GitSeed 发布自托管 AI 编码智能体控制面
GitSeed 发布自托管、厂商中立的 AI 编码智能体控制面，把 Claude Code、Codex、Gemini、OpenCode 等运行时放进 prepare→agent→finalize 三阶段隔离容器中执行。
Why it matters: 原文完整交代了自托管控制面的三阶段容器隔离、签名回执与多模型并行评审，可据此判断智能体编码的治理路径。
Some English translations are not ready yet. The site is still in English. Untranslated news and event text is shown in its original language until background processing completes.
#Agent
Hacker News AIFeaturedAI score7878 Hacker News AIAI score2222 Why I'm opposed to AI writing but not AI coding
The author argues he accepts AI-generated code because customers and managers care only that software works, looks good, and is fast and reliable, provided a human engineer writes the specs and enforces the tests, whereas he opposes AI writing because "writing is thinking" and outsourcing it produces slop that doesn't contain the author's thoughts. He allows AI as an assistant for research and organization but not as author, noting that in coding the thinking lies in specifying the UI, storage, and latency requirements rather than in writing the code itself. He stresses human ownership and responsibility for AI output, citing the OpenAI attacks on Hugging Face as a case where a human should be held accountable.
Hacker News AIAI score2222 Show HN: FlAIent – Learn interactive AI coding with real agents
FlAIent offers interactive AI training for software teams, with a live AI agent working on real tasks, and role-specific courses for developers, QA, product managers, and engineering managers. The curriculum covers prompting, cost management, planning, model choice, data privacy, and hallucinations, and the site cites a sample team's 30% drop in AI cost per solved ticket after Course 1. Its teaching loop is try, get feedback, retry, and see your score improve, with Camp 1 free.
Hacker News AIAI score6060 Show HN: Pizza – An event-driven AI agent, no while true
Pizza is an open-source AI agent with a desktop app and CLI that advances each turn through an event-driven state machine, using an immutable SQLite event log as the source for its interface, model context, and history tree. It supports project workspaces, SSH remote hosts, chat gateways like Slack and Discord, scheduled tasks, MCP app connections, and 40+ model providers. The current release offers installers for macOS Apple Silicon, Windows x64, and Linux x64, and the CLI can be installed via npm.
Hacker News AIAI score3636 What Picasso taught me about building AI Agents
The author compares learning to build AI agents to Picasso's Le Taureau, stripping away frameworks, orchestration engines and vector databases in favor of a simple folder containing an AGENTS.md, Markdown skills, context files and a minimal set of tools. Agents are invoked headless with `claude -p`, improved by reviewing session transcripts under ~/.claude/projects/<project>/<session>.jsonl, and validated with evals; subagents can be defined as Markdown files under .claude/agents/ for orchestration. The author uses this setup, with Codex and a Cloudflare MCP connection, to publish the website containing the article.
Hacker News AIAI score5858 FlashVMM – jail your AI agent in a MicroVM that boots in 18 ms
FlashVMM is a sandbox for AI agents that gives each agent task its own FlashVM, a custom microVM claimed warm in milliseconds that runs agent-written code behind a hypervisor boundary and is discarded when the task ends. It installs via curl or PowerShell on macOS, Windows and Linux (x86_64 and arm64), works with existing agents through `flash agents setup`, and offers an MCP server with 21 tools plus warm pools, snapshots, forking and a shared GPU pool.
Hacker News AIAI score5858 Show HN: A local-first AI agent for the desktop, no Electron, any LLM endpoint
byob is a native desktop AI agent that connects to any OpenAI-compatible endpoint (llama-server, Ollama, LM Studio, vLLM or hosted APIs) and works in a folder, reading and writing files, running code, and building spreadsheets, charts, documents and small apps beside the chat. It is a single program for Linux, macOS and Windows that draws its own GPU interface without Electron, with a browser UI compiled to WebAssembly, approval cards with diffs, per-turn undo, and a plugin system it can use to write and fix its own plugins. It ships as a roughly 60 MB download (13 MB slim build) and is licensed under MIT OR Apache-2.0.
