Argusic

Argusic tests whether real software actually runs 👋 Every developer knows this moment. The README says "just npm install". Two hours later you're deep in dependency conflicts, missing env vars and a model that needs a GPU nobody mentioned. Argusic exists to answer one question with evidence: Does it actually run? 🤖 What Argusic does AI agents take real software (open source repos and Hugging Face models) and install, launch and debug it exactly like a new engineer on day one. Clean, single-use machine. Pinned commit. No human help. 📊 So far: 3,163 projects tested, every run recorded. 🔍 How it works 1️⃣ Every project is pinned to an exact commit 2️⃣ An agent gets one mission on a disposable machine: Make it work 3️⃣ A failure earns a second attempt 4️⃣ Two failures settle "could not verify". Never "broken". We don't blame code we couldn't run. 🧮 How we score (out of 100) Install 30, launch or tests 30, error recovery 20, verification depth 20. A deterministic program does the scoring. No AI model grades anything, ever. "Verified" means the agent proved the output works, not just that a process started. 🧾 Proof over opinion Every published number links to its full log and terminal recording. Nothing on Argusic is a review, and no one can pay to change a result. Doubt a verdict? Open the log and check it yourself. 🔬 Methodology: Full rules, scoring and changelog argusic.com/methodology 🏆 Best software, tested: Databases, CMS, AI agent frameworks and more, ranked by whether they actually install and launch argusic.com/best 📰 Reports: Daily and weekly summaries of what ran, what failed and what it cost argusic.com/reports 🖥️ Servers: 333 GPU cloud and VPS offers from 114 providers, with verified prices and measured spin-up times argusic.com/servers 💻 Hardware: 1,300+ laptops, desktops and mini PCs for programming and AI, with estimates of which local models each can run argusic.com/hardware 🧪 Maintainer or builder? Request a test for your repo argusic.com/request 📂 Open data, free under CC BY 4.0, updated daily. Use it, cite it, build on it: 🐙 GitHub: Every verdict, score and pinned environment github.com/argusic/does-it-r… 🤗 Hugging Face: Load the dataset straight into your notebook huggingface.co/datasets/argu… 📺 Every run on video youtube.com/@argusiccom 🤝 Follow along We build Argusic in public. Follow for daily verdicts, new reports and the occasional install that fights back. Reply with a repo you want us to test next 👇 #Argusic

Vibe_coding_guide: 中文优先的 Vibe Coding / AI coding engineering workflow guide: specs, agents, worktrees, skills, CI, and review. Lling0000/Vibe_coding_guide · JavaScript · MIT · 242 stars Vibe_coding_guide tested: 4 errors, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 5fea8fc. Whole session: 6 min Errors met: 4, fixed without help: 4 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "The static tutorial site installs with zero dependencies, serves HTTP 200 on python3 -m http.server 4173, and works in real headless Chrome: schedule/day navigation, checklist progress persisted in localStorage, and reader mode rendering the markdown course; its only 404 is the optional favicon.ico." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #VibeCodingGuide #AgentWorkflows #AgenticEngineering #AiAgents #AiAssistedDevelopment #AiCoding #Bilingual #Argusic

code-input: code-input.js: An editable <textarea> that supports any syntax highlighting algorithm, for code or something else. WebCoder49/code-input · JavaScript · MIT · 240 stars code-input tested: 3 errors, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit eaee428. Install to first launch: 1 min Whole session: 4 min Errors met: 3, fixed without help: 3 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "Fresh install builds (npm install, npm run prepack exit 0) and both browser-based automated test suites pass fully: prism.html 107/107 and hljs.html 96/96 assertions, each page answering HTTP 200, observed in headless Chromium under Xvfb DISPLAY." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #CodeInput #CodeEditor #Editor #Javascript #Modular #Textarea #JavaScript #Argusic

release-downloader: Github action to download release assets from private or public repositories. robinraju/release-downloader · TypeScript · MIT · 242 stars release-downloader tested: 1 error, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 64affec. Install to first launch: 1 min Whole session: 3 min Errors met: 1, fixed without help: 1 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "The release-downloader GitHub Action installs, builds, and passes all 48 tests across 6 test suites on Node.js v18.19.1, with code bundled into dist/index.js via rollup." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #ReleaseDownloader #CiCd #Downloader #GithubActions #Release #ReleaseAutomation #TypeScript #Argusic

