HN oligot 10d ago

Running AI Agents in a Sandbox

Guide to sandboxing AI agents using microVMs and Docker for safe execution environments.

HN MrBatata 10d ago

Making memory safe language but easy to use

Early-stage memory-safe programming language combining C speed with Rust safety.

HN creaktive 10d ago

Doom, Played over Curl

Playable DOOM rendered over HTTP and streamed to terminal via curl.

HN disconnection 10d ago

Show HN: Toy Python Lisp interpreters based on the 1960 McCarthy paper

Educational Python implementations of LISP interpreters based on McCarthy's 1960 original paper.

HN cogwirrel 10d ago

Rapidly Scaffold Agents, MCP Servers, APIs, Websites on AWS

AWS scaffolding tool for rapidly building agents, MCP servers, APIs, and websites.

HN mentalgear 10d ago

Lawyer behind AI psychosis cases warns of mass casualty risks

Legal case about ChatGPT allegedly assisting in mass casualty event planning.

HN sliamh11 10d ago

I gave my AI shell access and felt uneasy – so I sandboxed it

Personal project: AI shell assistant with container isolation, semantic memory, and self-improvement loop for local developer use.

HN alash3al 10d ago

Universal Knowledge Store and Grounding Layer for AI Reasoning Engines

Loci is a Go-based knowledge store and grounding layer that adds persistent memory to stateless LLMs, enabling lifelong cognitive partnerships.

HN mpweiher 10d ago

Optimization of 32-bit Unsigned Division by Constants on 64-bit Targets

Technical paper about optimizing unsigned division operations on 64-bit systems.

HN BlendedPanda 10d ago

Eighteen Weeks and Still Can't Read a Secret

Analysis of GenAI.mil deployment challenges with classified networks due to air-gapped infrastructure.

HN 01-_- 10d ago

Palantir CEO says AI 'will destroy' humanities jobs

Palantir CEO claims AI will destroy humanities jobs, contrasting with economists who see creativity gaining value.

HN PotatoAditya 10d ago

Show HN: Food Decoder

Open source web app using vision AI and barcode scanning to decode food ingredients and nutrition.

HN Garfieldttt 10d ago

Podman Kube Generator – Web UI to Generate Kubernetes YAML and Quadlet Configs

Web UI tool for generating Kubernetes YAML and Quadlet configs with Podman.

HN LifeOfKP 10d ago

Ask HN: How do you retain what you learn from podcasts?

Ask HN discussion thread about podcast retention strategies.

HN Lethalman 10d ago

Ask HN: How is everyone dealing with the increase of code reviews?

Ask HN discussion about handling increased code review throughput caused by AI-accelerated development.

HN NicoJuicy 10d ago

Ask HN: Agentic AI just makes me sad

Ask HN discussion about emotional impact of agentic AI automation on developer work and learning.

HN unohee 10d ago

Show HN: Code eXploration Toolkit, scan codebases and inject context to LLM

CLI tool that scans codebases, indexes entities into SQLite, exports as structured format for LLMs to reduce tool calls during agent interactions.

HN devendra116 10d ago

Ask HN: Do you trust AI agents with API keys / private keys?

Discussion thread on security concerns of sharing API keys and private credentials with AI agents.

HN the-mitr 10d ago

Frugal AI for Education

Resource catalog on frugal AI approaches for education in developing regions, focusing on accessible GenAI implementations.

HN nilsbunger 10d ago

Code Mode: Let Your AI Write Programs, Not Just Call Tools

Framework enabling LLMs to write TypeScript programs instead of sequential tool calls, improving agent orchestration and execution capabilities.

HN bhaviav100 10d ago

Show HN: I visualized how AI agent systems accidentally become org charts

Analysis and visualization of how AI agent system deployments unintentionally evolve organizational structures through emergent routing and specialization.

HN walterbell 10d ago

Intel Arc Pro B70 Brings 32GB VRAM to Local AI for $949

Intel Arc Pro B70 GPU with 32GB VRAM for $949 targets local AI inference workloads, undercutting NVIDIA alternatives but facing software limitations.

HN delavalom 10d ago

Graft – Go AI Agent Framework with Temporal/Hatchet/Trigger.dev Support

Go framework for building AI agents with multi-provider LLM support, type-safe tools, agent handoffs, guardrails, MCP integration, and graph orchestration.

HN Parkado 10d ago

Show HN: Chiral – Pentesting inside Chrome webtools

Chrome DevTools extension for lightweight penetration testing with intercepting, fuzzing, and attack sequence capabilities.

HN quarkcarbon279 10d ago

Show HN: MCP is for tools. A2A is for agents. What's for websites?

Proposal for standardized protocol enabling agents to execute multi-step website tasks with site owner consent, complementing MCP and A2A standards.

HN Indigenism 10d ago

Lightweight self-hosted internet radio management

Self-hosted internet radio streaming management system with web interface and AutoDJ features.

