No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by nossa-y · MCP Server · ★ 541
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is activity-frames safe to install? View the security audit →
activity-frames Download the desktop app - Nocta uses activity-frames to watch how you work and brief you daily on what needs your attention. 100% local. Episodic memory for AI agents. Your agent can read your code, search the web, and call APIs - but it has no idea what you have been doing for the last 8 hours. It starts every conversation blind. activity-frames gives your agent eyes. It records your screen locally, compiles what it sees into structure
| Stars | 541 |
| Forks | 36 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 67.1985392652909/100 |
| Open Issues | 27 |
| Last Updated | 2026-08-26 |
| Created | 2026-07-04 |
| Platforms | mcp, python |
| Est. Tokens | ~15k |
These tools work well together with activity-frames for enhanced workflows:
Looking for a activity-frames alternative? If you're comparing activity-frames with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Self improving agents through iterations
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory,
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antig
Explore other popular mcp server tools:
activity-frames is Turn your workday into structured workflows agents can execute. 100% local, served over MCP.. It is categorized as a MCP Server with 541 GitHub stars.
activity-frames is primarily written in Python. It covers topics such as agent-memory, ai-agents, computer-use.
You can find installation instructions and usage details in the activity-frames GitHub repository at github.com/nossa-y/activity-frames. The project has 541 stars and 36 forks, indicating an active community.
activity-frames is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to activity-frames on Agent Skills Hub include altk-evolve, agentic-context-engine, m_flow. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: