30
30
The VMs Powering Mobile Agents (Instinct, Claude Code)
A teardown reveals Claude Code runs in Firecracker microVMs with a Rust PID 1 and MITM'd egress, while Instinct rents E2B sandboxes with git-based memory.
The author inspects the virtual machines hosting cloud agents: Claude Code runs in a Firecracker microVM with a custom Rust init (process_api) as PID 1, a 324 MB Bun harness on a read-only disk, and 443-only MITM'd SSE egress to api.anthropic.com with host-rotated OAuth tokens and no inbound access. Instinct rents E2B sandbox-as-a-service Firecracker microVMs (Ubuntu 22.04, 2 vCPU, 1.9 GB RAM) where agent memory is a git repo of Markdown committed by the agent and pushed to S3 as a single bundle, using short-lived STS credentials. Both platforms rely on Firecracker, differing mainly in fleet operator and guest boot configuration.
35
30
30
Show HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs
Developer launches Engrim, an open-source local-first SQLite memory engine giving AI CLI agents persistent memory.
Engrim, shared on Hacker News (89 points), is a universal, local-first memory layer built on SQLite for AI CLI tools. It targets agent-style CLI applications that need durable cross-session memory without cloud dependencies. Details beyond the repository description were not provided in the source text.
18
Akamai Valkey Managed Database: Real-Time Memory for Enterprise AI
Akamai launched Valkey Managed Database, a low-latency in-memory data layer aimed at cutting AI inference costs and accelerating RAG.
Akamai introduced Valkey Managed Database, a managed in-memory data service based on the open-source Valkey project. The company positions it as real-time memory for enterprise AI, optimizing inference costs, accelerating retrieval-augmented generation, and powering real-time AI agents.
Akamai Blog28
Inside NVIDIA’s cuDNN Graph API: Fusion, Autotuning, and Plan Reuse with cuDNN Frontend
MarkTechPost tutorial walks through NVIDIA's cuDNN Frontend graph API, covering kernel fusion, autotuning, plan reuse, and CUDA graph capture on Colab GPUs.
The tutorial explains how to express GPU computations as operation graphs via the cuDNN Frontend graph API, running the five-step build pipeline of validate, build operation graph, create execution plans, check support, and build plans. It progresses from a single fused convolution with bias and ReLU to autotuning across engine configs, FP8-style epilogues, attention, plan serialization, dynamic shapes, and CUDA graph capture. Each kernel is benchmarked against a PyTorch reference on a single Colab GPU to verify correctness and measure cost. The piece also covers practical setup issues like making libcudnn.so visible to the frontend's dynamic loader.
18
Give Your Coding Agents a Memory You Own
Hugging Face introduces Funes, a tool that gives coding agents persistent, self-owned memory outside vendor clouds.
A Hugging Face blog post presents Funes, an approach for giving coding agents a persistent memory that developers own and control. The piece targets agent workflows where context must survive across sessions without ceding data to third-party services. No article body was available in the feed, so specifics beyond the title are limited.
25
30
Nous Research Adds One-Click Local Model Setup to Hermes Desktop
Nous Research's Hermes Desktop now offers one-click local model setup that reads hardware, picks a fitting quantization, downloads weights, and configures llama.cpp automatically.
Hermes Desktop, the MIT-licensed build of the open-source Hermes Agent, now sets up local models in one click: it reads the machine's hardware, selects a model that fits, downloads weights, and configures the inference runtime. It manages a pinned llama.cpp build with CUDA, Metal, Vulkan, HIP, and CPU backends, and shows green/amber/red memory-fit verdicts per catalog model before download. Quantization floors at 4-bit, and recommended models guarantee at least a 64K context window protected by ordered RAM offload (expert weights first, never the attention cache). It runs on macOS 12+, Windows 10/11, and Linux with no account required for local models.
25
30
NVIDIA Announces CUDA Rust with cuda-oxide (SIMT) and cutile-rs (Tile) for Compile-Time-Safe GPU Kernels
NVIDIA launches CUDA Rust via open-source cuda-oxide (SIMT) and cutile-rs (Tile), bringing compile-time-safe Rust GPU kernels.
NVIDIA announced CUDA Rust, making Rust a first-class language for GPU kernels through two NVlabs open-source projects: cuda-oxide for the SIMT model and cutile-rs for the Tile model. Both use Rust's ownership and borrow checker to catch buffer aliasing bugs at compile time. cutile-rs is published on crates.io, runs on stable Rust 1.89+ with CUDA 13.3, and is already used in Hugging Face's Grout inference engine and mistral.rs; cuda-oxide is early alpha requiring nightly Rust, CUDA 12.x, and compute capability 8.0+. cuda-oxide compiles Rust MIR through the community Pliron IR framework and LLVM to PTX, while cutile-rs JIT-compiles kernels via CUDA Tile IR.
45
30
30
Rapidly scaling online storage to serve over 1 billion ChatGPT users
OpenAI's Habitat online storage platform now handles over 70 million requests per second and 500 PB of data for 1 billion users.
