24d ago
Show HN: MemoryOps – governed memory infrastructure for AI assistants
Enterprise memory governance layer for AI assistants with policy evaluation, typed storage, hybrid retrieval, and auditability.
24d ago
Hugging Face, ModelScope, or CSGHub: How Should a Team Choose?
CSGHub: open-source platform for managing LLM assets, datasets, and models with web interface, CLI, and SDK support.
24d ago
Badc – optimizing cross-platform C compiler built with Claude
C compiler built with Claude implementing C99/C11 standards as cross-platform compiler and library.
24d ago
Magpie-search – a federated search engine for LLM's/agents
Federated search engine for AI agents and LLMs providing local indexing and persistent memory across crashes.
24d ago
ILX Launcher – a developer cockpit for Python apps (hot reload, crash capture)
Python developer tool for running, hot-reloading, and debugging desktop apps with integrated local LLM coding assistant.
24d ago
When AI Agents Do the Work, What Do We Lose?
Opinion piece on societal implications of AI agents automating work.
24d ago
Show HN: Crespo – Tree-sitter AST blueprints instead of raw code for LLMs
Tree-sitter AST-based code compression for LLMs reducing context window consumption while preserving architecture understanding.
24d ago
Show HN: I applied Lyapunov stability theory to detect when LLM agents spiral
Lyapunov stability monitoring for multi-turn LLM agents detecting token spirals and failure patterns without extra LLM calls.
24d ago
Show HN: Open-source Notion-style personal site / blog
Next.js-based self-hostable note-taking app with block editor, nested organization, and SEO-friendly publishing.
24d ago
Show HN: HyperSnatch – local-first evidence workstation for Windows
Windows tool for organizing and verifying investigation artifacts. Content is incomplete with error messages and version warnings.
24d ago
WebGPU feature detection was not enough to run small LLMs on phones
Technical analysis of running small LLMs in browser on phones using WebGPU, testing feature detection and buffer limitations.
24d ago
Fugu: Learn to assemble, route, and coordinate expert agents [pdf]
Fugu research paper on assembling, routing, and coordinating expert AI agents for complex multi-step tasks.
24d ago
Ask HN: What will AI coding look like when today's CS freshmen graduate?
Discussion about future of AI coding tools and LLM capabilities for developers over next four years.
24d ago
Sakana Fugu
Sakana Fugu API orchestrates multiple AI models dynamically for complex multi-step tasks without vendor lock-in.
24d ago
Visual Thought Simulator: Tiny demo showing why LLMs have no internal imagery
Demo exploring why LLMs lack internal imagery, proposing alternative systems that generate and store visual scenes using phonetic methods.
24d ago
Microsoft Activation Scripts – Activate Windows / Office / ESUs
Open-source Windows and Office activation tool supporting multiple KMS methods and troubleshooting utilities.
24d ago
Show HN: Woltspace – a lodge for your coding agents
Woltspace is a containerized sandbox platform for interacting with coding agents remotely via Telegram or Slack, supporting Claude Code with persistent memory.
24d ago
GitHub Banned All CI for Our (OSS) Org Because of Bad Drive-By Contributors
Open source organization's CI/CD disabled by GitHub due to crypto-mining activity by drive-by contributors.
24d ago
Americans and AI 2026: Chatbots, Smart Devices and Views on Impact
Pew Research survey on American attitudes toward AI, chatbots, and smart devices adoption and societal impact.
24d ago
2k retired Google Pixel phones get a second life as a private cloud
UC San Diego and Google deploy 2,000 retired Pixel phones as a distributed compute cluster for private cloud infrastructure.
24d ago
QEMU with Espressif
QEMU machine emulator and virtualizer documentation for Espressif platforms.
24d ago
Give your sandboxed agents API keys they can't read
Developer tool that securely provides API credentials to sandboxed AI agents without exposing real values.
24d ago
Promptblock – detect prompt injections in GitHub issues
GitHub App detecting prompt injection attempts in issues and comments targeting AI agents, including hidden HTML payloads.
24d ago
Show HN: Wirewright, an experimental symbolic physics environment
Symbolic physics environment modeling programs as physical mechanisms with time-stepping simulation.
24d ago
Show HN: Phileas – Local-first memory that remembers you
Local-first memory layer enabling LLMs and agents to read/write persistent context across sessions via Model Context Protocol.
24d ago
Codex-maxxing for long-running work
Whitepaper on using Codex as persistent workspace for long-running projects, managing context and complex workflows beyond single prompts.
