Attest 1.1.0 发布：测试 AI 智能体的行为而非仅回复文本
Attest 1.1.0 是一个面向 AI 智能体的 Python 和 TypeScript 测试框架，可在 pytest 或 Vitest 中检查回复、工具调用序列和外部状态变化。
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.
#开源/仓库
Hacker News AIAI score5858 Hacker News AIAI score5858 Groma.md: Stay in control of your architecture as AI agents write code
groma.md is a free, MIT-licensed tool that scans a repository into a live C4 architecture map stored as Open Knowledge Format Markdown in Git, updating as files are saved and keeping curation across later scans. It runs locally with no account or backend, uses deterministic code analysis, calls no AI service, and can be used entirely without AI; coding agents can curate the map via the same CLI. Architecture changes are reviewed in the same pull request as the code, and an optional GitHub Action comments on PRs with change counts and a before-and-after map.
Hacker News AIFeaturedAI score7878 GitSeed – Self-hosted control plane for AI coding agents
GitSeed is an Apache-2.0, self-hosted, vendor-neutral control plane that runs coding agents such as Claude Code, Codex, Gemini, and OpenCode inside isolated three-phase containers (prepare → agent → finalize) on your own infrastructure. It adds Ed25519-signed PR Governance Receipts, parallel three-model "Second Opinions," enforced per-run spend caps via LiteLLM, and a five-stage SDLC pipeline (Ideate → Plan → Execute → Review → Merge) or Fast-Track mode, with a CLI/TUI, a 65-tool MCP server, and a Helm chart.
Why it matters: Useful for teams weighing self-hosted agent orchestration against cloud SaaS bots, since it details concrete trust boundaries, audit receipts, and spend controls.
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 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 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.
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 score1616 Show HN: Aurora GeoXAI – Sovereign geospatial AI built out of frustration
Aurora Geointelligence XAI is an experimental, CPU-first Python MVP (v0.1.0) that reads PNG, JPEG, TIFF and GeoTIFF imagery, records available raster metadata, applies scikit-learn MiniBatchKMeans to preview RGB pixels, optionally computes NDVI/NDWI from user-selected bands, and exports images with a traceable JSON report. It uses NumPy, Rasterio, Pillow, scikit-learn and Gradio, and explicitly does not use PyTorch, provide validated model-level explainability, or constitute a production or forensic system. The repository pairs the code with English and Portuguese manifestos on technological sovereignty, stating that no MLCommons benchmark, Finep/CDTI partnership, institutional endorsement or legal admissibility is claimed.
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 score3434 Show HN: Vantage-V-AI – 2-bit ternary KV-cache with attention sinks
Vantage-V-AI (v8.2.0) is an open-source, bounded-memory inference runtime that integrates with Hugging Face AutoModelForCausalLM via a one-line vantage.enable() call to cap the active attention window and retain sink tokens. It uses a 2-bit packed ternary KV-cache (4 elements per uint8 byte, 7.97x storage reduction over FP16) plus attention sinks, and reports benchmarks on 2x NVIDIA Tesla T4 GPUs with Qwen2.5-3B-Instruct, including 100.0% exact token parity between lossless and FP8 streaming modes and 0.988 average retrieval coherence from 512 to 4,096 tokens. The repository is at github.com/khoadev-vn/VANTAGE-V-AI under the MIT License.
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 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 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.
Simon WillisonAI score2222 datasette-llm 0.1a11
datasette-llm is an intermediate Datasette plugin for configuring LLMs used by other Datasette plugins. Version 0.1a11 adds support for OpenAI-compatible endpoints, allowing Datasette to use an LLM hosted anywhere that speaks the OpenAI pseudo-standard web protocol, including local models run with LM Studio, Ollama or llama.cpp (which just hit v1.0.0). The post shows running Datasette via uvx with a default_model configuration pointing at a local LM Studio endpoint to get a Datasette Agent instance powered by a local model.
