An open-source platform for durable AI agents and background workflows written in TypeScript, with retries, queues, realtime streaming and run observability.
VoltAgent
Summary
An open-source TypeScript framework for building AI agents, paired with VoltOps, a console for tracing, evals, prompt management and deployment.
Screenshots
Description
VoltAgent is an open-source framework for building AI agents in TypeScript, paired with VoltOps, a hosted console for running them in production. The framework gives developers the building blocks for an agent application in code: agents with unified APIs, tools and memory, workflows, retrieval (RAG), guardrails and connections to MCP servers, on top of the model provider of their choice. The core is MIT licensed and published on npm as @voltagent/core.
VoltOps is the observability-first half of the project. Agents built with the framework report traces that VoltOps renders as a timeline of every step, tool call and LLM call, alongside dashboards for latency, cost, token usage and tool usage. It also covers evaluations with scorer suites and pass-rate trends, versioned prompt management, alerts on error rates or latency sent to channels such as Slack, triggers that start agents from external events, and deployment.
The framework is free. VoltOps has a free Developer plan with one seat and 250 traces a month, and a paid plan at $50 per month for up to three seats and 50,000 traces a month with pay-as-you-scale pricing beyond that and a 14-day free trial.
Reviews
No reviews yet — sign in to write the first one
Similar App Suggestions
See all VoltAgent alternativesAI engineering platform for tracing, evaluating and improving LLM apps and agents — with Phoenix, its open-source local-first counterpart, for teams that want to start without a vendor.
Reads your production chat and voice agent conversations to surface the silent failures, frustration loops and policy breaches that offline evals never catch.
The framework and observability platform most teams use to build, debug, and ship LLM agents.
Open-source LLM observability — trace, evaluate, and improve AI applications with production data.