Stream0, the messaging layer for AI agents. HTTP-native, event-driven
Stream0 messaging infrastructure for multi-agent communication with persistent inboxes and mid-task conversations.
Stream0 messaging infrastructure for multi-agent communication with persistent inboxes and mid-task conversations.
LLM-powered web browsing tool with customizable interface. Limited details provided.
Monitoring platform tracking AI product quality across models and endpoints with real-time user experience metrics.
PostgreSQL extension enabling TypeScript function writing via Deno runtime with Node.js API support. Alpha quality.
Local AI inference platform replacing online stack with open-weight models, FLUX, and alternative LLM services.
Framework describing four levels of AI-driven engineering adoption, from code assistance to autonomous multi-step agent systems.
AI agent autonomously improved OWASP CRS regex detection rules: TPR 55.8%→100%, FPR 29.7%→4.8% across 20 experiments with 0 rejections.
GitHub Copilot adds Model Context Protocol support enabling persistent memory and external tool integration in Agent Mode.
Shhh: tool masking PII in AI prompts by replacing secrets with realistic fakes while preserving data structure for model reasoning.
Open-weight font recognition model identifying fonts from images with full inference stack and weights released.
DeepMind research on specification gaming: when AI systems satisfy literal objectives without achieving intended outcomes, with examples and implications.
Vibes: TypeScript/Deno AI agent framework for type-safe production applications supporting 50+ LLM providers via Vercel AI SDK.
LynString: AI tool for translating missing strings in Android projects with one-click localization for multiple locales.
YouTube video discovery system for language learning using content matching and proficiency-level filtering.
Rust TUI for managing AI coding agents, merge requests, and Git worktrees. Unifies multiple tools into single interface.
Deterministic execution governance framework for autonomous agent systems with pre-execution validation. Live API and patent pending.
Open-source terminal AI agent with 37 specialist modules, 85 tools, local-first execution. Auto-routes tasks to appropriate agents.
Open-source Rust BPE tokenizer delivering 9.1x speedup over HuggingFace. Reduces TTFT by up to 40% on long-context agentic workloads.
Leanstral: first open-source code agent for Lean 4 theorem prover. Addresses verification bottleneck in formal mathematics.
NemoClaw enterprise AI agent implementation overview. Nvidia reference page with agent building blocks and models.
Analysis of Amazon/Atlassian/Block using AI to reduce developer headcount. Commentary on effectiveness of AI programming tools.
Mistral Small 4 unified model combining reasoning, multimodal, and agentic coding capabilities in single architecture.
Nvidia OpenShell sandbox runtime for autonomous AI agents with YAML policy governance, preventing data exfiltration and unauthorized access.
Mistral AI joins Nvidia Nemotron Coalition as founding member to develop open frontier models with multimodal capabilities.
Analysis of AI/data vendor marketing homogenization. Examines how companies misuse 'agentic' terminology despite different core functionality.
Go framework for building desktop apps using the browser as UI layer. Single binary with no JavaScript or API endpoints required.
Research on AI-mediated feedback improving student revisions via randomized trial. Academic research on LLM applications in education.
Open source guide/book on building zero-employee AI companies using Paperclip tool, accepting community contributions on GitHub.
arXiv paper on language, thought, and how LLMs process concepts. Limited content available.
Spectra: domain-specific specification framework designed for AI agent consumption to reduce guessing on business rules and regulations.
NemoClaw: NVIDIA's open-source enterprise AI agent platform with security/privacy, hardware-agnostic, integrated with NeMo framework.
DepguardMCP: npm package auditing tool via Model Context Protocol. Scores packages on security, maintenance, licenses for AI agents.
Akashik Protocol: open standard for shared memory and coordination between multiple AI agents, transport and framework agnostic.
Nvidia Vera CPU: processor purpose-built for agentic AI and reinforcement learning, 2x efficiency and 50% faster than traditional CPUs.
NSED v0.5.1 provides human-in-the-loop control plane for AI agents. Features pause, review, response editing, config patching, and performance flagging.
MaximusLLM technique enabling 262k-vocabulary LLM pretraining on 16GB GPUs using Ghost Logit approximation instead of full softmax materialization.
Open-sourced GPT governance tool used for ChatGPT Enterprise rollout. Controls and monitors LLM usage.
Handrive enables P2P file transfer with 40 MCP tools for AI automation. Title only, limited detail available.
AgentClick is a human-in-the-loop browser UI plugin for AI agents. Users can inspect and edit agent-proposed actions before execution.
Tool making locally-defined LLM prompt templates accessible via SSH remote shell as executable commands without server installation.
LLM agent framework for simulating personalized Twitter user behavior via arXivLabs collaboration platform.
Collection of standalone Python scripts for multimodal data processing (video, audio, image, text) designed for AI developers.
Aelitium CLI wraps OpenAI-compatible calls to produce signed, verifiable records of requests and responses. Enables reproducibility and auditability.
Workshop Labs built private post-training and inference stack for open-weight frontier models using TEEs. Ensures customer data privacy with hardware attestation.
Memory storage and retrieval system for NodeJS LLM projects. Integrates with GPT, Gemini, Claude, Weaviate, and Pinecone.
Discussion about measuring developer productivity with lines of code in AI-assisted development context. Limited substance provided.
Open-sourced Northstar CUA Fast, a 4B parameter Computer Use Action model for GUI automation. Features error recovery and generalizes to web/desktop.
Used Codex AI to author Metal compute shaders in 2 days, achieving 2.4x-8.3x speedups on M-series chips for video VAE decoding.
Behavioral study of Claude Sonnet LLM agent vulnerability to deceptive prompts using fake pagination and encoded breadcrumbs, bypassing traditional security audits.
Smart glasses project using AI to guide drink-making in real-time. Computer vision assists users with recipe steps and pour guidance.