CBF-RL: integrates control barrier functions into reinforcement learning training. Enforces dynamic safety constraints during RL policy training, not just inference.
RobotArena ∞: scalable robot benchmarking via real-to-sim translation. Enables rigorous evaluation of robot policies across diverse tasks and environments.
Verifying LLM inference to detect model weight exfiltration via steganography. Defends inference servers against model theft and anomalous behavior.
AnatomiX: anatomy-aware multimodal LLM for chest X-ray interpretation. Improves spatial reasoning and anatomical understanding in medical imaging.
FARM framework for malware family classification under concept drift. Uses triplet autoencoder for few-shot adaptation to covariate and label drift.
LatentChem: latent reasoning interface for chemical LLMs. Decouples chemical computation from discrete tokens to improve efficiency and performance in chemical reasoning.
Pyramid MoA: probabilistic framework for cost-optimized LLM inference via cascading and routing. Balances inference cost and reasoning capability for large language models.
IROSA: framework combining foundation models with imitation learning for robot skill adaptation via natural language. LLM application to robotics.
Disentangled Safety Hypothesis: mechanistic study of LLM safety showing decoupling between harmfulness detection and refusal. ML interpretability research.
Benchmark evaluating frontier AI models on multi-step cyber attack scenarios. Agent capability measurement across extended action sequences.
Agentic framework for multimodal query processing with adaptive tool orchestration across text/image/audio/video. Research on agent coordination and tool selection.
Proof-Carrying Materials: falsifiable safety certificates for machine-learned interatomic potentials. ML research on reliability guarantees for scientific models.
Codex Security: AI agent for code security that analyzes repository architecture and trust boundaries before validating findings with humans.
Open-source AgentFactory orchestrates fleet of coding agents (Claude, Codex, Spring AI) through automated pipeline for issue resolution and code shipping.
Open-source framework for personal AI agents running entirely on-device with efficiency-aware evaluations and learning loop using local trace data.
NPM package enabling free OpenAI API access via ChatGPT OAuth tokens. Creates localhost proxy to ChatGPT backend API with Vercel AI SDK provider support.
AI automation tool to summarize Datadog monitoring alerts and escalate issues, reducing manual dashboard review.
Discussion of mental fatigue and workflow challenges when working with LLMs like Claude and Codex, and recovery strategies.
Multi-agent workflow orchestration system supporting Gemini, Qwen, Claude with role-based agents, background execution, and visual workflow editing.
GitHub Action detecting LLM output drift in CI/CD by replaying workflows and diffing outputs to prevent silent model changes reaching production.
Dashboard for real-time observability into Claude Code sessions, tracking costs, tool usage, and subagent execution without code changes.
Security middleware for autonomous AI agents that risk-scores actions, detects injection attacks, and catches behavioral drift across multi-turn interactions.
Open-source SDK for building autonomous AI agents that execute cross-chain financial operations with cryptographic guarantees and trusted execution environments.
Multi-agent coordination system using Claude Code, Discord webhooks, and timer-based polling. Production autonomous workflows with real-time notifications.
Timezone converter tool for Claude API usage promotion (Mar 2026). Minor LLM-adjacent utility.
Overview of layered security architecture for AI agents, emphasizing secure human identity verification and token-based authorization.
Quell is a local security layer that intercepts prompts to AI IDEs, redacting secrets before they reach cloud models, storing values in OS keychain.
ARISE framework enables LLM agents to synthesize their own tools at runtime when they encounter task gaps, adapting without pre-crafted tool libraries.
clifast tool converts TypeScript/JavaScript functions into CLI packages with optimized help text for LLM navigation, reducing token usage versus MCP.
LiveAuth system providing Proof-of-Work and Lightning Network authentication for AI agents, replacing CAPTCHAs and API keys.
Critical perspective on AI agent hype, questioning whether agents are necessary or overused in current implementations.
Opsmeter tool for cost attribution and budget control in LLM applications, breaking down spending by endpoint, tenant, user, and model.
Caliber scans codebases to auto-generate tailored AI agent skills, configs, and recommended MCPs matching project stack and best practices.
Free tool for analyzing and comparing AI product costs across 9 LLM providers before implementation to identify optimal architecture.
Analysis of LLM inconsistency when prompted repeatedly on same question, showing tendency to contradict prior responses.
OpenLegion framework for AI agent fleets with Docker container isolation, vault proxy for credentials, and hard spend limits.
LLM-driven robot survival game built with Pygame Zero using Ollama for local inference and prompt design challenges.
Five-phase AI-assisted SDLC pipeline using Git worktrees and Claude for parallel agent orchestration with architectural governance.
Genetic algorithm framework using LLM as mutation operator to evolve optimal prompts through iterative selection and breeding.
Tool generating AI agent instruction files from contract.yaml configuration.
Study testing 10 chatbots on violent scenario response; Claude was most reliable at refusing participation.
Technical analysis of using OS-level process sandboxing for AI agents executing code and spawning subprocesses safely.
Mobile PWA app for managing Claude Code AI agent asynchronously, with file browser and code review/commit capabilities.
DocuDesign tool uses AI image models and text editing to generate print-ready design files from descriptions.
Dialtone watcher Go agent for macOS/Linux monitoring system processes, network traffic, and resource usage with anonymized comparison.
Case study: AI coding agents introduced vulnerable dependencies (cryptominer via CVE-2025-29927) in Next.js application. Security risk analysis.
Personal account of AI coding agent addiction and exploration of Model Context Protocol (MCP) tools. Member-only Medium story.
Recursive self-improving research system using LLMs to run fixed-budget ML experiments, log outcomes, and automatically rewrite its own research methodology.
Proof-of-Training blockchain where miners train a shared MinGRU neural network instead of computing hashes, producing public ML models as network byproduct.
Claude Code skill enabling No-Limit Texas Hold'em poker game with three AI subagents as opponents and optional coaching modes.