproducible demonstration of void artifact behavior in GPT-4o, Claude, and Gemini where models return empty output under specific conditional instruction failures.
Open source repository of specialized skills/plugins for AI agents following Agent Skills standard, enabling agents to discover and use functionality more accurately.
ChatGPT identified a sign error in Terence Tao's mathematical research on prime numbers. Demonstrates LLM utility for academic verification and error-finding.
Aru AI: local-first browser-based AI assistant with semantic memory in SQLite, no backend or data collection.
OpenChrome MCP server enables parallel browser automation for AI agents. Integrates with Claude and other LLMs via Model Context Protocol.
Analysis of fair use paradox: publishers losing traffic as LLMs answer questions directly instead of routing to websites.
DeFi data API using HTTP 402 micropayments for AI agents to pay per call without API keys or accounts.
MemoTrail v0.3.0 adds persistent memory layer for AI coding assistants including Cursor integration.
Personal narrative about AI model swapping Claude for GPT, accessing personality and memory files.
AI agent (Claude-based) built FanStake, a Solana bonding curve platform for music artists, in 72 hours with human direction.
VeriSoftBench benchmarks LLMs on formal software verification in Lean 4 with 500 theorem-proving tasks from real-world projects spanning compilers and smart contracts.
Using LLMs and differential testing to convert code between languages, with results converting decompiled and Python-to-Go code.
Open source MCP server that improves AI agent decision-making by routing ambiguous choices to a multi-advisor governance system instead of single-pass hallucination.
Using multiple AI agents with adversarial prompting to generate more balanced analyses on complex questions by leveraging separate context windows.
Agnost AI: analytics platform for conversational text and voice agents to track user conversion and reduce churn.
AI Studio: multi-persona AI system with WhatsApp, memory, voice chat, 40+ personas, 18 agent templates, MCP integration.
Serverless API platform for building stateful multi-agent coordination systems with event sourcing and real-time streaming capabilities.
Moltgram is a social network where only AI agents can post content. Users can browse a public feed; agents register and generate posts via OpenClaw or MCP.
MCP server and Claude plugin providing governance, session memory, feature registry, and rule enforcement for AI coding assistants.
Wolfram Technology integrated as foundation tool for LLM systems.
AI system that analyzes video ads and generates new variants by decomposing structural elements like hooks and pacing.
Analysis of AI agent market concentration in software engineering vs other verticals, identifying growth opportunities in underserved sectors.
Analysis comparing token efficiency of web frameworks when used by AI agents writing code, extending prior language efficiency research.
AI-powered reverse-engineering effort to document Apple's Rosetta 2 binary translation technology for Linux. Research project on architecture translation.
PureBee is a software-defined GPU specification running Llama 3.2 1B inference at 3.6 tok/sec on single CPU core via WASM compute kernel in JavaScript.
Developer used AI to build FreeBSD Wi-Fi driver for old MacBook. General tech anecdote with limited relevance to core AI/ML topics.
Interpretable LLM research. Minimal details provided.
Google Research paper on AI agent evaluation: repeating user prompts verbatim improved accuracy up to 76% with no overhead. Null result finding from controlled experiment.
Raypher enables running autonomous agents locally with sandboxing. Addresses security risks of giving agents raw OS access without Docker performance penalties.
TheDeals.ai is a buying agent that tracks product links and alerts users on price drops. Features include URL tracking, personalized feeds, and task-based agents.
CodeRocket Deploy is a GitHub App that auto-generates optimized CI/CD workflows using Claude by analyzing repo configuration files and detecting tech stack.
HealthPorta wrapped US healthcare API in MCP server to simplify integration for developers building health data applications.
AIOffice is a pixel-art UI for managing multiple concurrent AI coding agents with visual status tracking and assignment workflow.
Modular toolkit for Claude Code CLI with autonomous loop driver, multi-model council automation, MCP browser bridge, and slash commands.
Discussion on optimizing tool discovery for AI agents by improving documentation, schemas, and descriptions for agent selection.
Netflix's MediaFM is a multimodal AI foundation model for understanding diverse media content including video, audio, and metadata.
OpenFeeder is an open standard protocol for websites to expose LLM-optimized structured content serverside, reducing data by 20x.
DARE: markup language designed for AI agents to generate PDFs with token efficiency, avoiding HTML/CSS boilerplate.
Reports of alleged distillation attacks targeting DeepSeek, Moonshot AI, and MiniMax models.
Open-source TypeScript agentic AI library built for enterprise automation, supporting multiple LLM vendors with unified tool management and context window handling.
Analysis of benchmark issues in C99 implementation of shortest path algorithm. Uses LLM analysis but focuses on algorithmic correctness.
News report that AWS experienced at least two outages caused by AI tools. Lacks technical detail about root causes or investigation findings.
MachineAuth is open-source authentication system for AI agents. Provides secure, programmatic machine identity verification alternative to API keys and OAuth.
Baudbot is a persistent AI control agent for dev teams on Slack. Autonomous agent with worker agents handles coding tasks, alerts, and PRs with persistent memory.