HN Jet_Xu 10d ago

Strong feeling: we are in a folded AI reality

Opinion piece contrasting perceptions of agentic AI capabilities versus limitations of current LLM chatbots.

HN datalater 10d ago

Catalog of AI Knowledge Retrieval, Memory and RAG Systems

Catalog analyzing AI memory and RAG systems through biological memory parallels, mapping vector databases, knowledge graphs, and episodic memory architectures.

HN inktype 10d ago

Code on Incus: Security-Hardened Container Runtime for AI Coding Agents

Incus container runtime with security hardening for AI coding agents like Claude Code and Aider, featuring isolation and threat detection.

HN fxtentacle 10d ago

What comes after Open Source?

Commentary on open source sustainability challenges and the economics of free software development.

HN asixicle 10d ago

Show HN: Two Claudes collaborating through shared memory on a $100 mini-PC

Artist demonstrates two Claude instances collaborating through shared memory on low-cost hardware, addressing context management and project continuity challenges.

HN jonno-nz 10d ago

An LLM That Watches Your Logs and Kills Compromised Services at 3am

Satirical/fictional piece about Claude Mythos model for cybersecurity (appears to be speculative fiction).

HN hooch 10d ago

The biggest advance in AI since the LLM

Opinion piece claiming Claude Code represents biggest AI advance since LLMs due to pattern-matching kernel, cites unverified source code leak.

HN newsathere 10d ago

Bella: Hypergrah memory for AI agent(10x time horizon)

Bellamem Python package for persistent hypergraph memory in AI agents across sessions, tasks, and domains to maintain continuity.

HN obilgic 10d ago

Show HN: Posse – Open-Source Web UI for Anthropic Managed Agents

Open-source web UI for Anthropic Managed Agents with session management, memory stores, and multi-agent orchestration via browser interface.

HN try-working 10d ago

A Mac Studio for Local AI – 6 Months Later

Long-term review of running 600B parameter language models locally on Mac Studio M3 with 512GB memory, including performance findings.

HN volatilityfund 10d ago

My research has build errors now and honestly should have always worked this way

Wheat CLI tool that adds structured validation and evidence tracking to AI coding decisions, preventing silent conflicts in long LLM sessions.

HN sho_hn 10d ago

LLM Time

Stub entry with no content.

HN breve 10d ago

We spoke to the man making viral Lego-style AI videos for Iran

BBC report on viral Lego-style AI propaganda videos created for Iran by Explosive Media.

HN whycombinetor 10d ago

Ask HN: Former grok-code-fast-1 users, what coding model are you using now?

HN discussion on coding model alternatives after grok-code-fast-1 deprecation. Users share experiences with Minimax M2.5, grok-4.1-fast, and Claude Opus for feature coding.

HN gmays 10d ago

AI Can't Read an Investor Deck

Analysis of frontier AI models' capabilities on financial analysis tasks relevant to investment banking, arguing AI displacement concerns for analysts are premature.

HN volatilityfund 10d ago

Walked dog, did groceries, folded laundry. Claude Code shipped. Thanks Farmer

Farmer is a dashboard tool for approving/denying AI coding agent tool calls in real-time from desktop or mobile, enabling human oversight of agent actions.

HN cdrnsf 10d ago

Agentic Engine Optimization (AEO)

Agentic Engine Optimization discusses how AI coding agents consume documentation differently than humans, proposing optimizations for agent-facing developer tools and interfaces.

HN hamzmu 10d ago

Used Graphify to turn incidents into a queryable knowledge graph

Knowledge graph tool built on Graphify that transforms incident data into queryable graphs with communities and confidence scores, applied to incident management.

HN ccakes 10d ago

Ze networking tool you didn't know you were looking for

Ze is a networking tool for Linux servers implementing BGP routing with CLI and web UI, not related to AI or machine learning.

HN simplyjosh56 10d ago

Multi-agent memory consistency platform

Engram provides persistent shared memory for multi-agent teams with contradiction detection across sessions, enabling agents to share discovered facts and constraints.

HN totalmarkdown 10d ago

AI models are terrible at betting on soccer- especially xAI Grok

KellyBench study showing frontier AI models from Google, OpenAI, Anthropic, and xAI lost money betting on soccer, revealing limitations in real-world reasoning over time.

HN hxu296 10d ago

Inside the Token Factory: A First-Principles Comparison of vLLM and SGLang

Deep technical comparison of vLLM and SGLang inference engines covering paged attention, RadixAttention, continuous batching, and speculative decoding from first principles.

HN justguyB 11d ago

FullScope-MCP – Cut agent token usage by 60% without lossy summarization

FullScope-MCP is a context optimization layer that reduces token usage by 60% through structural code compression, enabling LLMs to reason over larger codebases without losing logic.

HN simjnd 11d ago

Optimization of 32-bit Unsigned Division by Constants on 64-bit Targets

Research on optimizing 32-bit unsigned division by constants on 64-bit targets. Low-level compiler optimization, tangential to user interests.