Introducing agentOS
A lightweight VM for AI agents, powered by WebAssembly and V8 isolates. ~6 ms cold start, 32x cheaper than sandboxes, full POSIX environment.
agentOS Blog6 min read
agents
233 stories
How we test Agent Skills with Scenario simulations
Most AI agent skills ship untested. See how LangWatch Scenario simulates full multi-turn conversations with a user simulator and judge to catch real failures.
LangWatch Blog7 min readProduct Managers and leaders are running agent simulations now, and it changing how AI ships
Non-technical leaders now write agent simulations in plain language with LangWatch and Claude, testing AI agents before a single customer sees them.
LangWatch Blog6 min read
LangWatch Skills: Your coding agent already knows how to test your agent
LangWatch Skills let your coding agent instrument tracing, observe production performance, and run tests automatically, no manual setup needed.
LangWatch Blog6 min read
Agent Command Center, Agent Playground, and ClickHouse Migration
Agent Command Center: routing, guardrails, fallbacks, per-key cost controls. Agent Playground: visual multi-step graph builder. Plus ClickHouse migration.
Future AGI Blog6 min read
Agent Middleware in VoltAgent - Intercept and Control Agent I/O
How to use middleware to sanitize input, validate output, and trigger retries before guardrails and hooks run.
VoltAgent Blog3 min read
Tool Routing in VoltAgent - Scaling Tool Use Without Stuffing Your Prompt
Why exposing every tool to the model does not scale, and how VoltAgent's Tool Routing keeps tool use fast, controlled, and observable.
VoltAgent Blog4 min readBaseline Chat Comparison, Fix My Agent Polish, and OpenTelemetry Instrumentation
Baseline chat comparison wires production conversations into simulation as the fastest path to reproducible tests. Plus Fix My Agent, OTel, image outputs.
Future AGI Blog3 min readChat Simulation via Observe, Pre-Built Evaluation Groups, and Fix My Agent for Chat
Launch chat simulations directly from real production conversations, 10 ready-to-use evaluation groups with no configuration, and Fix My Agent for chat.
Future AGI Blog4 min readChat Simulation V1, Agent Prompt Optimiser, and Reliability Upgrades
Simulation for text chat agents, a six-strategy automated prompt optimiser, selective optimisation against specific calls, and resilience on restarts.
Future AGI Blog3 min readFix My Agent, Persona Management Suite, and JSON Input/Output in Sessions
Context-aware debugging that explains why a simulation failed and how to fix it, full lifecycle for personas, structured JSON sessions, Optimiser backend.
Future AGI Blog4 min readMulti-Branch Scenarios, Custom Background Noises, and Critical-Issue Feed in Simulate
Scenarios that branch into multiple conversation paths, ambient noise profiles that push simulations closer to production, and a critical-issue feed.
Future AGI Blog3 min readCredit Usage Revamp, Multi-Language Agents, and New TTS Providers
Workspace credit attribution, a 3-step guided agent builder with multi-language, rebuilt Prompt Workbench with commit history, and 4 new TTS providers.
Future AGI Blog3 min readOpenAI Agent Builder
The refreshed Open AI Agent Builder beta now lives under the broader AgentKit umbrella. AgentKit bundles orchestration, governance, and UI pieces into one stack, and the canvas remains an efficient way to sketch an agent before committing to TypeScript.
VoltAgent Blog4 min readAutomated Scenario Builder, Agent Definition Versioning, and Simplified Session Tracking
Upload an SOP or call transcript to auto-generate test scenarios with edge cases. Commit-style version control for agents. Session observability per span.
Future AGI Blog3 min readAgent Compass, Annotation Quality Dashboard, and Enterprise Multi-Workspace Security
Zero-config performance insights on agent traces, statistical dashboards for annotator agreement, and multi-workspace isolation with audit logging.
Future AGI Blog4 min read
Browser security in the age of AI agents
AI agents introduce new security risks when given direct browser access. Lightpanda explores how a lightweight browser with instant startup can mitigate these threats.
Lightpanda Blog4 min read
Showing 233 of 233 stories
You're all caught up.
AiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts