A developer built an open-source PII firewall for LLMs after accidentally sending a customer's credit card number to OpenAI during a benchmark test. The tool, called LLM Governance Engine, intercepts …
A developer evaluated six LLM observability tools—Langfuse, Helicone, Arize Phoenix, LangSmith, Braintrust, and Laminar—for their ability to monitor the audio layer in voice agents, not just LLM calls…
RootSign, a new SDK that produces cryptographic audit logs for CrewAI and LangGraph agents, was released on GitHub. The tool adds a SHA-256 hash chain to every tool call to detect log tampering, addre…
LangChain details a three-layer loop engineering approach for building reliable AI agents, including the core agent loop, a verification loop for quality control, and an event-driven loop for backgrou…
Focused Labs argues that AI agent costs should be treated as a runtime signal rather than a monthly bill, emphasizing that cost management must integrate with traces, evals, and policy changes. The po…
LangSmith version 0.3.79 contains 5 CVEs, including a 9.8 severity request smuggling vulnerability in the undici HTTP client. The flaw allows attackers to inject malicious headers, potentially comprom…
AWS and LangChain released Deep Agents with Bedrock AgentCore, enabling developers to build context-rich research agents that delegate deep work to isolated subagents. The solution spawns specialized …
Three vulnerabilities in LangGraph's checkpointer, disclosed on June 12, allow attackers to chain SQL injection into remote code execution on self-hosted servers using SQLite or Redis backends. The fl…
A new open-source tool called agent-panorama converts raw LLM agent traces into plain-English reports for managers, answering whether agents are worth their cost. It works with LangChain and LangGraph…
Meera, a GenAI engineer at AcmeAI, addresses prompt regression risks by implementing evaluation gates with LangSmith, building a routing benchmark dataset and correctness evaluator to catch silent fai…
Meera, a GenAI engineer at AcmeAI, builds a customer-support agent using LangGraph that leadership loves, but risk head Sanjay halts the launch with demands for replayable interactions, tamper-evident…
Galdor, a Go-native framework for building and observing AI agents, launched v1.0.0 in June 2026 with built-in OpenTelemetry tracing, an embedded SQLite dashboard, and first-party support for both MCP…
ProofLayer released ProofLayer Rules, an open-source runtime security layer for MCP servers and LangGraph agents that blocks prompt injection, jailbreaks, and tool abuse in real-time with sub-100ms la…
LangChain launched LangSmith Sandboxes, a new infrastructure product that gives AI agents their own isolated computers with filesystems, shells, and package managers. The product addresses security ri…
Microsoft has open-sourced ASSERT, an AI evaluation framework that converts natural-language requirements into executable tests for enterprise agents, as organizations struggle to validate agent behav…
Runcap, a new open-source developer tool, estimates the cost of coding agent runs before they begin and enforces a hard spending ceiling that physically stops the run when the limit is reached. The to…
A developer spent 40 hours reading production logs from teams running LangGraph, CrewAI, and AutoGen agents, then launched a $149 diagnostic service that analyzes agent traces and delivers a written r…
Intencion launched a product analytics tool designed specifically for AI agents in production, capturing every user interaction end-to-end including intent, agent steps, and outcomes. The tool install…
A company shipped an AI chat feature to production but found the model was a black box, unable to answer basic operational questions about why answers were good or bad. The team added an observability…
The best evaluation harness for production AI and agents must support consistent testing across local development, CI, production monitoring, and continuous improvement as models, prompts, and agent d…