agentic-ai
Tested projects carrying the agentic-ai topic, with their current verdicts. Topics come from each project's own metadata and Argusic's pool tags. Spellings of the same topic are gathered here under one name, so this page holds every project tagged any of them.
Measured by Argusic on a fresh machine every time. Every number links to its evidence.
What Argusic measured in agentic-ai
Argusic installed and ran 97 agentic-ai projects on clean machines: 62 reached a running state, 30 only ran against stand-in services, 5 did not run. Last tested October 23, 2026.
Every tested agentic-ai project
| subject | verdict | language | runs | last tested |
|---|---|---|---|---|
| kelos | Runs | Go | 1 | |
| pydantic-ai-skills | Runs | Python | 1 | |
| wmux | Runs | TypeScript | 1 | |
| apm-studio | Runs | TypeScript | 1 | |
| sno-station-skills | Runs with mocks | Shell | 1 | |
| Flowtrace | Runs | TypeScript | 1 | |
| watch-skill | Could not verify | Python | 2 | |
| vibe-check-mcp-server | Runs | TypeScript | 1 | |
| unbody | Could not verify | TypeScript | 2 | |
| giselle | Runs with mocks | TypeScript | 1 | |
| Adrian | Runs | Python | 1 | |
| agents-universe | Runs with mocks | Python | 1 | |
| smythos-studio | Runs | TypeScript | 1 | |
| sqz | Runs | Rust | 1 | |
| trinity | Could not verify | Python | 2 | |
| cli | Runs with mocks | TypeScript | 1 | |
| second-brain | Runs | Python | 1 | |
| agentos | Runs | TypeScript | 1 | |
| RAGLight | Runs | Python | 1 | |
| awesome-agent-apis | Runs with mocks | Python | 1 | |
| code-on-incus | Runs with mocks | Go | 1 | |
| coi | Runs with mocks | Go | 1 | |
| cuga-agent | Runs with mocks | Python | 1 | |
| os | Runs with mocks | TypeScript | 1 | |
| semantix | Runs | Go | 1 | |
| mcp-client-for-ollama | Runs with mocks | Python | 1 | |
| projectmem | Runs | Python | 1 | |
| Foundry | Runs | Python | 1 | |
| unifi-mcp | Runs with mocks | Python | 1 | |
| ClawBench | Runs with mocks | Python | 1 | |
| mariadb-operator | Runs | Go | 1 | |
| SWE-AF | Runs with mocks | Go | 2 | |
| CORAL | Runs | Python | 1 | |
| innovation-lab-examples | Runs | Python | 1 | |
| ctx | Runs | Rust | 1 | |
| tuui | Runs | TypeScript | 1 | |
| aws-agent-skills | Runs | Python | 1 | |
| free4chat | Runs | TypeScript | 1 | |
| unigit-ecosystem | Runs | JavaScript | 1 | |
| awesome-muse-connectors | Runs with mocks | Python | 1 | |
| commonly | Runs | TypeScript | 1 | |
| invisible_dots | Runs | TypeScript | 1 | |
| llm-wiki | Runs | Python | 1 | |
| ouroboros | Runs | Python | 1 | |
| app-platform | Runs with mocks | Java | 1 | |
| OpenContracts | Runs | Python | 1 | |
| devops-ai-guidelines | Runs with mocks | Python | 1 | |
| pstack-claude | Runs | JavaScript | 1 | |
| Agentlas-OS | Runs | Python | 2 | |
| docs-mcp-server | Runs | TypeScript | 1 |
All tested projects: subjects.