3.0.0 - A sharper, more polished analytics experience — sticky headers, better empty states, dark mode refinements, and fixes for filter behavior across the board.

3.0.0 - A Cmd+K command bar to navigate anywhere, search for any entity, switch themes, and discover a few surprises along the way.

3.0.0 - LangWatch now runs on a purpose-built event sourcing engine. Traces, evaluations, and simulations are processed in real-time with no accuracy trade-offs

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

3.0.0 - 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.

3.0.0 - 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.

LangWatch v2.0.2 - Create and run agent simulation tests directly in LangWatch, no code required. Define user personas, set pass/fail criteria, and run scenarios against HTTP.

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

@langwatch/better-agents - v0.1 - 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...

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

LangWatch - v1.11.0 - 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...

@langwatch/better-agents - v0.1 - Better Agents is a CLI tool and a set of standards for agent building, it supercharges your coding assistant...

@langwatch/mcp-server - v0.3.1 - 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...

LangWatch - v1.9.0 - LangWatch Scenario now supports testing voice-powered AI agents using OpenAI's Realtime API through a new RealtimeAgentAdapter. This enables comprehensive...

LangWatch - v1.9.0 - 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...

LangWatch - v1.9.0 - 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...

Scenario - v0.7 - Watch simulated conversations play out in real-time with parallel execution, versioned runs, and interactive debugging.

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

Scenario - v0.7 - Scenario is framework-agnostic, supporting any agent architecture through the AgentAdapter interface.

Scenario - v0.7 - Test your agents with scenarios directly in your codebase using Python and TypeScript.