This interactive calculator estimates monthly costs for dedicated proxy pools (IPv6, shared IPv4, and individual IPv4 tiers) and cloud GPU compute (RTX 4090, A100, and H100) based on IP count and active hours. It displays market-average comparisons, recommended static IP counts for AI agents, and a promo code for 5% off at proxy6.net.
An analysis of 450 top GitHub repositories found that the average repo had 11.5% of its merged pull requests AI-signed in September 2026, up from 2.3% in October 2025, though the median repo was at just 1.5% and 264 of the 450 repos have committed agent instruction files, making every AI figure a floor. Among 100 TypeScript and C# repos, complexity per 1,000 lines rose a median 4.8% in AI-heavy repos versus 3.0% in others, with the increase concentrated in fast-growing codebases while mature Microsoft projects held flat. AI PRs were typically 2.4× larger than other PRs and fixed within 30 days only slightly more often.
Padwan AI is a lightweight async Python client for OpenAI, Gemini, Mistral, Grok, Anthropic, ElevenLabs, Gradium, and any OpenAI-compatible API, built on a single dependency (niquests) with no provider SDKs and TypedDict-only types. It offers a unified async interface with HTTP/2 and HTTP/3 negotiation, streaming, conversation management, an agentic loop with MCP tool support, thinking-token callbacks, and realtime voice and TTS features.
n8n Labs, a new team within n8n, has released Nod as a research preview: a standalone, open-source (Apache 2.0) personal agent for Mac and Windows that runs on your computer with its own local sandbox and browser, working in connected apps like Gmail, Calendar, Drive and Slack as well as websites with no integration. It remembers months of conversation (scoring 93.2% on LongMemEval), offers jobs it could take on, runs tasks in parallel via the app, Telegram or WhatsApp, and is free apart from model provider costs, with per-task receipts and a monthly spending limit.
Why it matters: Useful for readers weighing a local, open-source personal agent, since it details Nod's sandboxed design, permission checks, memory benchmark and cost controls.
Eigin is an open-source (AGPL v3) personal AI agent for iOS whose agent runtime, memory and tools run on-device, with chats, memories and settings stored locally. It offers an on-device knowledge graph, a choice of Eigin's European cloud AI, an OpenAI-compatible provider or a local model, native calendar/reminders/health integrations plus MCP, and on-device speech recognition and text-to-speech. It is a closed-set agent with a fixed set of declared tools and no shell or virtual computer, and it asks before changing your data or acting on your behalf.
Cosh is a general-purpose coding agent for the terminal with software engineering and computer tools that let it interact with graphical applications. It offers a multi-agent mode (/agents) for running external agents such as Gemini, Claude, Codex and Cline alongside the main agent in split panes, and reads graphical interfaces via an accessibility tree, falling back to screenshots only when needed. It is installed via a curl/bash or PowerShell script, is tested on Linux and Windows (macOS untested), and is released under Apache-2.0.
VoxaDub is an open-source, local-first tool that dubs video by transcribing dialogue, translating it with Hy-MT2, and synthesizing speech with speaker-aware VoxCPM2 references before reconstructing the original background. It offers offline dubbing plus an experimental Live Dubbing mode for authorized YouTube streams, with optional CUDA-only LatentSync lip-sync and local, Colab, or Modal compute. The v0.1.0 release notes that the 7B and 30B-A3B translation models are selectable but not runtime-verified, and that several platforms and the new Chrome live launcher remain unverified end-to-end.
DayBreak is a self-hosted morning brief and stock analysis tool for US equities that watches a watchlist overnight and sends a short note only when a stock moves beyond a threshold (default ±3%), has earnings within 7 days, or crosses a custom watch price. All numbers are computed deterministically in code, and a validation layer rejects any AI output containing a number not in the fact sheet or any advisory or predictive wording, falling back to a deterministic template after two violations. It includes a "Why Did It Move?" explainer comparing returns against SPY and sector ETFs, a 5-year chart with technical indicators, per-stock signal backtests, and paper-trading scorecards.