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 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 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 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 Guru: An Self Evolving AI framework for Android
GURU is a free, open-source (AGPL-3.0) Android app from Unus Lumen that acts as a permission layer across 167 Android permissions with a tool registry of around 390 tools, an encrypted Rust memory engine, a bundled Unix userland, and device control via protocols including UPnP, DIAL, Wake-on-LAN, Android TV Remote, Roku ECP, Xbox SmartGlass, SNMP, IR, SSH and ADB. It routes model calls through an embedded Tor engine that fails closed, lets users bring their own cloud, local or rented-GPU model, and can write and register its own tools, skills, automations and rooms. It is a public beta distributed as a signed ~743 MB APK (Android 8.0+) outside the Play Store, with payments and the planned data marketplace not yet live.
Hacker News AIAI score7171 Show HN: Timon, an open-source AI workstation for coordinating agents
Timon is an open-source AI workstation that runs a team of agents on your own machine through the CLI subscriptions you already pay for, with an orchestrator splitting jobs into tasks handled by coder, reviewer, merger, researcher and ops roles. Each task runs in its own git worktree and is reviewed by a second model before merging, and agents ask for permission before pushing, publishing or deleting anything. It runs as a background daemon on Windows, macOS and Linux with desktop, browser, phone, Telegram and CLI clients, and is licensed under the GNU AGPL v3.
MarkTechPostAI score5959 Stanford Research Open-Sources Memorilla, a Latent Memory Module for Frozen LLMs
Stanford researchers have released Memorilla, an open-source 194M-parameter memory module that condenses a whole document collection into 16 memory tokens for a frozen LLM, with code, training recipes and checkpoints public under Apache 2.0. On FactKG, a frozen Qwen3-8B scored 84.33% with Memorilla versus 80.43% for full context, using 108x fewer document tokens, and it reported the highest average (49.68) across 8 benchmarks while losing on PubMedQA (59.00% vs 69.00% for LLMLingua-2). The quickstart requires one 80 GB CUDA GPU, and the full training recipe takes about 19 hours on 4 H100 GPUs.
The DecoderAI score6565 Runway's open-source Praxis-1 turns video AI into a robot controller
Runway has released Praxis-1, a World Action Model that takes camera images, text instructions and robot position data to predict scene changes and derive robot movements, with weights and code under the Apache 2.0 license. Built on a video model fine-tuned with human action videos and robot data, it scored 46.2 percent on Nvidia's RoboLab-120 leaderboard, ahead of FLUX 3 Action at 42.9 percent, though Runway ran the tests itself and they have not been independently verified. The model still needs specialized robot data for adaptation, sometimes confuses similar-looking objects, and cannot reliably plan complex action sequences on its own.
Hacker News AIAI score5858 Show HN: Gamma PDF – AI-native PDF reader, self-hosted
Gamma PDF is an open-source, self-hosted PDF annotator with outliner notes, live Markdown and LaTeX, and an AI that answers questions about papers with cited answers using your own Anthropic or OpenAI key or a paid ChatGPT plan. It runs on Windows, macOS, Linux, iPad, Android and Docker, stores data as SQLite and files in one folder with no account or telemetry, and supports shared workspaces, Zotero/Obsidian/Logseq/Notion imports, and read-only MCP access for Codex and Claude Code.
MarkTechPostAI score6464 Vercel Releases UI SDK: 50+ UI Behaviors for AI Coding Agents
Vercel Labs has released UI SDK, an open-source beta headless library of 50+ interface behaviors that coding agents assemble into accessible components for React, Vue, Svelte, Solid and Web Components. It ships as 6 npm packages at 0.1.0-beta.1 under Apache-2.0, with a createAgent() bridge letting agents snapshot UI state and act on it; Vercel's self-reported benchmark on one task showed 69% fewer tool calls, 61% faster time and 56% lower cost versus browser tools.
Hacker News AIAI score5858 ShieldFont – Protect human muffins by poisoning unauthorized AI starfish
ShieldFont is an open-source tool that swaps content words in a page's HTML source for other real, same-grammar-class words, so humans see the original text via a custom font while scrapers collect altered meaning. Built with Danish type foundry Playtype as ShieldFont Optik, it ships with three ~12,000-pair English dictionaries and supports bringing your own font or mapping. The project reports that swapping about 25% of words caused 50% of 1,500 test passages to lose their original factual claim, and that roughly one in ten shielded chunks still passed the FineWeb-Edu quality filter.
