Harness Hub
All startups

Mastra

The TypeScript-first company behind the Mastra agent framework.

Mastra builds the eponymous open-source TypeScript framework — workflows, tools, RAG, evals and a local dev playground — and is becoming the default 'agent backend' choice for JS/TS teams.

Pros & cons

Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.

Pros

  • MetadataTypeScript-first agent framework (about 29k stars) with typed tools, Zod schemas, workflows and storage-backed human-in-the-loop suspend/resume.[1]
  • DocsOne interface routes to 40+ model providers, and it integrates with Next.js, Vercel AI SDK UI and CopilotKit.[1]
  • DocsBuilt-in evals, observability, RAG, memory and MCP server authoring mean fewer extra libraries to add.[1]
  • Independent testReviewers credit Mastra Studio for visual local debugging of agents and workflows.[1]

Cons

  • MetadataThe core is Apache-2.0, but code in ee/ directories falls under a source-available Mastra Enterprise License that requires a paid license for production use.[1]
  • Independent testSupports TypeScript only, so Python-first teams need another framework.[1]
  • Independent testReviewers note fewer production proof points and a younger plugin ecosystem than LangGraph or LlamaIndex.[1]
  • MetadataHas about 379 open issues, and only collaborators can open pull requests.[1]
Best for
TypeScript and Next.js teams building agents and workflows that want most pieces built in.
Watch out for
Check whether features you need fall under the ee/ enterprise license.

Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction

People

Official YouTube channel

Evals & benchmarks · Context engineering & memory · Tutorials & getting started

Open roles (2)

  • Founding Sales

    United States · Full-time · Posted Oct 28, 2026

    Go-to-marketRemote
  • AI Engineer

    Remote · Full-time · Posted Oct 7, 2026

    EngineeringRemote

Their open-source work

Featured

mastra-ai/mastra

The TypeScript framework for production agents.

Maintained by Mastra

@mastra/core@1.84.0released
4 pros · 4 cons

Activity

Last push
· today
Latest release
@mastra/core@1.84.0
· 3d ago
Last 90 days
20+ releases
  1. @mastra/core@1.84.0November 17, 2026

    · 3d ago

    Highlights Storage Version 2 for Agents & Evented Workflows (much smaller writes + faster runs) Agents (createDurableAgent, createEventedAgent) and evented workflows can now opt into experimental storageVersion: 2, storing runs as a header + per-step rows so long runs write…

  2. @mastra/core@1.83.0November 12, 2026

    · 8d ago

    Highlights Resumable Agent streams (now for every Agent) Every Agent can now publish a resumable run stream with replay caching, cross-instance observe/abort (agent.observe(runId), observe().abort(), agent.abortRunStream(runId)), and ownership/TTL enforcement—so clients can…

  3. @mastra/core@1.82.0November 4, 2026

    · 2w ago

    Highlights Knowledge v2: page-tree model, richer tools, and server-side sync APIs Knowledge is now a first-class page tree (pages/notes/pins) with major tool upgrades: knowledge_list, line/section/grep-style reads in knowledge_read, list pinning (kind: 'list'), and a link index…

  4. @mastra/core@1.81.0November 2, 2026

    · 2w ago

    Highlights MCP Tasks (Storage-backed, restart-safe long-running execution) @mastra/mcp adds experimental Mastra-storage-backed MCP tasks so long-running tools/agents/workflows can return immediately with a task, be polled/answered/cancelled across instances, and survive…

  5. @mastra/core@1.80.0October 28, 2026

    · 3w ago

    Highlights End-user (per-resource) connections in @mastra/connect tools({ resourceId }) and new userConnectRoutes() enable user-scoped OAuth connections so agents can safely use each end user’s accounts (in addition to global connections), with built-in caching and hard…

Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.

On X

Posts by the company and its team, shown as plain text; “Load on X” loads X's script for that post, which may set cookies.

  • Mastra Factory is your software factory. Today we're announcing:

    - App previews that persist across work sessions
    - Ambient mode in Slack that knows when to reply in a thread
    - PR reviews that pick up comments and address them automatically
    - Cloud workspaces with your own… pic.twitter.com/zFQTQs7aQ3

    Open on X

Follow @mastra on X · The X feed

Videos

Their YouTube channel · All videos

Featured

The de-facto standard toolkit for building LLM applications and agents.

LangChain makes the LangChain framework and LangGraph, the low-level orchestration standard for stateful, controllable agents, plus the LangSmith platform for tracing, evaluating and monitoring them in production.

~$75M raised

4 pros · 4 cons
Featured

Conversational AI agents for customer experience.

Sierra, co-founded by Bret Taylor and Clay Bavor, builds production conversational agents that resolve real customer issues with guardrails, evaluation and human escalation — a template for deploying vertical agents at the enterprise edge.

~$10B valuation (Oct 2025)

4 pros · 4 cons

Multi-agent orchestration, from open-source framework to enterprise platform.

CrewAI popularized role-based multi-agent teams ('crews') with a simple mental model and ships an enterprise control plane for deploying, monitoring and governing them.

$18M Series A led by Craft Ventures (2024)

3 pros · 4 cons

Connections

Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.

The Harness Hub newsletter

New harness companies, projects, releases and the monthly State of Harness report, in your inbox.