A comparison of LLM observability tools MLflow, Langfuse, and Confident AI highlights that standard application logging fails to capture critical context like retrieved documents, system prompts, and …
A new protocol for validating large language model (LLM) agent model swaps uses a 20-minute diffing process to catch regressions before production, according to a developer who built the open-source t…
A developer created WhatBroke, an open-source tool that diffs agent behavior before and after swapping to a new model, catching silent failures like dropped tool calls or drifted arguments. The tool r…
Expedia Group has introduced Service Telemetry Analyzer (STAR), an internal AI-assisted observability platform that helps engineers investigate production incidents by analyzing service telemetry and …
A developer found that an LLM judge gave opposite results for the same eval run on consecutive days due to position bias, one of three systematic biases documented in the 2023 paper "Judging LLM-as-a-…
OpenObserve crossed 20,000 GitHub stars with 8,000+ production deployments, including Fortune 100 companies ingesting 2.5 petabytes of telemetry daily, three months after a $10 million Series A from N…
Trigger-tree, a new open-source tool by developer Hedde, measures which project documentation files AI coding assistants like Claude and Codex actually read, providing heat maps, cold maps, and a live…
Dify, an open-source LLM app development platform, gained 840 GitHub stars and now has 149k stars total. The platform offers a visual builder, RAG pipelines, and agent workflows for teams building LLM…
MongoDB released a tutorial and demo for building an agentic event venue operator using MongoDB Atlas, Voyage AI embeddings, and LangGraph, featuring a fictional tennis tournament scenario where the a…
A new guide evaluates eight audit logging platforms for B2B and agentic AI applications, highlighting the need for compliance tools that can handle AI-native features like massive payloads and non-det…
Oodle.ai has launched LLM Agent Observability, a service that stores all agent traces without sampling at $10 per million traces, using a custom columnar storage engine on S3 and AWS Lambda for sub-se…
Halley, an open-source tool built for LLM agent teams, records production agent runs as bit-fidelity cassettes and replays them as zero-cost regression tests in CI, enabling deterministic bisection to…
Langfuse, an open-source LLMOps platform licensed under MIT, provides tracing, prompt versioning, and evaluations in a single stack that can be self-hosted with Docker Compose. The platform addresses …
A survey of 696 experts conducted by The Register and NeuBird AI in April 2026 found that 73 percent are not using AIOps at all, with only eight percent having it in production. 60 percent of responde…
BoundFlow, an open-source control plane for AI agents, enforces cost caps, approval gates, and self-healing policies on unattended LLM workflows. The backend is Apache-2.0 licensed and self-hostable, …
VXControl released PentAGI, an open-source autonomous penetration testing tool that orchestrates multiple LLM agents and sandboxed Kali Linux environments to automate offensive security workflows. The…
Rightmodeler replays real agent traces through cheaper models, judges outputs against shipped versions, and shows cost-saving opportunities with evidence. The tool supports traces from Claude Code, Co…
A developer evaluates six LLM observability tools—Helicone, LangSmith, Langfuse, Future AGI, and Braintrust—for debugging hallucinated answers in production. The key requirement is the ability to quic…
Immersive Fusion released TraceGen, a single-binary distributed trace generator that produces realistic OpenTelemetry traces and correlated logs for up to 28 services, including AI agentic scenarios w…
Glad-Labs retired its Gen-1 TopicDiscovery orchestrator, cutting nearly 900 lines of legacy code and collapsing logic into a single topic path. The team also fixed a GPU lock deadlock that caused invi…