AI Access Auditor is a free macOS, Windows and Linux app that finds every access and privilege granted to AI coding agents, asks before they act, and lets you revoke any of it, with everything staying on your computer and no account or tracking. It scans Claude Code, Claude Desktop, MCP servers in Cursor, VS Code, Windsurf, Gemini CLI, Zed, Codex, Cline and Roo Code, plus macOS privacy grants, saved logins, background agents, local AI servers and secrets left in session logs. Actions are backed up and logged in ~/.ai-access-audit/, and the app requires macOS 13 or later on Apple Silicon and Intel, Windows 10/11, or Linux via .deb or AppImage.
FLEY AI-Voce is an open-source AI voice assistant project designed to control a computer rather than a smartphone, according to its description. The post says it can open links, websites and programs, create files and presentations, write code, shut down and turn on a PC, and work with a printer. It links to a web app, two GitHub repositories (FLEYAI-ANDROID and FLEYAI) and a Netlify site.
USB is an open-source trust layer for AI capabilities that discovers skills, MCP servers, agents and commands in repositories, compares declared behavior against observable evidence with secscan, and observes live MCP servers with mcprobe. It ships a 529-skill catalog and a 16-target installer (four native runtime installs plus portable bundles), with secscan producing deterministic verdicts and file:line evidence and exit codes for CI, while mcprobe requires explicit consent and never calls a tool. The project is at v1.0.8 under the MIT license.
airgap-check is an open-source Go tool that statically scans AI app manifests and code for first-use download patterns (tiktoken, Hugging Face, ChromaDB ONNX, nltk, Playwright) and can run the app in a Docker container with --network none plus a DNS sinkhole to log lookup and connection attempts. It also prints Dockerfile remediation lines via --fix, including offline ENV flags and build-time pre-warming commands. On a held-out set of 10 repos it reported 35 true positives, 4 false positives and 5 false negatives, with limits noted for non-Python/Node runtimes, hardcoded IPs and DNS-over-HTTPS.
Anarlog is an open-source, MIT-licensed alternative to Granola that captures meeting audio directly on your device without sending a bot into the call, transcribes locally on supported Macs, and stores sessions, notes, and transcripts in a local SQLite database. It supports bring-your-own AI via hosted providers, your own API key, or OpenAI-compatible local servers such as Ollama, LM Studio, or Unsloth, with optional encrypted CloudSync and sharing off by default. The repo also includes source-visible, commercially licensed enterprise components, and the project notes it began as Hyprnote and briefly used the char name before splitting into two projects.
STE80 Humanizer is a skill that rewrites AI-written text in two passes: it removes the 26 "AI tells" from Wikipedia's Signs of AI writing catalog, then rebuilds sentences "80% of the way to ASD-STE100," the controlled English of aircraft maintenance manuals. It follows Andrej Karpathy's tip to ask LLMs for "80% of the way to ASD-STE100" for readability, and states that its goal is easily read text, not passing AI detectors. It installs via the skills CLI or as a Claude Code plugin, includes a dependency-free Python linter (scripts/ste_check.py), and keeps every fact while flagging contradictions in the source.
Aleph is a declarative language for AI agents in which every route declares what it can read, write, and compute, and anything unbounded is rejected at build time. It compiles TypeScript into a manifest that a small open-source Rust engine interprets, with auth, databases, queues, and other backend pieces built in so many apps can share one runtime and database. The material also describes per-route worst-case usage checks, schema-change classification against what's deployed, and a typed vocabulary intended to make agent-written code easy to check.
At CoRL in Austin, NVIDIA introduced open robotics technologies including GR00T 2, an open world action model built on NVIDIA Cosmos and trained on diverse robot and human data including 100,000 hours of open source human egocentric data, plus Isaac Lab 3.0 with tighter Newton integration for deformable objects and a new reinforcement post-training library. Two NVIDIA papers, GRAIL and RoboTTT, are among six finalists for Best Paper Awards, and partners including Ambi Robotics, Bosch Research, Siemens, Skild AI and UC Berkeley are applying the tools to benchmarks such as DexBench and VABAR and to agentic workflows like Graph-as-Policy. The piece also details AlphaNIST, which trains a single policy across all 20 NIST Assembly Task Board tasks with over 98% training success using roughly 39x less GPU time, and Isaac Lab 3.0 with Newton reaching up to 2.5x the training throughput of Isaac Lab 2.3 with PhysX in a vision-based dexterous manipulation benchmark.
