mastra
mastra copied to clipboard
mastra-ai
the TypeScript AI agent framework
Running `npm audit` reveals moderate severity vulnerabilities in the AI SDK dependencies of `@mastra/[email protected]` and current stable version 1. `nanoid < 3.3.8` vulnerability in: - `@ai-sdk/provider-utils` - `@ai-sdk/anthropic` - `@ai-sdk/openai`...
Congratulations on securing a spot in Y Combinator! We are [Needle](https://needle-ai.com/), a Knowledge Threading Platform designed to build AI Agents, including MCP, and support Agentic integrations. We are interested in...
This PR sets up senku. We have a bunch of tools which should be connected to a workflow so that we can preview in `mastra dev`. The tool fetches channels...
Title self explanatory. ```sh # pnpm approve-builds node_modules/.pnpm/[email protected]_@[email protected][email protected][email protected][email protected][email protected]/node_modules/mastra: Running postinstall script... ^c node_modules/.pnpm/[email protected]_@[email protected][email protected][email protected][email protected][email protected]/node_modules/mastra: Running postinstall script, failed in 9m 54.8s .../node_modules/mastra postinstall$ node src/scripts/postinstall.js │ Detected package manager: pnpm │...
This PR introduces the deprecation of the @mastra/speech-openai package in favor of the new @mastra/voice-openai package. OpenAIVoice provides both Text-to-Speech (TTS) and Speech-to-Text (STT) capabilities
From the examples in `@mastra/evals`, it appears that the evaluation is performed using an LLM. Do these eval functions always return the same score for identical inputs and outputs?
In Mastra, when adding a logger using UpstashTransport, the Log Drains feature in the playground throws an error: "transportId is required" This happens even when following the official guide: [Upstash...
