ai-agents, page 8
Tested projects carrying the ai-agents 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 ai-agents
Argusic installed and ran 644 ai-agents projects on clean machines: 430 reached a running state, 179 only ran against stand-in services, 33 did not run. Last tested October 24, 2026.
Every tested ai-agents project, page 8
| subject | verdict | language | runs | last tested |
|---|---|---|---|---|
| boss-agent-cli | Runs with mocks | Python | 1 | |
| agentset | Runs with mocks | TypeScript | 2 | |
| future-agi | Runs with mocks | Python | 1 | |
| neuron-ai | Runs | PHP | 2 | |
| fusio | Runs | PHP | 2 | |
| skybridge | Runs | TypeScript | 1 | |
| TradingAgents-astock | Runs with mocks | Python | 1 | |
| antigravity-sdk-python | Runs | Python | 1 | |
| LiveAgent | Runs | TypeScript | 2 | |
| open-cowork | Runs | TypeScript | 1 | |
| harmonist | Runs | Python | 1 | |
| agency-orchestrator | Runs with mocks | TypeScript | 1 | |
| VoiceMem | Runs with mocks | Python | 1 | |
| fable-method | Runs | Python | 1 | |
| lanhu-mcp | Runs with mocks | Python | 1 | |
| Filtmall-Shopping-Skill | Runs | JavaScript | 1 | |
| mirage | Could not verify | TypeScript | 2 | |
| openscience | Could not verify | TypeScript | 2 | |
| dots | Runs with mocks | TypeScript | 1 | |
| gptme | Runs | Python | 1 | |
| linkedin-skills | Runs with mocks | Python | 1 | |
| Financial-API | Runs with mocks | TypeScript | 1 | |
| xerj | Runs | Rust | 1 | |
| atomic-agent | Runs | TypeScript | 1 | |
| yao-meta-skill | Runs | Python | 1 | |
| webcmd | Runs | TypeScript | 1 | |
| brightdata-mcp | Runs with mocks | JavaScript | 1 | |
| danghuangshang | Runs with mocks | TypeScript | 1 | |
| database-lab-engine | Runs | Go | 1 | |
| spider | Runs | Rust | 1 | |
| trustgraph | Runs with mocks | Python | 1 | |
| serenity-skill | Runs | Python | 2 | |
| hyperresearch | Runs with mocks | Python | 1 | |
| adhd | Runs with mocks | TypeScript | 1 | |
| anti-slop | Runs | JavaScript | 1 | |
| hunk | Runs | TypeScript | 1 | |
| agent-scripts | Runs | Shell | 1 | |
| opengap | Runs | TypeScript | 1 | |
| readme-ai | Runs | Python | 1 | |
| social-media-research-skills | Runs with mocks | Python | 1 | |
| agent-scan | Runs with mocks | Python | 1 | |
| skills | Runs with mocks | TypeScript | 1 | |
| browser-control | Runs | Rust | 1 | |
| MiroFlow | Runs with mocks | Python | 1 | |
| vibe-coding-prompt-template | Runs | TypeScript | 1 | |
| open-terminal | Runs | Python | 1 | |
| claude-tap | Runs | Python | 1 | |
| Raven | Runs with mocks | Python | 1 | |
| FrontierAgent | Runs with mocks | Python | 1 | |
| mattpocock-skills-zh-CN | Runs | JavaScript | 1 |
All tested projects: subjects.