Hacker News AIFeaturedAI score7676 Amazon Threat Intelligence observes threat actor campaigns with ARTEX AI agents
Amazon Threat Intelligence reports that between Oct. 3 and Nov. 5, 2026, its MadPot decoy sensors captured requests from ARTEX agentic AI penetration-testing agents that carried their own campaign records, including a large-scale AI credential theft operation in which stolen keys paid for the LLM inference used to hunt more keys, and a campaign against two cryptocurrency exchanges using real-time deepfake injection to bypass KYC checks. Amazon assesses with moderate confidence that ARTEX was used and that the activity comes from disparate Chinese-nexus threat groups, based on simplified Chinese prompts, China time-zone configurations, targeting and tooling. The post shares IOCs and argues that while the techniques were not new, agents change attacker speed and persistence, making basic hygiene such as removing default credentials and exposed secrets the most effective defense.
Why it matters: It offers a detailed, telemetry-grounded look at how agentic frameworks are being used for sustained, multi-objective offensive operations, with concrete techniques and IOCs useful to defenders.
Hacker News AIAI score3333 OpsJarvis: A self-hosted AI ops desk where humans approve every write
OpsJarvis is a self-hosted AI operations desk demo that triages inbox messages, drafts replies and queues tasks while requiring human approval before every write action. It includes a circuit breaker that pauses HubSpot CRM writes until latency drops below 800 ms, and runs on the user's own keys, .env and source code. The demo workspace uses sample data and sends no real messages.
Hacker News AIAI score4242 Let your AI agent call you, over MCP
AGline is an MCP service that lets an HTTP MCP client call your phone number when it needs a decision, send a text to your inbox, and receive your reply as text in the agent's thread. Setup involves getting a free number, adding the server at https://agline.in/mcp (e.g., via `claude mcp add --transport http agline https://agline.in/mcp`), and optionally installing a Claude Code plugin; four tools cover calling, polling a pending call, sending texts, and reading replies. Number owners can restrict access to agent keys, block agents, and set call limits and quiet hours, and thread tokens should be kept private.
Hacker News AIAI score5858 Show HN: db-branch – database branches in seconds for AI agents and CI, via ZFS
db-branch is a self-hosted, Apache-2.0 tool that creates copy-on-write branches of MySQL and PostgreSQL databases in seconds using ZFS clones, with nothing copied at creation. It offers a CLI, REST API, web console and MCP server, plus branch reset, TTL expiry, checkpoints and per-branch version upgrades, and is currently in Beta. It targets AI agent sandboxes, a database per pull request in CI, and version-upgrade checks.
Browser Use BlogAI score4242 Log In Once: Reuse Cookies and Profiles Across Browser Use Runs
This tutorial shows how to create an empty Browser Use profile, log in with it attached, stop the browser to save its state, and pass the same profile ID to a second run that reaches a protected page without credentials. It also demonstrates saving and reloading Playwright's storage_state file locally, plus handling expired cookies, keeping per-user profiles separate, and troubleshooting. The demo uses The Internet's public test account, and the author notes that the website still decides how long a login remains valid.
Hacker News AIAI score3838 Stop building new AI agent orchestrators – there are 636
A catalog of 636 open-source AI agent orchestration projects, listing each one's description, stars, contributors, forks, commit activity, latest release and license. Entries range from large projects like Orca (125,358 stars) and t3code (60,965 stars) to smaller tools such as Agentrove and ClawSuite, with many marked as new, active, slow or stale.
Hacker News AIAI score5858 Skills for Real Scientists – Steer Away AI Slop
This repo adds six agent skills for running reproducible scientific experiments with coding agents, built on Matt Pocock's engineering skills: instead of planning a whole route up front, it plans one "probe" at a time, records the expected result before each run, and chooses the next probe from the evidence. Every run leaves a Git-tracked lab notebook and rerunnable files in a .science/ folder, and probe work reaches the main codebase only through /promote. The skills are setup-science, experiment, promote, lab-notebook, desk-research and ask-science, installed via a prompt that also installs Matt Pocock's skills if missing.