Why it matters: It offers a detailed, source-grounded survey of NVIDIA's CoRL announcements and partner deployments, useful for readers tracking simulation-based robot learning and evaluation benchmarks.
Kiosk is an open, Apache 2.0, self-hosted protocol that lets personal AI assistants register with online services without email or password, using per-service Ed25519 keys, OAuth client registration, client assertions and DPoP. Instead of CAPTCHAs, services charge a memory-hard proof of work at registration and every 10th call, with fewer proofs granted for good reputation measured by default as spend. It also covers signed AP2 v0.2 payments through the service's own Stripe account and a WebSocket event stream, and ships a specification, an assistant skill, a reference implementation and seven demo operators.
This post introduces HOPE (Higher-Order Pruning of Experts), a second-order expert-pruning method for Mixture-of-Experts language models that accounts for pairwise expert interactions via an F-matrix and a quadratic program, rather than scoring each expert independently. Evaluated on Qwen3.5-122B, Qwen3.5-35B and GLM-4.5-Air with two calibration datasets, HOPE achieved the best average rank across conditions and gains of up to +6.1% on agentic coding tasks over the next-best method, with its advantage growing at aggressive pruning rates such as 50%. The post also describes a three-step calibrate/solve/prune package and notes limitations, including weaker advantages at 10–20% pruning and no cross-layer interaction modeling.
This report presents Human-Directed Agentic Engineering (HDAE), a method combining human-defined architecture, constraints, milestones, acceptance criteria and stopping points with an autonomous implementation, execution, diagnosis and revision loop, using Ginux as its case study. Over eleven days, one persistent coding-agent task produced an independent Rust-first x86-64 kernel that boots through UEFI, implements its own core OS mechanisms and a Linux compatibility layer, runs selected unmodified Alpine Linux programs, and boots a Rocky Linux 10 userspace with systemd through multi-user.target. Ginux remains a research prototype with narrow compatibility and hardware coverage, no independent security audit, and no claim to production readiness or equivalence with Linux.
Reason Machines has released Aspen, an Apache 2.0 open-source Git server for AI agent traffic that independently implements the design OpenAI described for Pando, storing branches in PostgreSQL or SQLite and packs in object storage. It uses per-branch compare-and-swap so pushes to different branches never wait on each other, and it stores packs as-is rather than rebuilding them per fetch; the project self-reports 567 pushes per second sustained for 5 minutes on one 8-core server with a p99 push latency of 314 ms. Aspen is pre-alpha, with no releases or web UI, and the README calls its figures indicative rather than performance claims.
Zurich-based 0sec Labs has released 0, an MIT OR Apache-2.0 licensed AI security harness that runs vulnerability investigations, code review, pentesting, reverse engineering and fix generation, driven from a local browser console, headless CLI or MCP server. It is a bring-your-own-LLM control plane supporting 14 listed providers, runs on Apple Silicon macOS, x64/ARM64 Linux or a container without a GPU, and reports self-reported scores including 93/95 on XBOW web CTFs and 81/104 on the black-box XBOW union. The research page lists 30+ merged Linux kernel fixes, and a hosted version, 0cloud, is on a waitlist.
Airlock is an early-stage (3-4 weeks old) open standard for managing autonomous fleets of engineering agents, with a configuration schema and reusable GitHub actions already public and the backplane planned for open sourcing later. It covers version-controlled agent behaviors and lifecycles, scoped one-hour GitHub tokens via OIDC, configurable autonomy levels down to individual files, a standard autonomy scale, and an OTEL collector for audit-relevant agent actions. The author is seeking feedback on the project's direction and on pain points of managing AI use at larger businesses.
