What's new in LangWatch

Every release, improvement, and fix as it ships. Follow along as the platform evolves.

AllScenarioLangWatch

• April 13, 2026 - 3.0.0
  Keyboard Warriors - The Command Bar
  A Cmd+K command bar to navigate anywhere, search for any entity, switch themes, and discover a few surprises along the way.

• April 13, 2026 - 3.0.0
  Polished Analytics
  A sharper, more polished analytics experience - sticky headers, better empty states, dark mode refinements, and fixes for filter behavior across the board.

• April 8, 2026 - 3.0.0
  LangWatch 3.0 - Self-Host with ClickHouse
  LangWatch 3.0 is here, a simpler, faster stack built on ClickHouse. Deploy with Helm, run with Docker Compose, no Elasticsearch required.

• April 8, 2026 - 3.0.0
  Event Sourcing Engine Fast is the only “mode”
  LangWatch now runs on a purpose-built event sourcing engine. Traces, evaluations, and simulations are processed in real-time with no accuracy trade-offs.

• April 6, 2026 - 3.0.0
  Built-in MCP Server with OAuth
  LangWatch now ships a built-in MCP server with OAuth. Connect Claude Code, or any MCP client to manage prompts, datasets, evaluators etc from your editor.

• April 3, 2026 - 3.0.0
  Prompt Tags
  Tag your prompts across every surface platform, SDKs, CLI, and MCP. Use syntax (prompt:tag) to fetch tagged versions, and manage tags from wherever you work.

• February 5, 2026 - LangWatch v2.0.2
  LangWatch Scenario on the Platform
  Create and run agent simulation tests directly in LangWatch, no code required. Define user personas, set pass/fail criteria, and run scenarios against HTTP.

• January 8, 2026 - LangWatch - v1.12
  Graph Alerts
  The alerting feature now includes custom graph alerts that trigger when specific thresholds are met, with notifications sent via preferred channels like Slack.

• December 16, 2025 - LangWatch - v1.11.0
  Audit Logs
  We’ve introduced a new Audit Logs page, giving you complete visibility into user activity across your projects. This feature helps you monitor actions...

• December 16, 2025 - @langwatch/better-agents - v0.1
  Better Agents just got better! Support for Google ADK, LangGraph, Antigravity & more
  New Coding Assistants Supported: Antigravity, Crush CLI, Gemini CLI, Qwen Code. With this, Better Agents now works across a much wider range of tools and...

• December 16, 2025 - LangWatch - v1.11.0
  Replicate Workflows/Prompts/Datasets
  We’ve added the ability to replicate workflows, their datasets, and prompts to another project. This lets you safely test in a staging environment, validate...

• November 25, 2025 - @langwatch/better-agents - v0.1
  Launch Week - Day 5: Better Agents
  Better Agents is a CLI tool and a set of standards for agent building, it supercharges your coding assistant...

• November 25, 2025 - @langwatch/mcp-server - v0.3.1
  Launch Week - Day 4: Writing Tests with the Scenario MCP
  Scenario MCP will enable you to generate high-quality tests, and it's as easy as cake. One prompt is all it takes, and the outcome will...

• November 21, 2025 - LangWatch - v1.9.0
  Launch Week - Day 2: RBAC Custom Roles & Permissions
  With the new RBAC Custom Roles, you can now enforce finer-grained access control, allowing different role sets to focus on their specific domains. The permis...

• November 21, 2025 - LangWatch - v1.9.0
  Launch Week - Day 3: Testing Voice Agents with LangWatch Scenario in Real Time
  LangWatch Scenario now supports testing voice-powered AI agents using OpenAI's Realtime API through a new RealtimeAgentAdapter. This enables comprehensive...

• November 20, 2025 - LangWatch - v1.9.0
  Launch Week - Day 1: LangWatch New Prompt Playground
  With the new RBAC Custom Roles, you can now enforce finer-grained access control, allowing different role sets to focus on their specific domains. The permis...

• June 27, 2025 - Scenario - v0.7
  Real-time simulation visualization and debug mode
  Watch simulated conversations play out in real-time with parallel execution, versioned runs, and interactive debugging.

• June 26, 2025 - Scenario - v0.7
  Scripted simulations, evaluations, and guardrails
  Scripted simulations let you orchestrate how conversations unfold, when evaluations occur, and what custom logic runs.

• June 25, 2025 - Scenario - v0.7
  Test agents on Mastra, Agno, and 10+ other frameworks
  Scenario is framework-agnostic, supporting any agent architecture through the AgentAdapter interface.

• June 24, 2025 - Scenario - v0.7
  Introducing simulation-based agent testing
  Test your agents with scenarios directly in your codebase using Python and TypeScript.