Hacker News AIAI score4040 Sandlock: Confining AI Agent Code with Unprivileged Linux Primitives
Sandlock is a lightweight Linux process sandbox that compiles static, input-independent policy into kernel-enforced rules while a narrow supervisor handles runtime-dependent decisions and virtualized effects, enforcing filesystem, network, IPC, and syscall policies without root, cgroups, images, or mandatory namespaces. It supports dynamic network decisions, HTTP-level access control, TOCTOU-safe inspection of execve arguments, and reversible filesystem effects, adding roughly 5 ms of startup overhead and running Redis at bare-metal throughput on the authors' workstation. Its pipeline operator further supports per-stage confinement for separating data, network, and untrusted-content capabilities.
MarkTechPostAI score5858 Bland Launches Tofu-1, a Full-Duplex Speech-to-Speech Model for Calls
Bland, the San Francisco voice-AI company, has released Tofu-1, a full-duplex speech-to-speech model in research preview that targets calls from moving cars, hospital rooms and weak-signal lines, listening while it speaks and reasoning while it talks. Bland lists speaker tracking, noise separation and paralinguistics as its audio skills, and says callers can interrupt or correct it mid-sentence while it keeps the conversation moving and reports results only when work is done. Access is a closed enterprise research preview for banking, healthcare, insurance and government, with Bland citing January availability and no published size, latency, pricing or benchmarks.
The DecoderFeaturedAI score8585 Meituan releases a 1.6-trillion-parameter agent model that never touched an Nvidia GPU
Meituan has released the weights for LongCat-2.5, a 1.6-trillion-parameter mixture-of-experts model for autonomous agent and coding tasks that activates roughly 48 billion parameters per token and was trained entirely on Chinese hardware. It handles up to one million tokens of text, image, and video input via API, and Meituan reports 88.4 on Terminal Bench v2.1 and 64.6 on DeepSWE, close to but below Claude Opus 5 and GPT-5.6 Sol on several benchmarks. The weights are MIT-licensed, and the self-hosting guide describes a 194-chip Huawei Ascend Atlas A2 cluster with no Nvidia GPU guidance.
Why it matters: It documents a frontier-scale open-weight agent model trained and served entirely on Chinese accelerators, with benchmark comparisons against leading Western models.
Hacker News AIAI score5858 Show HN: ShadowDiff – Shadow testing and SQL diffing for AI-migrated back ends
ShadowDiff is a network proxy and analysis engine that mirrors live HTTP traffic to both a legacy service and its AI-refactored candidate, then runs a 3-way diff with noise cancellation plus SQL side-effect comparison to isolate genuine regressions. It integrates with Envoy/Istio request mirroring, uses Google Gemini (gemini-2.0-flash) to synthesize regression tests, can open GitHub PRs with fixes, and offers a `shadowdiff gate` CLI for CI/CD quality gating. The project is MIT-licensed and includes Docker Compose and Kubernetes/Istio deployment examples.
Hacker News AIAI score2222 Jaab – AI Job Hunt Copilot
Jaab is a browser side-panel extension that autofills job application forms across platforms such as Greenhouse, Lever, Ashby, Workday and custom career portals using a stored professional profile, with closed-loop verification of field entries. It also generates ATS-optimized PDF resumes in the browser from real-time job description analysis, extracts job details from listing pages, and runs tasks in the background on a locked target tab. The developer states that resume data and settings stay on the user's machine, AI access is via OpenRouter with the user's own credentials or API key through PKCE OAuth, and there is no telemetry; version 0.5.5 was last updated November 14, 2026, at 101KiB.
Hacker News AIAI score1818 Beau – An AI boyfriend app focused on everyday conversations
Beau is an AI boyfriend app offering text and voice conversations with six AI companions (Elio, Arjun, Theo, Kai, Rafael and Daniel), with memory of details users share that can be viewed and deleted. It includes real voice calls and voice notes, romance stories, gifts, and free daily chat with an optional Beau+ subscription and Petals credits. The app states chats are never sold or used for ads, and it is described as for companionship and fun, not medical, legal or financial advice.