OpenAI details the evolution of Habitat, its online storage platform backing ChatGPT and other products, which began in mid-2024 as a Python client-side library over Azure Cosmos DB. Habitat now processes more than 70 million requests per second, serves over 500 petabytes of data across nearly 40 geographic regions, and supports over 1 billion users weekly. By mid-2025 the client library approach became brittle, so OpenAI moved Habitat into a standalone service to centralize deployments, observability, and multi-tenancy reliability. This is part one of a two-part series; a future post will cover read optimization and scaling the Azure Cosmos DB partnership.
30
UC Berkeley Researchers Release CUA-Lite, an Open Platform Unifying Sandboxes, Data, Evaluation and RL for Computer-Use Agents
UC Berkeley's CUA-Lite is an open platform unifying computer-use agent sandboxes, datasets, evaluation and RL; Lite.OSWorld cuts OSWorld memory 4.1 GB to 0.9 GB.
UC Berkeley researchers released CUA-Lite, an open platform placing agents, environments, traces, and training for computer-use agents behind one action space, one LiteSample schema, and one command across desktop, browser, and mobile. Lite.OSWorld reproduces the OSWorld task suite and evaluators in plain Docker containers (0.9 GB RAM vs 4.1 GB, cold start 23.8s, ~4.6× more parallel instances), with scores matching the QEMU/KVM VM across 13 models. The platform claims 30k+ verifiable tasks, 15+ benchmarks, 10+ agents, and 20+ datasets on Hugging Face including Aguvis, OpenCUA, and ScaleCUA. A documented SFT run lifts Qwen3-VL-2B-Instruct mean episode return from 0.138 to 0.237 on the 332-task lite.osworld split.
45
30
30
30
30
30
Agent-net Open Sources Webagent: A Go Harness That Turns Any Website into a Guarded AI Agent
Agent-net open-sourced Webagent, a Go harness turning websites into AI agents with code-enforced guardrails wrapping every tool call.
Agent-net released Webagent under Apache 2.0, a Go framework where a business fills in a declarative JSON spec, picks one provider for each of nine pluggable slots (retrieval, memory, guardrail, channel, secrets, presenter, model, action, observability), and runs webagent serve. Every tool the agent holds is wrapped by action.Guard so the chosen guardrail executes before any action runs and the model cannot bypass it. Live capabilities include OpenRouter/gateway LLM brains, MCP tools over Streamable HTTP, and Slack, WhatsApp, and HTTP channels; browser actions, OAuth-gated MCP, OTel export, and AgentNet identity/billing are not yet built. The project is v0 with a deferred-hardening list and cites arXiv 2511.19477 on an 85% versus 50% task-success gap attributed to architecture over model capability.
28
AWS Introduces Pizza Bot: An Open Source Inbox for Background AI Agents
AWS open-sourced Pizza Bot, a self-hosted inbox app for background AI agents with approval gating and multi-provider model support.
AWS released Pizza Bot under Apache 2.0 after earlier versions served over 2,000 Amazon employees for meeting prep, email drafting, and research. The app provides macOS, Windows, and Linux desktop builds plus browser and terminal clients talking to a Hono API server, with LangGraph/DeepAgents checkpoints preserving thread state and approval pauses. It supports Amazon Bedrock, Anthropic, Google Gemini, OpenAI, OpenRouter, and Ollama, exposes external tools via MCP servers, and lets skill authors gate actions behind approve/edit/reject flows.
45
The OpenClaw 2.0 release moves your sessions into SQLite
OpenClaw 2.0 migrates AI agent sessions to SQLite, adds guided credential setup, and flags shared-session controls as not a security boundary.
OpenClaw 2.0, described as the largest update in the project's history, migrates sessions and transcripts into SQLite and adds guided setup that detects existing AI credentials from Codex, ChatGPT, Claude CLI sign-ins, API keys, and local Ollama or LM Studio models. The release expands multiplayer sharing while explicitly stating its permission controls are not tenant isolation or a security boundary, and that revoked access can briefly remain usable. Startup JavaScript requests fell from 140 to 45 and startup time from about 1.6 seconds to 575 milliseconds in simulated tests against a mocked Gateway. Automation wrappers must now inspect reported health because requesting --json does not waive risk acknowledgement.
35
The Evolution of the Agent Harness
Latent Space essay argues late-2025 agent gains came from models and harnesses maturing together, with harness logic absorbed into model weights.
The piece defines the agent harness as everything beyond model weights—tools, context, memory, guardrails—and charts its evolution from ReAct prompting (October 2022) through AutoGPT's premature autonomy, Cursor/Copilot's human-in-the-loop retreat, and Devin's roughly 15% success rate, to o1's capability overhang and Claude Code's February 2025 terminal agent with permission rules. It argues the Christmas 2025 jump cited by Transformer co-inventor Lukasz Kaiser reflected model and harness curves crossing, and that remaining harnesses will serve human attention rather than the model.
32
30
30
30
30
30
Show HN: Sunk Cost – How long until a local LLM rig pays for itself?
Show HN tool 'Sunk Cost' calculates when a local LLM rig breaks even versus falling API prices, factoring electricity cost and inference speed.