24d ago
Bean – a portable convergence gate for agent work
Bean is a runtime tool that prevents AI agents from declaring tasks complete until claims are verified, conflicts resolved, and questions documented. Maintains typed claim ledger and runs verification compiler.
24d ago
Show HN: ANMA, boundary contracts for cheaper AI coding agents
ANMA: YAML-based boundary contracts for enforcing architecture rules in cheaper AI coding agents, with benchmarks showing 100% compliance vs 32% without.
24d ago
Show HN: PeekAI – Local-first observability for Python AI agents
PeekAI provides local-first observability and debugging tools for Python AI agents, enabling developers to monitor agent behavior.
24d ago
Show HN: Lupen – an itemized, verified receipt for Claude Code and Codex spend
macOS tool that itemizes and verifies AI coding spend from Claude Code and Codex logs with granular breakdowns.
24d ago
China's Z.ai open-sourced a frontier coding model as Washington bans it rival
Z.ai open-sourced a frontier coding model amid US regulatory restrictions on rival systems.
24d ago
An In-Browser Visualizer for GPS Satellites
Browser-based GPS satellite visualizer displaying real-time positions and orbital paths of navigation system satellites in 3D.
24d ago
Samsung Electronics brings ChatGPT and Codex to employees
Samsung Electronics deploys ChatGPT Enterprise and Codex to employees globally, marking one of OpenAI's largest enterprise deployments.
24d ago
Good results fine tuning a local LLM like Qwen 3:0.6B to categorize questions
Personal project fine-tuning Qwen 3:0.6B for household question categorization using RAG with metadata-aware vector search.
24d ago
Show HN: Real-Life Deception Detection Without Uploading Video
Self-contained deception detection pipeline fusing text, visual, and audio features from courtroom video for truthfulness prediction.
24d ago
Evaluating sugar-sweetened beverage tax effects
Academic paper on sugar-sweetened beverage tax effects on public health, unrelated to AI/tech.
24d ago
I Canceled My French Tutor and Built an LLM Tool That Does It Better
Developer built LLM-based French tutoring tool replacing paid human tutor, focusing on improved retention through interactive conversation and personalization.
24d ago
Compass – guardrails and a hard budget cap for AI coding agents
Compass: local-first config layer for AI coding agents with budget caps, guardrails, and safety features. Prevents unsafe commands and unverified code merges.
24d ago
Real-Time GPS Tracking Station
Real-time GPS satellite tracking dashboard with 3D globe visualization, signal analysis, and orbital telemetry using Docker and Three.js.
24d ago
I Gave an AI a Civilization to Run. It Built a Nuke – Launching CivBench
CivBench: benchmark for evaluating AI agents by tasking them to run civilizations in game environment.
24d ago
AI Is Discovering the Doorman Fallacy [video]
Video discussing doorman fallacy concept in AI systems.
24d ago
Show HN: Tunr – Expose your local server in 3 seconds
Tunr exposes local development servers to public internet in under 3 seconds with automatic HTTPS, alternative to ngrok built in Go.
24d ago
Show HN: EGC - MCP server that gives AI coding tools memory across sessions
EGC: MCP server giving AI coding agents persistent memory across sessions to retain decisions and learnings.
24d ago
Jonathan Blow on why LLMs cannot program [video]
Video: Jonathan Blow discusses fundamental limitations of LLMs in programming tasks.
24d ago
Apertus – Open Foundation Model for Sovereign AI
Apertus: open-weight foundation model (8B/70B) from Swiss AI Initiative. Open data, reproducible training, EU AI Act compliant.
24d ago
Securing the Future of AI Agents
Analysis of security requirements for increasingly capable AI agents in autonomous tasks like cybersecurity and R&D.
24d ago
Stop wasting tokens and re explaining your project between sessions
Recall: Local session logger that condenses Claude Code interactions into project summaries without external API calls or data transmission.
24d ago
QueryLoL – open-source League of Legends companion built with Tauri
QueryLoL: Open-source League of Legends companion app built with Tauri providing real-time play calling and game strategy for all champions.
24d ago
Conduit – Self-hosted Bitcoin Lightning payments for AI agents
Conduit: self-hosted Bitcoin Lightning payment infrastructure for autonomous AI agents with spending guardrails.
24d ago
AuraText – a Windows overlay that brings AI into any text field URL
AuraText: Windows overlay for AI assistance in any text field with contextual prompt generation.