Pydantic AI Harness now ships AWSLambdaDurability, a capability that checkpoints every model request, function tool call, MCP call, and dynamic-toolset resolution as an AWS Lambda durable functions st…
Anthropic's Claude models have adopted the archaic term 'seam' to describe software connection points, and the usage has proliferated across codebases and other AI models, according to a developer's a…
NVIDIA Labs released NOOA (Object-Oriented Agents), an Apache 2.0 alpha that treats agents as Python classes, claiming 82.2% on SWE-bench Verified with 1.1 million tokens and 28 model calls per task, …
A benchmark of 160 agent tasks found LangGraph and Pydantic AI tied at 100% correctness with gpt-4o, but swapping to gpt-4o-mini dropped overall correctness to 75%, with one date-arithmetic task faili…
Pydantic Logfire, from the team behind Pydantic, is named the best OpenTelemetry backend in 2026 in a comparison that evaluates cross-signal querying, high-cardinality tolerance, and GenAI awareness. …
Pydantic AI has launched realtime voice support for its AI agents, enabling live speech-to-speech conversations through a provider-agnostic API that works with OpenAI Realtime, Azure OpenAI, Gemini Li…
LangChain's Terminal-Bench experiment found that changing only the harness—keeping the same model—moved a coding agent from roughly 30th place into the top 5, reframing harness design as an architectu…
A developer's analysis of Pydantic AI's run loop reveals that the framework maintains a single mutable conversation list per run and re-sends the entire accumulated history—including tool outputs—on e…
CopilotKit released Open Bot, an open-source agent platform that runs on a user's own machine and lets any AG-UI agent operate a real browser, files, and tools through a governance gateway that decide…
Crusoe is now a native model provider in Pydantic AI, enabling developers to run agents on Crusoe Managed Inference with a single string like 'crusoe:zai/GLM-5.2'. The integration, contributed upstrea…
Benchclaw, an AI agent benchmarking platform, published a public evidence bundle for its pilot runs showing LangGraph 1.2.9 and Pydantic AI 2.13.0 both completed 20 of 20 tasks under gpt-4o at a total…
FreeCodeCamp published a tutorial on building production-grade AI agents using Pydantic AI, emphasizing the need for structured outputs, testable code, and reliability over raw LLM SDKs. The guide cov…
StackOne, the integration gateway for AI agents, is now a capability in Pydantic AI Harness, allowing agents to access actions on linked accounts such as Workday, BambooHR, Salesforce, and Zendesk wit…
A developer's review of recent AI releases found only two updates met a strict 36-hour cutoff: Meta's Muse Glimmer, a 30B multimodal model under Apache 2.0, and Hugging Face's Transformers 5.15.0. The…
Snowflake and Pydantic AI have launched a native integration, adding SnowflakeModel and SnowflakeProvider to Pydantic AI, enabling governed AI agents to run on Snowflake data via the Snowflake Cortex …
Airbnb published a playbook for evaluating generative AI at scale, recommending teams read roughly 100 outputs and traces before building evaluators, then layer programmatic checks, LLM judges, and hu…
SerpApi released serpapi-search-tools, an open-source Python package that gives AI agents real-time access to web, news, maps, images, shopping, videos, hotels, flights, and travel search, compatible …
Pydantic AI introduced Pydantic Evals, an evaluation library designed to test AI agents by combining deterministic structural checks with LLM-based judgment for subjective qualities. The library inclu…
A developer outlines the fragmented agent platform market as of August 2026, distinguishing between agent logic frameworks, managed runtimes, and control plane infrastructure. The post emphasizes that…
Pydantic AI v2 is being integrated into three specific layers of two production systems—a content-generation platform and a brand-measurement platform—but not as the orchestrator, according to a build…