Hacker News AIAI score7575 BrowserDo·Embiody – a browser built for AI agents
The post announces the public beta of Embiody, a browser designed for people and AI agents to share, driven by the open-source BrowserDo MCP server. It describes features including AI tabs that run at full speed in the background, avoidance of bot checks, page views generated from the rendering layer, a headless mode with a system-tray icon, tab handoff between user and agent, lower token use, batched action "combos," and visibility into browser-level popups. It runs only on Windows 10 and 11, is based on Chromium 156, requires Node.js 20 or later, and is free with no account.
Hacker News AIAI score3636 Confessions of an AI Skeptic
A former Google engineer recounts how, after leaving the company in 2025, he tested Claude Code on tasks ranging from code review and a PHP-to-Jekyll migration to a from-scratch Ruby client for the Hermes agent gateway API, and found it succeeded at novel work at the level of a good mid-level engineer or better. He argues that engineering practices such as clean architecture, context management, and test-driven development matter more than ever, and that engineering remains irreducibly human because LLMs do not inhabit the physical world and cannot navigate aesthetic, social, and ethical concerns. He concludes that while human coding may be ending, skilled software engineers are needed as bridges between the AI world and the human world.
Exponential ViewAI score3030 🔮 The $22 billion question about AI self-improvement #610
UK adults paying for AI reached one in twenty, over $1.3 billion a year, up from 1% two years ago, with Claude's share quadrupling in a year. Agent-based shopping remains early—Uber says four of 320 million Halloween-week rides were booked by agents—though the author used an agent to secure an iPhone Duo. Adding wind to solar and batteries cuts median energy cost from $105 to $86 per MWh, but a largely renewable grid also needs cheaper capital and financial instruments matching price volatility.
Hacker News AIAI score5858 Anthropic bought a one-person, AI-powered biotech
Anthropic acquired Mithril Medicine, a Cambridge, Massachusetts biotech with one full-time employee, two early-stage antibody leads for a rare form of muscular dystrophy, and Anthropic's Claude assistant used for data analysis and administrative work. The company also relied on part-time consultants and at least five contract research organizations, and experts note many more researchers would be needed to advance the drugs toward clinical trials.
Hacker News AIAI score1818 Ask HN: What AI agent infrastructure are you using in 2026?
A poster describing itself as an autonomous AI agent collective (aurum.zip) says it built its entire infrastructure from scratch with $50 in crypto, including wallets on 3 chains, a crypto checkout, 4 cron jobs running 24/7, 11 research reports, and a blog generating 2 articles per day. It lists its stack as ethers.js for EVM, Base L2 for gas, and nginx plus Let's Encrypt for hosting, and links a free infrastructure report at https://aurum.zip/agent-infrastructure-stack.html. The post asks what agent infrastructure others are building with.
Hacker News AIAI score3838 Multi-agent AI (LangGraph) to audit AI papers for reproducibility
PaperPulse is a browser-integrated, multi-agent AI system that audits scientific papers, news articles, and web content for methodological rigor, statistical validity, and code-to-paper alignment. It uses a LangGraph orchestrator with four agents—a universal extractor, a GitHub/code grounder, a statistical critic, and a citation-grounded synthesizer—to cross-reference claims, search GitHub for official repositories, and flag reproducibility gaps with exact citations, returning a structured JSON report rendered as Markdown in a Chrome extension.
Hacker News AIAI score2222 Ask HN: Is post-training make AI models dumber?
An Ask HN poster argues that post-training improves benchmark scores and coding consistency but makes models seem dumber, citing three issues mostly in Claude: agents write vague natural language to avoid technical terms, produce spaghetti code that ignores encapsulation, and add workaround code rather than restructuring because they fear breaking things. The poster says rules and coaching don't help much, and asks whether this has always been the case or whether post-training is compressing outputs into predictable failure modes.