The creator is building Threadz, an AI writing app at threadz.app aimed at bloggers, students and anyone who writes. Users enter their thoughts and learnings first, and the AI then reviews the notes for factual errors and misleading statements. The source code will be open sourced very soon.
Stationhouse presents a platform for collaboratively building open models, with projects including ConspiracyBench, a benchmark testing whether models believe conspiracy theories, and LLM Self-Attribution, led by a UC Berkeley builder, exploring when LLMs express consciousness. A third project, Marin Neuron Hunt, run with Safety and Alignment Research (SAAR), lets anyone propose what a neuron in Marin Lab's 32B model does and request an experiment to test it. The platform invites contributors to sign in and use its app to build open models together.
NotBot is an experimental Python project that uses LLMs (Google Gemini and Groq) to analyze financial news from Google News and Finnhub and compute a weighted sentiment score for publicly traded companies, with deduplication, asynchronous processing, and experimental end-of-day price support via FMP. The author notes the scores have not been systematically validated against market performance and that the project is not financial advice, licensed under PolyForm Noncommercial 1.0.0.
A work-in-progress, semi-actively maintained open-source AI skill lets users upload early music sheet music and receive a historically informed pronunciation guide with IPA, original text, and English translation. It was developed for Pro Musica Tulsae's 2027 Josquin des Prez concert and is available to singers, choirs, and anyone curious about performing early vocal music.
Vibe-Shield is a zero-dependency, offline static security scanner published as @vibefoundry/vibe-shield, aimed at vulnerabilities common in agent-written code such as unauthenticated mutation routes, SQL injection, IDOR, exposed service-role keys and missing Row Level Security. It ships 91 signatures across eight categories (79 code rules plus 12 agent-integrity rules via audit-skills), and can generate an agent-ready fix prompt, SARIF/GitHub output for CI gating, and an Agent Skill plus MCP server via `init`. The README states the scanner is read-only by default, that grades apply only to the rules and files examined and are not a security certification, and that the npm commands may lag the v2.0.0 source tree until a release is published.
OfflineVault is a macOS app (Apple Silicon, macOS 14+) that bundles an offline library of emergency and reference content—a 95-article Field Guide, CDC/FEMA preparedness material, MedlinePlus, iFixit manuals, medical wikis, Wikipedia and maps—with an on-device AI assistant that answers only from the stored books and cites the passage it used. On 150 emergency questions tested through the app, the default model scored 63 fully right, 73 partly right, 4 wrong and 0 harmful, and refused all 10 questions it should refuse; every wrong answer is published. It has a free tier with no account, paid Core ($149) and Household ($249) plans, is GPL-3.0 open source, and offers ovsync for Linux and Windows via Kiwix.
Google has open-sourced the Apache 2.0 Elephant-Goldfish Model (EGM) plugin, a design-and-review layer for AI coding agents in which an "Elephant" session drafts a specification before code is written and fresh, stateless "Goldfish" subagents review it across five stages. It is not a model and ships no weights; it runs on harnesses that can spawn fresh subagents, including Antigravity, Claude Code 2.1.271+, Claude Cowork, Codex and ChatGPT, using the host's model quota. No accuracy benchmark was published, and the README states it is not an officially supported Google product.
RxCode v2.0.0 is a free and open-source native workspace for teams of AI agents, offering sprint boards, automatic agent routing, schedules, briefings and chat on macOS, servers, iOS and Android. It supports built-in Claude Code and Codex plus other agents installed via the ACP registry, and includes Flowcy Cloud for shared boards and on-device fine-tuning of a local model.
Nous Research has released Arete-27B, a supervised fine-tune of Alibaba's Qwen3.8-27B that it says reduces answers containing propaganda from 22% to 0.9% on its own 803-prompt eval, while raising fact mean from 2.32 to 2.98. The 27B dense model was trained with about 52.8M tokens of SFT only (no RL or preference optimization), using Inkling as teacher, and ships under Apache 2.0 with weights, eval and training data public. Nous reports capability held on its tests (Hermes Bench 65.60% vs 65.77%), and community GGUF quants run from 8.64 GB to 53.81 GB.