Misaka-Agent: A multi-agent research system for the humanities and social sciences. Luciole-Studio/Misaka-Agent · Python · Apache-2.0 · 235 stars Misaka-Agent tested: 3 errors, 2 fixed alone, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 3bcf7a3. Install to first launch: 1 min Whole session: 22 min Errors met: 3, fixed without help: 2 Argusic Score: 93.33/100 Depth: checked against the real service The agent's own closing words: "MISAKA 0.18.11 installs and launches: --version prints 0.18.11, init creates a git project, the panel opens the setup wizard with fd and pdftotext present from the bundled archive, dm runs real turns that reply, and the test suite passes 4361 tests (the single remaining failure needs the optional ocrmypdf system package, which is absent without root)." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #MisakaAgent #AgentFramework #AiAgents #ComputationalSocialScience #DigitalHumanities #History #Humanities #Argusic

env-ci: Get environment variables exposed by CI services. semantic-release/env-ci · JavaScript · MIT · 242 stars env-ci tested: 2 errors, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 4df63c6. Install to first launch: 1 min Whole session: 2 min Errors met: 2, fixed without help: 2 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "All 113 tests pass under Node 24. Lint passes. Coverage 99.6% statements. The library correctly detects CI services from environment variables." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #EnvCi #Appveyor #Bamboo #Bitbucket #Bitrise #Buddy #Buildkite #Argusic

Albatross: Open source, terminal-first AI coding agent with fully transparent multi-model routing. morganlinton/Albatross · Rust · MIT · 242 stars Albatross tested: 3 errors, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit e458e42. Install to first launch: 15 min Whole session: 18 min Errors met: 3, fixed without help: 3 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "Albatross 2.5.0 builds from source, passes all 712 unit tests, passes cargo fmt and clippy -D warnings, and can run a one-shot prompt against an Ollama-compatible API returning SSE streaming chunks." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #Albatross #AiCodingAgent #AiCodingAssistant #Cli #CodingAgent #DeveloperTools #Harness #Argusic

tagref: Manage cross-references in your code. stepchowfun/tagref · Rust · MIT · 242 stars tagref tested: 1 error, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 4894b87. Whole session: 2 min Errors met: 1, fixed without help: 1 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "Tagref 1.14.0 installed and verified: prebuilt binary and source build both run, its 29-test suite passes, and it validates real tag/group/reference fixtures with correct exit codes on both passing and failing cases." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #Tagref #ContinuousIntegration #CrossReference #CrossReferences #CrossReferencing #Linter #Rust #Argusic

ai-fomo-skills: Personal superalignment skills for turning AI information overload into reusable knowledge, signals, and digests. vincelele/ai-fomo-skills · Python · MIT · 246 stars ai-fomo-skills tested: nothing broke, ran first time in 4 minutes. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 2401c6e. Install to first launch: 4 min Whole session: 21 min Errors met: 0, fixed without help: 0 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "The 3 skill directories are installed in ~/.codex/skills. The import_source.py script handles 6 source types: official-page, rss, github-repo, github-trending (all work without credentials), x-user (requires X_BEARER_TOKEN), and xiaoyuzhou-episode (scrapes public episode page). The xiaoyuzhou_account.py script provides bridge management, SMS login, inbox import, comments, and DashScope transcription but requires a Go bridge and optionally DashScope API key." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #AiFomoSkills #Ai #Codex #KnowledgeManagement #PersonalAi #Skills #Python #Argusic

act: Run your GitHub Actions locally 🚀. nektos/act · Go · MIT · 72,475 stars act tested: it runs, but only against stand-in services, never the real thing. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit a34fa0c. Install to first launch: 11 min Whole session: 23 min Errors met: 4, fixed without help: 4 Argusic Score: 92/100 Depth: checked against stand-in services only The agent's own closing words: "act binary v0.2.89 (commit a34fa0c) builds and installs; non-Docker unit tests (9 packages) pass; lint clean; workflow dry-run and WITHOUT_DOCKER (host-execution) mode verified working; Docker-dependent features (container runner, artifact server, CLI integration tests) are unavailable because the Docker daemon cannot be started in this unprivileged container" The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #Act #Ci #Devops #GithubActions #Golang #Go #GitHub #Argusic

