--- title: "Your Next Dependency Is an Agent" newsletter: "MLOps Community" date: 2026-07-16 source: https://aaif.live/newsletters/mlopscommunity/2026-07-16-your-next-dependency-is-an-agent --- # Your Next Dependency Is an Agent *Plus MCP design, serving runtimes, and agent health* *MLOps Community — Agentic AI Foundation, 2026-07-16* Lots of you replied last week with the AI buzzword you’re hearing most so you’re ready when this newsletter starts coming from demetrios@aaif.live as part of the move to the Agentic AI Foundation. If you haven’t replied yet, hit reply and send us yours. See if you can get it to the top the leaderboard [http://aaif.live/resources/downtime/ai-buzzword-leaderboard]. ## Commitment Issues Most agent-built internal tools should be disposable by default. Maintain or Regenerate? [MAINTAIN](https://go.mlops.community/NL_HT1_Jul16) [REGENERATE](https://go.mlops.community/NL_HT1_Jul16) ## No Reminder Needed We’ll remember not to ask twice when it’s this clear you’re choosing memory over long context for agents. ## Curated finds to help you stay ahead ## What 116 Agentic AI Projects Reveal ## Agentic AI Momentum Report The open-source agent stack is attracting contributors and adoption quickly, but popularity does not show whether a project is secure, responsive, or structurally resilient. AAIF’s new Momentum Report compares 116 projects across five layers using adoption, development health, maintainer activity, vulnerabilities, governance, and contributor concentration. Frameworks and infrastructure lead adoption with 1.5 million GitHub stars and 226,000 forks. Agent applications tell a different story: they attract the most active contributors and resolve issues in roughly two weeks, with pull requests merged in about two days. Security presents a less encouraging picture. Unpatched CVEs across the projects rose 2.6x between December 2025 and June 2026, reaching around 9,200. Framework and infrastructure projects account for nearly half of them. The governance data also separates formal processes from genuine contributor diversity. Some projects meet OpenSSF governance checks but remain controlled by one organization, while others have broader participation but weaker documentation. Read the report and compare individual projects. [https://aaif.io/report/agentic-ai-momentum-report/] ## JOB OF THE WEEK ## Developers May Stop Depending on Libraries Models can now run 80 to 100 tool-call loops, while one compact tool can expose a huge capability surface without flooding the context window. * RL has improved how agents chain actions, navigate environments, and use minimal tool interfaces. * Small MCP surfaces can generate code, query large hubs, and return results without replaying everything through the model. * MCP apps can place rich results directly in the UI, reducing token waste. The design question is shifting from tool count to how efficiently each tool expands what an agent can do. [https://podcasts.apple.com/us/podcast/developers-may-stop-depending-on-libraries/id1505372978?i=1000775640153](https://podcasts.apple.com/us/podcast/developers-may-stop-depending-on-libraries/id1505372978?i=1000775640153) [https://home.mlops.community/public/videos/developers-may-stop-depending-on-libraries](https://home.mlops.community/public/videos/developers-may-stop-depending-on-libraries) [https://open.spotify.com/episode/7rXqiBVdG4ShsbCzg9pVfB?si=Wz9kXo-fQkuRVVQnzRQyiA](https://open.spotify.com/episode/7rXqiBVdG4ShsbCzg9pVfB?si=Wz9kXo-fQkuRVVQnzRQyiA) ## 10 Cities. 4 Countries. One Unexpected MCP Lesson. An MCP server can take seven lines of Python, but each exposed tool consumes context and creates another surface to secure. * MCP does not make an API intelligent. It gives an LLM a structured way to select and call functions. * Strong designs expose a small set of common actions, with clear annotations, validation, authorization, and limits on costly requests. The practical lesson is to treat MCP as a controlled interface for model-driven API use, not a layer of magic. [https://podcasts.apple.com/us/podcast/10-cities-4-countries-one-unexpected-mcp-lesson/id1505372978?i=1000775639902](https://podcasts.apple.com/us/podcast/10-cities-4-countries-one-unexpected-mcp-lesson/id1505372978?i=1000775639902) [https://home.mlops.community/home/videos/10-cities-4-countries-one-unexpected-mcp-lesson](https://home.mlops.community/home/videos/10-cities-4-countries-one-unexpected-mcp-lesson) [https://open.spotify.com/episode/4A4Imp2s1r0x4LHrxWPINR?si=8NMLa0mESJWpZBF1a_L8Jg](https://open.spotify.com/episode/4A4Imp2s1r0x4LHrxWPINR?si=8NMLa0mESJWpZBF1a_L8Jg) ## Best Model Serving Runtimes To Build Optimized ML APIs A Flask container can become an expensive bottleneck once inference traffic rises and latency starts to matter. This guide compares four production serving options. * TensorFlow Serving and TorchServe suit teams committed to one framework. * BentoML favors Python flexibility, broader compatibility, and simpler implementation. * Triton offers stronger GPU utilization and optimization, with considerably more operational complexity. The right choice depends on whether your priority is development speed, framework support, or squeezing more predictions from each machine. [Read the blog](https://mlops.community/blog/best-model-serving-runtimes-to-build-optimized-ml-apis) ## IN-PERSON EVENTS * Munich [https://luma.com/5ckfr8dm] - July 23 * San Francisco, Voice Agents Forum [https://luma.com/voiceagentssf] - September 16 ## VIRTUAL EVENTS * Coding Agents Lunch & Learn Session [https://home.mlops.community/home/events/coding-agents-lunch-and-learn-session-19-understanding-mcp-pjzpzu8dwt?agenda_day=6a5500e8d641d60d89f008bd&agenda_track=6a5500e9d641d60d89f008d4&agenda_stage=6a5500e8d641d60d89f008c3&agenda_filter_view=stage&agenda_view=list] - July 17 * A Discussion on Loop Engineering [https://home.mlops.community/home/events/a-discussion-on-loop-engineering-me6r7t97sh?agenda_day=6a44eb367234763b95523e18&agenda_track=6a44eb377234763b95523e4a&agenda_stage=6a44eb367234763b95523e1c&agenda_filter_view=stage&agenda_view=list] - July 21 ## Speak for Yourself --- Source: https://aaif.live/newsletters/mlopscommunity/2026-07-16-your-next-dependency-is-an-agent