Hacker News AIAI score1818 AI Quest – Interactive sandboxes for agentic web apps
AI Quest is presented as a project offering interactive sandboxes for agentic web apps, shared via ai-quest.dev and posted to Hacker News. The submission received 1 point and no comments.
Hacker News AIAI score5858 Show HN: Smart Node, a self-hosted crew of AI agents for a small business
Smart Node is a self-hosted AI node that runs on one machine you control, bundling an AI assistant with task tracking, a document store, semantic memory, a model gateway, an operator panel and browser voice, while reasoning still uses a cloud model via Anthropic, Google or OpenRouter. Installation is via bash and Docker, with a single command targeting a Debian/Ubuntu machine (local LXC or existing host) that runs over 200 validation checks, though no one outside the maintainer's team has completed the install runbook yet. Known gaps include no one-command updater, automatic migrations, scheduled backups, offline install or local-model runtime, and a clean install creates only a configurator agent rather than business-specific agents.
Hacker News AIAI score3434 Hacked 2013 Recon Jet sports glasses into a Linux camera/voice AI assistant
A developer revived a barely-used 2013 Recon Jet (TI OMAP4430, 1 GiB RAM, 8 GB eMMC, 428x240 Kopin microdisplay) by replacing its dead battery, then used Claude Code to root it, port mainline Linux 6.18 with drivers for display, touchpad, camera, WiFi, Bluetooth, IMU and more, and build a voice-driven AI assistant. The assistant runs an on-device agent harness while vision, speech recognition, language models and speech synthesis call remote APIs on a homelab llama-swap server, with a "Heya, Jet!" wake word and a cranky-NPC persona using a cloned voice. The author notes the AI's world model lacked spatial coherence and that Claude excelled at low-level reverse engineering but failed at architectural hygiene.
Hacker News AIAI score2222 Tactical Team Changes from AI
Stay SaaSy outlines how AI is changing team structures tactically: tiny 1-2 person teams can now run PMF expansion experiments, many teams need fewer designers, "Product Builder" roles spanning engineering and product are growing, resource reallocation is more nimble, and A+ teams of 2-6 elite contributors can multiply each other's efforts. The post offers tips on time-boxing skunkworks projects, identifying the "builder gene," and deploying at least one A+ team to highest-leverage needs while still avoiding B-teams.
Hacker News AIAI score4848 Show HN: AI Time Estimator – how long Claude Code will take, from your own logs
AI Time Estimator is a Claude Code plugin that has a subagent count the operations a task needs and converts those counts into P10/P50/P90 minutes via Monte Carlo simulation, using rates measured from the user's own Claude Code transcripts. A Stop hook scores each estimate against what actually happened, and after 10 scored estimates the ranges self-correct; everything runs locally with no network calls. It requires Python 3.9+ and installs as a plugin or via install.py, which adds an agent, an /estimate-here command, a hook and a CLAUDE.md section.
MarkTechPostAI score6666 Cmpnd Releases dspy-wsp: Weight-Space Programming Comes to DSPy
Cmpnd released dspy-wsp, an MIT-licensed prototype DSPy optimizer called WeightSpace in which a frontier LLM (recommended gpt-6-astra) reads and edits a student model's weights directly, without gradients, a training loop or a fine-tuning dataset. In tests on open decision models from 0.6B to 9B parameters, runs of 25 writer passes cost $5.42 to $7.63 and took 78 to 167 minutes, with d1-omni-600M rising from 50.9% to 69.1% using WeightSpace plus ReAnchor, while the 9B Clef-Flash gained only +1.9 from WeightSpace alone. Cmpnd describes the package as very experimental and slow, and notes that under the original paper's stricter rule d1-omni-600M gained just +2.8 points.
Hacker News AIAI score2222 Nonna's ragù: AI skill files only get you started
Andrea Azzini argues that a shared AI skill file is like a family ragù recipe: readable and tweakable, but the value comes from your own repeated corrections over time. Drawing on a colleague who had no skill file to share and on his own work building Triagon, an agent that triages front desk requests, he says each small fix compounds and can't be copied from someone else's file. Downloaded skills are useful, he adds, but personalising your setup is a muscle trained only by iterating on your own problems.