pyvesync: pyvesync is a python library to manage Etekcity & Levoit smart devices. webdjoe/pyvesync · Python · MIT · 247 stars pyvesync tested: it runs, but only against stand-in services, never the real thing. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 58eee3b. Install to first launch: 3 min Whole session: 8 min Errors met: 5, fixed without help: 5 Argusic Score: 92/100 Depth: checked against stand-in services only The agent's own closing words: "In the .venv, pyvesync 3.4.2 installs editable and its pytest suite passes 380/3; a real library run against a local schema-correct mock of the VeSync API logs in, retrieves devices, instantiates VeSyncOutlet15A, and turns it on and off." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #Pyvesync #SmartHome #Smarthome #Python #GitHub #Argusic

visualize_ruby: Transform code into a flowchart and experimentally trace the execution path through it. zeisler/visualize_ruby · Ruby · MIT · 252 stars visualize_ruby tested: 3 errors, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 5ecdd2b. Whole session: 5 min Errors met: 3, fixed without help: 3 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "Inside the container, Ruby 3.4.8 and Graphviz live in a userspace conda env, bundle install completes, the full RSpec suite passes with 103 examples and 0 failures, and both README example scripts generate real decodable PNG flowcharts." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #VisualizeRuby #Diagram #ExecutionGraph #Flowcharts #Graphs #Graphviz #Ruby #Argusic

iva-agent: AI assistant in Telegram that remembers everything and helps you run your life. smixs/iva-agent · TypeScript · MIT · 274 stars iva-agent tested: 10 errors, 7 fixed alone, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit b2cabff. Install to first launch: 35 min Whole session: 64 min Errors met: 10, fixed without help: 7 Argusic Score: 94/100 Depth: checked against the real service The agent's own closing words: "Iva v0.4.8 dependencies installed and CLI launches (bin/iva.mjs --help shows all commands); test suite runs at 3646/3649 passing, with three pre-existing test-environment failures: OverlayFS container metadata edge case, EPIPE on Claude subprocess mock pipe, and cross-test module cache pollution in card-store resolver" The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #IvaAgent #Agent #AiAgent #AiAssistant #KnowledgeGraph #Llm #LocalFirst #Argusic

🚨 Apple just dropped its biggest MacBook Pro redesign in years. Meet MacBook Pro with PROLED XDR Display, and yes, it's the first Mac with a touchscreen. 🖥️ Tandem OLED: Up to 2000 nits peak HDR and SDR, 10,000,000:1 contrast 🎨 P3 + Adobe RGB, 80%+ Rec. 2020 coverage 👆 Touch on Mac for the first time 🏝️ Dynamic Island comes to Mac ⚡ M5 Pro or M5 Max, up to 128GB memory and 16TB storage 🔋 Up to 24 hours of battery life 🪶 Just 3 lb (14") and 4 lb (16") 💰 Starts at $2,899 (14") and $3,399 (16") 📅 Pre-order now, ships Nov 6 📰 Source: apple.com/newsroom/2026/10/a… 🔍 Specs: apple.com/macbook-pro/proled… We'll be updating our full breakdown soon, stay tuned 👉 argusic.com/hardware #Apple #MacBookPro #OLED

vector-graph-rag: Graph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios. zilliztech/vector-graph-rag · Python · MIT · 262 stars vector-graph-rag tested: it runs, but only against stand-in services, never the real thing. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 656bdf2. Install to first launch: 1 min Whole session: 12 min Errors met: 0, fixed without help: 0 Argusic Score: 92/100 Depth: checked against stand-in services only The agent's own closing words: "The full test suite (143 tests across 11 files) passes cleanly and the FastAPI server starts and responds correctly on /health." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #VectorGraphRag #GraphRag #Graphrag #Jev #KnowledgeBase #KnowledgeGraph #Milvus #Argusic

