Developer Tools
MCP servers, CLIs, SDKs, APIs, and open source tooling for building on agentic AI platforms.
Building on agentic AI platforms requires the right developer tools—from MCP servers and CLIs to SDKs, APIs, and integration frameworks. Explore open source tooling, integration guides, and developer resources for building, extending, and connecting AI-powered applications.
920 articles in this category
NVIDIA's PAIR Is a Router, Not an Inference Cluster
NVIDIA open-sourced PAIR under Apache 2.0 on September 3, 2026. It routes each request to one eligible node, it does not shard a model or pool VRAM, and every node needs an RTX 20-series GPU or newer.
Open Weights Are Becoming Enterprise Default Infrastructure
NVIDIA signed the $12.9B Hugging Face agreement on September 2 and expects to close in the first half of 2027, AT&T routes roughly 40% of employee AI queries to open models, and Mistral raised €3B at a €21B valuation.
Sheba Is Rolling Out ChatGPT. The Data Layer Decides.
Sheba will be OpenAI's first international hospital partner for ChatGPT for Healthcare, announced July 28, 2026. The constraint is underneath: symplr's 2024 survey puts 51% of health systems above 50 software solutions.
Tencent's 770B Hy4 Is Apache-2.0, and 1.56 TB of Weights
Tencent released Hy4 preview on 28 August 2026 under a genuine Apache License 2.0: 770B total parameters, 49B active, 1M context. The licence is permissive, but the BF16 weights are 1.56 TB and an 8xH100 node cannot load either checkpoint.
Canada's 49-Day Defence Drone Award: Speed Has a Mechanism
Canada named six drone suppliers on September 10, 2026, forty-nine days after the Defence Drone Initiative launched. The speed came from a pre-qualified supply arrangement with nearly 400 vetted vendors, not from skipping procurement.
Prior-Auth Automation Optimizes a Queue, Not the Patient
Vendors advertise prior-auth automation across 600-plus payers, yet the AMA's 2025 survey still puts prior authorization at 13 hours of physician and staff time a week. The clinical half is a data problem.
Finding Where a 50-Step Agent Run Dies Is Not Solved
Microsoft Foundry's agent tracing reached general availability at Ignite 2025, not this week, and the docs still mark workflow and external agents preview. It narrows where a 50-step run died, not why.
Cisco's MyAgent: 90,000 Seats and a Model-Agnostic Stack
Cisco's own 27 August account names the agent MyAgent and the platform beneath it Circuit, a multi-model-agnostic stack now rolling out to 90,000 employees with much of the infrastructure on-premises.
Cache Side-Channels Break the On-Premise Assumption
A USENIX Security 2025 paper reconstructed a local LLM's output from CPU cache patterns at a 5.2% edit distance, using unprivileged code on the same host. Air-gapping closes the network boundary, not the host one.
A Court Struck a Deutsche Bank Brief Over Fake AI Cites
On September 3, 2026 the D.C. Court of Appeals struck a brief filed for Deutsche Bank National Trust Co. because four cited cases did not exist. It is one of more than 1,148 such US filings.
Shadow IT Stored Data. Shadow Agents Take Actions.
IBM's 2026 breach report puts shadow AI in 43% of security incidents, more than double the year before, while close to seven in ten breached organizations had no governance policy covering unapproved AI use.
Base Labs, Marin, Nemotron: The Moat Is Architecture
Base Labs published its manifesto on September 2, 2026, joining Stanford's Marin open lab and NVIDIA's eight-lab Nemotron Coalition. As open models multiply, the durable asset is the architecture that swaps them.
Quasar 438B Is API-Only, and That Is Not Sovereignty
Multiverse Computing's Quasar 438B scored 43 on Intelligence Index v4.1.1 at launch on 2 September 2026, the top European result. It is also proprietary, API-only, and compressed from Z.ai's open-weights GLM-5.2.
Chat Logs Are Not Clinical Memory. The Difference Is Safety.
Storing transcripts is not clinical memory: accuracy fell from 75.8% to 53.8% when the key document moved to the middle of a 20-document context, below the model's 56.1% closed-book score.
69 Releases in a Week, and Why Model Switching Compounds
ibl.ai shipped 69 web frontend releases in the week to September 4, 2026, refreshing its LLM registry to GPT-5.6, Claude Opus 5, Gemini 3.7 and DeepSeek V4. Models retire on the provider's calendar, not yours.
Open-Source AI Agents Reach K-12 Before Governance Does
ByteDance's MIT-licensed DeerFlow hit #1 on GitHub Trending on 28 February 2026 and IFM's Apache-2.0 K2 Horizon fleet spans 0.9B to 375B parameters. Neither ships the governance a K-12 district needs.
Financial AI Agents Ship as SKUs. Integration Doesn't.
Alphio.AI listed its AI Financial Agent on AWS Marketplace on September 8, 2026, into a category AWS opened in July 2025 that press coverage put at 900+ agents. The agent is the SKU, not the moat.
OpenAI Wired ChatGPT Into Epic. Where Does the PHI Go?
On September 1, 2026 OpenAI connected ChatGPT for Healthcare to Epic — read-only, and OpenAI reports physicians rated 99.1% of responses safe across 4,363 ratings. The 325 million patients is Epic's install base.
An Anthropic Resignation and the Case for Owning the Stack
Jacob Coxon spent three years training models at OpenAI and Anthropic, then resigned on September 8, 2026 saying neither company is acting responsibly. The enterprise lesson holds either way.
DeerFlow 2.0 Is Free. Your Governance Layer Is Not.
ByteDance did not just open-source DeerFlow: v1 shipped May 2025 and the 2.0 harness launched 28 February 2026, now past 82,000 stars. The agent is free; the governance layer is what you own.
Palantir and Nebius: Sovereign Deployment vs Ownership
On September 8, 2026 Palantir named Nebius its preferred sovereign AI infrastructure partner, scoped to commercial customers. Agencies need the distinction between sovereign deployment and sovereign ownership.
Spec-Driven Development: Why Vibe Coding Doesn't Ship
GitHub's Spec Kit makes the specification the shared source of truth an AI agent executes against — spec, then plan, then small testable tasks. The reason it matters is that ambiguity is where coding agents fail, and a spec is where ambiguity surfaces cheaply.
The Model Is the Commodity. The Context Layer Is the Moat.
Verizon expanded its Google Cloud partnership to scale Gemini across customer service, network operations and marketing — and the reporting kept returning to unifying enterprise data. The model was available to every competitor. The unified data access was not.
The 5-Layer Agent Stack: Most Vendors Ship Layer One
A five-layer model of agent architecture — interface, orchestration, knowledge, memory, governance — is the most useful way we have found to audit an enterprise AI product. The uncomfortable part is that most enterprise AI products implement the first layer and describe the other four.