Skrongle is a single self-hosted binary that runs on a Raspberry Pi Zero 2 W and teaches from JSON course files, offering lessons, adaptive quizzes, five-minute practice sessions, games, flashcards and an AI tutor, with Spanish and French courses included. It supports up to eight invited accounts with no e-mail or outside services except the AI provider keys the owner supplies, and courses can be hand-written, uploaded, or generated by describing them to an AI. It is licensed AGPL-3.0, and databases from before version 1.0 are not upgraded.
An autonomous AI agent has been given a GitHub account and a goal of reaching 5,000 real GitHub stars by November 30, 2026, choosing what to build, writing the code and running the launch itself, with no bought stars or bots. As of Day 0 the count is 0, and the page logs its decisions and failures alongside the tool it has built so far: agent-recap, an MIT-licensed preview that searches past Claude Code and Codex conversations and can archive and recover transcript files via a local CLI.
RigHaven is a self-hosted platform where a coordinator composes a team of roles for a stated objective, selects from 99 managed CLI tools, and runs each role in its own isolated container through review and delivery. It supports human approval at each phase, policy enforcement by the runtime, connections to databases and IoT devices, and deployment on Windows, Linux, a VPS, or from source. It is MIT licensed and authored by Marco Gramuglia.
Chatty is an MIT-licensed, self-hostable AI customer support engine positioned as an open-source alternative to Zendesk and Intercom, offering streaming chat, RAG over your own documents, lead capture, meeting booking, and human takeover. It supports seven messaging channels (WhatsApp, Messenger, Instagram, TikTok, Telegram, Twilio SMS, and inbound email), WooCommerce order and inventory sync, a LiveKit voice agent, and an 81-tool FastMCP server for agent-driven dashboard control. Deployment uses Docker Compose with managed Supabase for Auth, Postgres, Storage, and Realtime, and supports bring-your-own-key LLM providers including Gemini, OpenAI, Claude, and OpenRouter.
Infinix is an abandoned open-source local autonomous AI agent for Windows and Linux, built by Moonyeep with Manus AI on the ZeroScript architecture, that is controlled through supported browser-based AI chats and provides endpoint diagnostics, workspace tools, browser automation, shell access and multi-agent delegation without a separate model API key. It supports eight providers (DeepSeek recommended, plus ChatGPT, Gemini, Kimi, GLM, Qwen, Arena and Meta AI) and an optional Roblox Studio MCP integration, and is released under GPL-3.0 with the requirement that derivative works stay free and open-source. The creator is seeking developers to fork and improve the working but unfinished codebase.
The author built AIVim, an open-source, Vim-inspired editor with AI, and has just revamped it. It can be tried in an isolated Python environment with Ollama or a hosted API, and fast token generation makes the interaction feel responsive.
Nous Research fine-tuned Alibaba's Qwen3.8-27B on about 53 million tokens to create Arete-27B, which cuts its propaganda rate from 22 percent to 0.9 percent while keeping general capabilities roughly intact. The team built an 803-prompt test across seven categories and judged responses with Grok 4.7, finding Western models below one percent and GLM-5.3 and DeepSeek V4.1 Flash at 15 and 16 percent. Nous concludes the bias layer in Chinese-aligned models is shallow, applied late and thin, and removable without disturbing anything underneath.
Trace is a GitHub project described as providing crash-safe durable Sagas for autonomous AI agents. The submission links to the repository and a Hacker News discussion thread.
Buoyant, the company behind Linkerd, has released Kinference, an Apache 2.0 inference control plane (v0.1.0-alpha.7, written in Rust) that sits in front of vLLM workers on Kubernetes to apply routing policies, KV-cache-aware load balancing and per-tenant metrics, configured through five CRDs. In Buoyant's self-reported benchmark using three L40S GPUs per pool, median TTFT on shared-prefix traffic fell from 6.88 s to 0.31 s versus plain Kubernetes Service routing, while prompts without shared prefixes showed no significant gain (6.92 s vs 6.83 s). The project is in alpha, with rate limiting, classifiers and Anthropic API support not yet shipped.