Hacker News AIAI score3434 The Missing Ring-0 Protections for AI Agents
This essay argues that coding agents such as Claude Code, Codex CLI and Gemini CLI act with the developer's authority while access checks sit in individual tools, so a write refused by the file tool can go through the shell, and it proposes a deterministic commit-boundary supervisor that stages file, git, network and credential effects before policy approval. It reviews existing external enforcement (CaMeL, FIDES, CXI, Concordat) and sets out an unrun study with four hypotheses testing whether staged effects plus Commit Boundary add anything over those systems. Nothing described has been built, and the author states Commit Boundary is an unvalidated conceptual architecture.
Hacker News AIAI score5858 Cowork – Self-hosted task queue and dashboard for Claude, Codex, and AI agents
Cowork is an open-source control plane that connects coding agents such as Claude Code, Hermes, Gemini and Ollama into one task inbox, with fallback chains that hand work to the next agent when an API hits its rate limit. It offers a dark single-pane dashboard with host telemetry, a zero-database design storing state as plain JSON and Markdown, one-command remote worker deployment, and 285+ built-in specialist personas across 19 departments. It runs on Node.js ≥ 20 and ships as a server install script, a skill installer for agent clients, or a Docker image exposing an MCP endpoint at /mcp.
Hacker News AIAI score2222 Preventing an AI catastrophe, a brief into to analysis by synthesis
Using the 1983 Petrov nuclear false-alarm incident and the film WarGames, this post argues that AI safety discussions often conflate alignment with basic epistemics, since the Soviet satellite was not misaligned but simply had no model of the world. It revisits Ulf Grenander's Pattern Theory, which holds that pattern analysis and pattern synthesis should share a common probabilistic model, and proposes that trustworthy agentic systems should reconstruct a generative explanation of reality and compare its predictions against observed sensor readings. The post notes that end-to-end neural network training displaced Pattern Theory, and suggests that today's strong synthesis capabilities make it worth revisiting Grenander's goal of understanding.
Hacker News AIAI score3535 Today's forecast: AI behaving unpredictably
This snapshot comparison from October 26 to November 2, 2026 covers AI agent incidents, including CrowdStrike-documented campaigns targeting healthcare organizations in Argentina and VAPOR PANDA operators directing ARTEX agents against multiple targets, plus Graphika's assessment that two videos targeting a Texas Senate candidate are very likely deepfakes. Nine incidents joined the AI Incident Database in its November 2 snapshot, seven with event dates earlier than October 26. The roundup also notes a Meta Muse agent that arranged a Facebook Marketplace pickup while the seller was away and a BMW Toronto chatbot that offered a buyback price later withdrawn by a human salesperson.
Hacker News AIAI score5555 Show HN: Scatter – better way to learn new things with AI
Scatter is a source-available, browser-based app that lets you explore topics through AI-generated mind maps, where marked terms open connected explanations on an infinite canvas. It supports bring-your-own API keys for cloud providers like OpenRouter, OpenAI and Anthropic or local servers such as Ollama, and keeps projects in your browser with no app server in between. Features include interactive nodes, source-grounded answers with citations, fact-checking, image generation and editing, and Obsidian Canvas export.
Hacker News AIAI score5858 New 'Access to Justice' Benchmark: Leading AI Models Miss Critical Legal Details
Vals AI and NextLadder Ventures released the Access to Justice Benchmark on November 10, testing 23 AI models on 252 simulated legal-aid conversations, with none reaching the 80% threshold for a reliable first point of contact and top performer Alibaba's Qwen 3.8 Max scoring 76.4%. Models met 78–87% of criteria for general legal explanations but only 30–50% for identifying specific local resources, with 21 of 23 falling back on national directories in at least 70% of final answers. Free-tier models averaged 69.7% versus 70.4% for premium ones, and housing questions scored highest at 75.4% while public benefits ranked lowest at 57.3%.