Hacker News AIAI score3434 Transforming Ripgrep's Documentation with AI Automation and MkDocs
The author describes a third-generation documentation automation workflow that expanded ripgrep's two documentation files into 55 pages, using automatic page splitting, per-page visual enhancement, and Mermaid diagram validation via a new tool called mermaid-sonar. The workflow runs on MkDocs Material and adds 87 Mermaid diagrams, 358 admonitions, and 180+ code annotations, with a strict build passing. The post also compares the workflow to earlier mdBook-based versions and outlines steps for adapting it to other projects.
Hacker News AIAI score5858 Show HN: Browserr – An MCP-first browser for AI agents (one Rust binary)
Browserr is an MCP-first browser for AI agents built on the Servo engine, distributed as a single ~120 MB Rust binary with a 22-command JSON-over-loopback protocol and 42 MCP tools. It emphasizes agent-first design—structured extraction, stable refs, fail-closed interception, built-in adblock, and evidence logging—plus human handoff via a native window with headed:true. It is free and open source, with packages for Windows x64, Linux x64/ARM64, and macOS Apple Silicon, requiring Python 3.10+ for the SDK and MCP server.
Hacker News AIAI score6262 Show HN: Open-Source Version of Cyclon: Phone where AI is the interface?
OpenCyclone is a free, open-source AI agent for stock Android that reads your apps on a hidden display, decides what to tap, and asks for approval before any irreversible action. It requires Android 12 or later, a one-time setup script on a computer, and a model provider account, and is built and tested on a Pixel 7. The project is Apache-2.0 licensed, unaffiliated with Cyclon or Y Combinator, and its benchmark results are not yet published.
Hacker News AIAI score4242 Doc-foundry – AI writes Security detection rules, then proves they work
Doc-foundry is an adversarial multi-agent detection-engineering workflow (LangGraph, Pydantic, FastMCP, Claude) that turns a threat such as a CVE, CISA KEV entry, incident writeup or ATT&CK technique into a validated first-version Sigma detection rule, a threat report with round-by-round convergence history, and a proof bundle containing a positive corpus, benign baseline, adversarial mutation set and a computed coverage label (real-coverage/brittle/broken) with FP/FN numbers and a reproducibility hash. Four LLM agents (Threat Analyst, Blue Detection Engineer, Telemetry, Red-Team Adversary) propose, while a deterministic referee handles FP/FN evaluation, adversarial evasion, the coverage verdict, red-team verification and the deployment gate, so the same input yields the same verdict and hash. A second pipeline, the Review Chain, runs draft → Red Team → revision → SOC Lead → final rule and produces a reviewed but explicitly unvalidated rule with the full trail of findings that shaped it.
Hacker News AIAI score6060 QuAIA: An open-source team of AI agents that handles the whole test process
QuAIA (Quality Assurance with Intelligent Agents) is an open-source multi-agent system under AGPL-3.0 in which an orchestrator coordinates specialized agents for requirements review, test design, UI and API test execution, and defect reporting, connected to tools like Jira, Confluence, and Zephyr via the A2A and MCP standards. The UI agent operates keyboard and mouse from the screen without test scripts, runs on multilingual models, and learns workflows from expert demonstration, with self-hosted models and in-infrastructure deployment supported. Several features, including agent memory, self-hosted model support, and desktop support, are marked as prototypes.
AWS Machine Learning BlogAI score3838 Route coding agent requests to the right model on Amazon Bedrock with NVIDIA NeMo Switchyard
This AWS sample deploys LiteLLM with the open source NVIDIA NeMo Switchyard routing plugin on Amazon ECS Fargate via AWS CDK, so coding agents can send requests to a model group that Switchyard routes between a capable and an efficient model on Amazon Bedrock. It covers Stage routing (which reads recent tool activity and results to pick between two candidates) and Random routing (weighted traffic splits for A/B tests), plus a benchmark runner that measures cost per solved task against single-model baselines. The post notes the sample uses switchyard-server 0.3.0 and LiteLLM v1.102.0, is for non-production use, and that its configuration and APIs may change between releases.