notion-electron: Notion Desktop Client for Linux. anechunaev/notion-electron · TypeScript · MIT · 264 stars notion-electron tested: 3 errors, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 92918eb. Install to first launch: 7 min Whole session: 7 min Errors met: 3, fixed without help: 3 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "The repository installs (npm install), builds (npm run build emits complete main/preload/renderer output), typechecks (tsc --noEmit passes all three tsconfigs), lints (ESLint + Prettier pass), and the Electron application launches and runs persistently on a virtual X display (state S, killed by timeout after 20s) with only expected container-related D-Bus warnings." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #NotionElectron #Electron #Javascript #Nodejs #Notion #Office #Productivity #Argusic

client: Tetiva — desktop API client for HTTP, gRPC, GraphQL and WebSocket (Wails v3 + Vue 3). tetiva-app/client · Go · MIT · 267 stars client tested: 4 errors, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 3eb9e14. Install to first launch: 12 min Whole session: 16 min Errors met: 4, fixed without help: 4 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "Server binary builds and serves HTTP 200 on port 9246; 38 Go test packages pass (36 ok, 2 no test files); frontend dist embedded and served correctly" The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #Client #ApiClient #DesktopApp #DeveloperTools #Go #Golang #Graphql #Argusic

animaworks: Organization-as-Code for autonomous AI agents. xuiltul/animaworks · Python · Apache-2.0 · 268 stars animaworks tested: 5 errors, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit f700ff9. Install to first launch: 8 min Whole session: 44 min Errors met: 5, fixed without help: 5 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "17092 unit tests pass; CLI prints full help; demo server binds port 18501 with Uvicorn; all 5 pre-existing test failures fixed via IPv6 loopback detection, zstd Python fallback, and Node 18 ESM compatibility." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #Animaworks #AgentFramework #AiAgents #AutonomousAgents #BrainInspired #Claude #Forgetting #Argusic

heimdall: A cloud native Identity Aware Proxy and Access Control Decision service. dadrus/heimdall · Go · Apache-2.0 · 260 stars heimdall tested: 2 errors, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 4e12733. Install to first launch: 4 min Whole session: 32 min Errors met: 2, fixed without help: 2 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "Heimdall builds from source, the binary starts in decision mode listening on configured ports, the management API responds HTTP 200 on /.well-known/health and /.well-known/jwks, and all 101 Go test packages pass with serial execution to avoid the container's inotify instance limit." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #Heimdall #AccessControl #AccessManagement #ApiGateway #AuthApi #AuthProxy #Authentication #Argusic

LinkBreeze: The self-hosted Linktree alternative. OmniRise/LinkBreeze · TypeScript · MIT · 260 stars LinkBreeze tested: 5 errors, no human help, still ran. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit c41555a. Install to first launch: 26 min Whole session: 31 min Errors met: 5, fixed without help: 5 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "LinkBreeze 1.4.1 builds from source, passes all 1064 unit tests, and serves the setup page on port 3344 with health endpoint responding 200." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #LinkBreeze #Analytics #CreatorTool #Docker #DockerImage #LinkInBio #LinkInBioPage #Argusic

workflow: The type-safe, event-driven workflow orchestration library that scales with your business. luno/workflow · Go · BSD-3-Clause · 264 stars workflow tested: nothing broke, ran first time in 2 minutes. It was installed and run by an Argusic agent on a clean machine, with no human help, from the repository pinned at commit 13d66ce. Install to first launch: 2 min Whole session: 4 min Errors met: 0, fixed without help: 0 Argusic Score: 100/100 Depth: checked against the real service The agent's own closing words: "The repository builds from source with Go 1.26.10, all internal unit tests pass (14 packages, 0 failures), and three in-memory example workflows (gettingstarted, callback, timeout, schedule, connector) execute end-to-end successfully. The embedded Web UI server starts, serves the homepage, and responds to all 3 API endpoints." The whole session is in this video, unedited, at the speed it actually happened. Every number above is read from that run's own log. Follow for a new repository put through this every day. #Workflow #Durable #Eda #Eventdrivenarchitecture #Go #Golang #Hacktoberfest #Argusic