MCP App StoreLe meilleur de l'écosystème IA et MCP, sélectionné chaque jour.
Sources
Cursor's Bugbot can now learn from live PR feedback, turning code review signals into persistent rules that improve future suggestions. This makes automated code-review tooling progressively more accurate and context-aware for developer workflows.
Safetensors joining the PyTorch Foundation signals stronger governance and broader adoption for the compact, safe model serialization format. For developers and tool builders, this should simplify ecosystem compatibility, increase trust for distribution, and encourage library maintainers to standardize on safer I/O for models. Expect improved tooling and clearer licensing/interop guidance over time.
The Model Context Protocol project added a new Lead Maintainer and expanded its Core Maintainer group as the open-source project scales. This formalizes governance and should speed reviews, releases, and community contributions—important for developers and integrators building on MCP. Expect clearer ownership of key repos and faster turnaround on contributions.
Anthropic introduces Claude Managed Agents, a set of composable APIs designed for building and deploying cloud-hosted agents. This allows developers to scale agentic workflows without managing the underlying infrastructure.
Carta Healthcare developed 'Lighthouse,' a clinical abstraction platform using Claude and advanced context engineering. The system achieved 99% accuracy across 22,000 cases, demonstrating the viability of LLMs for high-precision medical data extraction.
Deep Agents v0.5 adds async subagents and expanded multimodal filesystem support, enabling non-blocking background delegation and richer data handling for complex agent workflows. These changes make it easier to build scalable, modular agent systems that run long-lived or parallel tasks.
LangChain announced Arcade's integration with LangSmith Fleet, giving agents access to Arcade's catalog of 7,500+ agent-optimized tools through a single secure gateway. This simplifies tool discovery and authorization for production agents, improving operational reliability and governance.
A guide on leveraging subagents within Claude Code to parallelize research and obtain fresh reviews. It provides a framework for deciding when to delegate to a subagent versus staying in the main session.
OpenAI launched a Safety Fellowship to fund and support independent safety and alignment research, aiming to grow the next generation of talent in these areas. The program provides resources and mentorship for researchers working on practical alignment problems, which could accelerate progress on safety tooling and evaluations that developers and researchers rely on. This matters to the community because it expands training and funding pathways focused on rigorous, independent safety work.
Cursor presents `warp decode`, a technique that flips the parallelism axis to speed up and improve MoE model inference by ~1.8×. The approach reduces bottlenecks in routing and offers a practical path to faster inference for large MoE deployments. Developers running MoE architectures should evaluate warp decode for latency-sensitive inference workloads.
LangChain describes the architecture and engineering decisions behind LangChain Hub, detailing how they handle extension discovery, packaging, and scalable indexing. For developers, the post clarifies how to publish and consume community-contributed chains and components and what changes to expect in the Hub API and metadata schema.
LangChain argues that "continual learning" for agents happens across three layers — the model, the harness, and the context — and that treating these separately leads to more practical strategies for long-lived agent systems. The post outlines engineering patterns for updating non-weight artifacts (harnesses and context stores) and why those can yield faster, safer iteration than continual weight updates alone. This framing matters for teams building production agents that must adapt over time without frequent full-model retraining.
A practical engineering account of building a self-healing deployment pipeline for LangChain's GTM Agent — after every deploy, it detects regressions, triages whether the new code caused them, and automatically opens a PR with a fix. No manual intervention until review time. A concrete example of agents managing agents in production CI/CD workflows.
LangChain's evals show open models like GLM-5 and MiniMax M2.7 now match closed frontier models on core agent tasks — file operations, tool use, and instruction following — at a fraction of the cost and latency. The post shares the benchmark results and explains how to start using these models in Deep Agents. A significant data point for teams weighing open vs. closed models for production agents.
Google introduced two new inference tiers for the Gemini API — Flex and Priority — to let developers trade off cost and latency more granularly. Flex is lower-cost with relaxed latency SLAs for background workloads, while Priority offers lower latency for interactive use cases; both aim to reduce wasted spending and make inference choices explicit. This is useful for teams optimizing agent responsiveness and budgets across mixed workloads.
OpenAI added pay-as-you-go pricing for Codex on ChatGPT Business and Enterprise plans, removing the need for a fixed seat commitment to get started. Teams can now scale Codex usage up or down without upfront contracts. A meaningful change for teams that want to pilot Codex without a large spend commitment.
Google released Gemma 4 — their latest open-weight model family with frontier multimodal capabilities designed to run on-device. Gemma 4 brings vision understanding, multilingual support, and significantly improved reasoning to a form factor that fits on consumer hardware. A major open-weight model release that expands what's possible for local AI development.
Cursor launched Cursor 3 — a unified workspace for building software with agents, bringing together the editor, cloud agents, and background automations into a single coherent product. The release represents a significant architectural shift from IDE-with-AI-features toward an agent-first development environment. The biggest Cursor product update to date.
Google released Gemma 4 — their most capable open model family yet, with multimodal understanding and strong performance across reasoning, coding, and instruction following tasks. Designed to run on-device and at edge scale, Gemma 4 closes the gap with frontier closed models while remaining fully open-weight. A significant update to the most widely-used Google open model series.
Anthropic outlines three patterns for building applications that keep pace with Claude’s evolving capabilities: lean on what Claude already knows, continuously question which harness logic Claude can now handle itself, and set boundaries carefully. The post highlights how assumptions baked into agent harnesses go stale as models improve, and why giving Claude tools like bash and a code executor lets it orchestrate its own actions more efficiently. Essential reading for anyone building production agents.