A Hacker News Show HN project called Sunk Cost models the payback period of buying local LLM hardware instead of paying API prices. Users can adjust assumptions like electricity cost ($/kWh) and API speed (tokens/second), and the model assumes API prices keep falling. Where local speed is unmeasured, it is estimated from memory bandwidth divided by bytes read per token, and labelled as an estimate.
12
NVIDIA Details BioNeMo Inference Runtime (BioIR): 2.90x Higher Boltz-2 Folding Throughput and 58.5K Residues per GPU-Hour on 8xH100
NVIDIA released BioNeMo Inference Runtime (BioIR), an open-source PyTorch-compatible library delivering 2.90x higher Boltz-2 protein-folding throughput on 8xH100 GPUs.
NVIDIA detailed BioIR, a Python library that accelerates Boltz-2, OpenFold2, and OpenFold3 structure-prediction inference on NVIDIA GPUs while preserving standard PyTorch workflows. On a matched benchmark of 1,000 human dimers on 8xH100 80GB GPUs, BioIR delivered 58.5K folded residues per GPU-hour versus 20.2K for a torch.compile baseline, a 2.90x throughput gain. BioIR already powered the AlphaFold Database expansion, generating about 31 million candidate complexes across 4,777 proteomes, with 1.81 million released as high-confidence predictions. Extrapolated to 1 million targets, estimated folding energy drops from 35 MWh to 11 MWh at 8-GPU TDP equivalents.
25
Introducing the Agents API
OpenAI launched the Agents API in public beta, exposing the Codex agent harness, managed sandboxes, and multi-agent orchestration to developers.
OpenAI introduced the Agents API in public beta, giving developers the same agent harness and infrastructure that powers Codex through a single API call specifying task, model, tools, and environment. It supports OpenAI-managed sandboxes, customer infrastructure, or partner environments from providers including Cloudflare, Modal, E2B, Vercel, Oracle, DigitalOcean, Blaxel, Daytona and Runloop. Features include automatic context compaction for long sessions, tool search and programmatic tool calling to reduce token usage, and multi-agent support for parallel subagents. The harness is open-source Codex code; there are no extra API fees during beta, with developers paying only for tokens and tools used.
73
Speculative Decoding in vLLM on AMD GPUs
vLLM benchmarks speculative decoding on AMD Instinct MI300X and MI355X GPUs across five drafting methods including EAGLE-3 and native MTP.
The vLLM project documents draft-and-verify speculative decoding support for AMD GPUs via ROCm, comparing native MTP, Gemma 4 MTP, EAGLE-3, DFlash, and DSpark drafting approaches. Output-token throughput effects varied with drafting method, proposal length, model family, draft checkpoint, workload, and acceptance behavior. The post also covers how to enable each method plus practical tuning and observability considerations.
40
Perplexity Details Its GPU Embedding Stack: How Ivy, Tulip and ROSE Serve pplx-embed
Perplexity details its GPU embedding serving stack (Ivy, Tulip, ROSE), which reuses LLM prefill/decode kernels, CUDA graphs, and LazyTensors to cut launch overhead.
Perplexity engineers published a deep dive on the serving infrastructure behind pplx-embed, used across Perplexity Search and its API platform. The stack comprises Ivy (Rust HTTP gateway), Tulip (gRPC scheduling and batching), and ROSE (Runtime-Optimized Serving Engine), which reuses LLM prefill and decode kernels rather than running a separate embedding engine. Optimizations include whole-model CUDA graphs with lazy capture and a LazyTensor abstraction that overlaps CPU batch preparation with in-flight GPU work. Benchmarks are reported against vLLM v0.22.0 in BF16, with FlashAttention 4 generally fastest but FlashInfer 3 winning on Qwen-based models at very long sequence lengths.
33
HyQuant: Hybrid-Precision Quantization for LLM Attention
HyQuant keeps most LLM attention states low-bit while preserving vertical-line tokens and local windows in high precision, maintaining near-lossless accuracy.
HyQuant is a hybrid-precision quantization framework for LLM attention that quantizes most attention states to low bits while keeping accuracy-critical vertical-line tokens and local-window states in full precision, selected via lightweight attention-pattern signals. In the prefill stage it uses a hybrid-precision attention operator, and in the decode stage it applies the same principle to KV-cache compression with fused dequantization and attention computation. Across diverse tasks, models, and datasets it maintains nearly lossless accuracy; code is available on GitHub.
33
A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware
OreoLook's three-layer Redis caching architecture cuts redundant LLM calls and embedding work for CPU-hosted web-search answer generation.
The paper describes a three-layer caching architecture for OreoLook (formerly lixSearch), an open-source LLM answer engine: a Redis session context window with Huffman-compressed disk overflow, a semantic query cache matching rephrasings via embedding cosine similarity, and a URL embedding cache deduplicating embedding computations. Deployed on a single 8-vCPU Intel Cascade Lake server with 30 Hypercorn workers across three containerized replicas, it achieved an 89.3% aggregate Redis keyspace hit rate, 0.1 ms read latency, and 1.38 MB memory overhead. An LRU eviction daemon migrates idle sessions to disk and rehydrates them for resumption hours or days later.
34
30
30