Codex ReleasesAI score1212 0.171.0-alpha.5
This GitHub Changelog entry is titled "0.171.0-alpha.5" and lists only the site's navigation menu, covering Platform, Copilot, Actions, Code Quality, Codespaces, Secure Code, Secret Protection, Build with Copilot, Integrations, Changelog, Add-ons, and Pricing. The material contains no details about the release itself.
Cloudflare BlogFeaturedAI score7171 Kitesurf is now open source
Cloudflare has open-sourced Kitesurf, its stateless browser for AI agents that runs entirely on Workers, under the Apache 2.0 license on GitHub. The repository includes the engine, PageScript, PageRenderer, and CLI, built on Rust-to-WebAssembly projects like Blitz, Stylo, Boa, and Linebender libraries, and supports the Chrome DevTools Protocol for clients such as Puppeteer. Developers can run it locally or deploy their own instance to Cloudflare Workers, which requires a Workers Paid plan because it uses Dynamic Workers.
Why it matters: Useful for developers who want to self-host a lightweight agent-oriented browser engine and inspect or contribute to its open-source components.
Hacker News AIAI score4040 Show HN: AI Juggler – Orchestrate your desktop Claude and Codex apps
AI Juggler is a free, open-source (MIT), local-first macOS app that shows which AI coding sessions are open across the Claude app, terminals, the Codex app and Cursor, lets you jump to any of them in one step, and reports usage and limits per account. It works with tools you already use, never proxies their traffic, never signs in for you and never stores your credentials, and it requires macOS 14 Sonoma or later plus at least one of Claude Code or Codex installed and signed in.
MarkTechPostAI score5858 Perplexity Releases Decider v1.3: Open-Weight Decision Models Add Locate
Perplexity released pplx-decider-v1.3 and pplx-decider-flash-v1.3, open-weight decision models that return probabilities for yes/no, multiple-choice and score questions rather than generated text, with weights under Apache 2.0 on Hugging Face and availability in the Perplexity Decisions API and on OpenRouter. The main addition is Locate, which extracts exact text spans by type or instruction for NER, PII detection and extractive QA. Perplexity reports 91.6% mean accuracy on 63 query-classification tasks and a 0.27% answer-flip rate, with all figures self-reported.
Meta EngineeringAI score3939 Cuttlefish on Mac: Running Android’s Virtual Device Framework Natively on Apple Silicon
Meta describes porting AOSP's Cuttlefish virtual-device framework to run natively on Apple silicon Macs, reviving QEMU support and making vhost-user buildable on macOS, increasing QEMU's HVF memory-region tracking slots, and adding a native Cocoa display plus code-signing and notarization paths. The unified platform replaces the previous split between Goldfish and Cuttlefish, cutting maintenance and infrastructure overhead and letting developers and CI use the same high-fidelity virtual devices. Meta is releasing a QEMU fork (qemu-wearables) and Cuttlefish patch set (cuttlefish-wearables) and is exploring upstreaming the changes.
Hacker News AIAI score5858 Show HN: Langfuse AI Gateway, open source rust gateway to trace every LLM call
Langfuse AI Gateway is a standalone Rust gateway that exposes OpenAI and Anthropic native APIs under /openai/v1 and /anthropic/v1 namespaces, relaying provider JSON or SSE without rewriting bytes while capturing each finalized generation and uploading it to Langfuse via OTLP. It resolves gateway keys to trusted provider connections through Web, adds request IDs and trace/observation IDs to responses, and emits operational OpenTelemetry traces and metrics. Configuration is environment-based, with pnpm dev or cargo run for local use and no real provider credentials needed for building and testing.
Hacker News AIAI score2020 Nil-3B Open Source Sovereign AI
This repository hosts the nil-3b-q4_k_m.gguf file for running the NIL-3B project locally with a GGUF-compatible inference runtime, via a chat script that expects the file in the project root. It also documents an uploader script that uses a Hugging Face token and repo ID from a .env file to create the model repository if needed and upload the GGUF file. The root LICENSE covers only the project source code and does not by itself confirm license or redistribution rights for the model weights or training data.