Mastra: what’s new in @mastra/core@1.79.0 and our verdict
TypeScript framework for AI-powered applications and agents, with a local Studio.
At a glance
- Evidence
- Tested (smoke test)
- Released
- Oct 21, 2026
- Last verified
- Oct 25, 2026
- Pricing
- Not verified
- Best for
- agent building
Evidence and ranking
Evidence behind this verdict
- Sources read2 cited sources, latest fetched Oct 25, 2026. (done)
- Facts re-checkedLast verified Oct 25, 2026. (done)
- Run by usSmoke test on Oct 25, 2026 (scope below). (done)
Passed Test log result: Passed. Read the log
Where we rank it (editorial)
- agent building#6 of 33 tools
Editorial picks, not benchmark scores. How we rank.
Pricing: We have not verified pricing for this tool; see the official site.
Our verdict
A strong TypeScript option if you are building agents in a Node stack; read the breaking-change note on sessions before upgrading.
Good for
- TypeScript and Next.js teams building agents
- Teams that need observability and tracing out of the box
- Developers experimenting with MCP events
Skip if
- You work in Python
- You need a stable session API; this release changes it
Tested. Tested 2026-10-25 (America/Chicago). Mastra passed 5 of 5 on Node 20 (0.24.9) and 5 of 5 on Node 24 (1.79.0) with temperature pinned to 0, after failing 5 of 6 earlier trials at default sampling. Test environment: Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key. Agent tools were pointed at a local open-weight model (Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11), so we tested the tool, not any vendor's hosted models. Not tested: Any vendor-hosted model: everything ran against one local 3B model; Multi-agent flows, memory, streaming and deployment; Anything beyond one tool and one question; five trials is a smoke test, not a benchmark. These are smoke tests, not a benchmark. Full log: /tests/mastra.
Full test log with exact commands, versions and raw output: Mastra 0.24.9 (Node 20) / 1.79.0 (Node 24): our test log.
- Evidence
- Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)). A smoke test is not a benchmark.
- What we ran
- Mastra passed 5 of 5 on Node 20 (0.24.9) and 5 of 5 on Node 24 (1.79.0) with temperature pinned to 0, after failing 5 of 6 earlier trials at default sampling.
- Model used
- Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11
- Environment
- Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key
- Not tested
- Any vendor-hosted model: everything ran against one local 3B model; Multi-agent flows, memory, streaming and deployment; Anything beyond one tool and one question; five trials is a smoke test, not a benchmark.
- Date
- (America/Chicago)
Get the next tool verdict in your inbox. Free, about six minutes a week.
Free. Unsubscribe anytime. No spam. We email a confirmation link first. Privacy
Best for
- Best AI tool for agent building: TypeScript-first framework with Studio, observability and MCP support.
What’s new
@mastra/core 1.79.0 adds experimental MCP Events, richer observability (span aggregation and time-to-first-chunk), session-ID based agent controller sessions (a breaking change) and a native filesystem API for sandboxes.
- @mastra/core@1.79.0 (Oct 21): Experimental MCP Events let MCP servers publish event streams that clients can poll, stream or receive by signed webhook, with Studio inspection under mastra dev.
- Observability: new aggregateSpans() for per-span analytics such as p95 latency per tool, plus timeToFirstChunkMs fields and richer querySpans filters.
- Agent controller sessions are now addressed by sessionId, allowing many sessions per resource (breaking change).
- Sandboxes can expose a native filesystem API for faster file operations.
- @mastra/connect adds per-end-user connection scoping and a Microsoft Teams channel.
How to set it up: Create a Mastra project
Steps come from the vendor's own docs or README. We ran Mastra on 2026-10-25; the test log lists what was and was not covered.
Scaffold a project
The README starts with the create command.
npm create mastra@latestRun the local Studio
Mastra has a dev command that starts Studio so you can inspect agents. The release notes mention mastra dev for inspecting MCP events.
npx mastra devRead the breaking changes
Before upgrading an existing app to @mastra/core 1.79.0, read the release notes on controller sessions now keyed by sessionId.
Pros and cons
Pros
- TypeScript-native
- Detailed release notes with highlights
- Strong observability additions in this release
Cons
- Breaking change to agent controller sessions in this release
- License reported as NOASSERTION on GitHub, so check the repository's license text
- Some features are experimental
- Our test was one small task on a local 3B model; it does not show behaviour with hosted models or larger jobs
Alternatives and comparisons
- CrewAI: Python framework for orchestrating role-playing, autonomous AI agents that work as a crew.
- LangGraph: Low-level framework for building long-running, stateful agents as graphs.
- OpenAI Agents SDK: Lightweight Python framework for multi-agent workflows, with tools, handoffs, sessions and tracing.
- Langflow: MIT-licensed visual builder for AI agents and MCP servers with a very large GitHub following.
FAQ
What is new in Mastra @mastra/core 1.79.0?
Experimental MCP Events, span aggregation and time-to-first-chunk observability, session-ID based controller sessions (breaking), a native sandbox filesystem API, and per-user connection scoping in @mastra/connect.
How do I start a Mastra project?
Run npm create mastra@latest.
Is Mastra open source?
The code is public on GitHub; GitHub reports the license as unspecified, so read the repository's license file before using it commercially.
What we have not verified
- License terms (GitHub reports NOASSERTION)
Sources
- @mastra/core@1.79.0 release (fetched 2026-10-25)
- README (fetched 2026-10-25)
Last verified · Agentic Weekly
Part of the week of Oct 19, 2026 archive.
Related tools
How to cite this page
Agentic Weekly, "Mastra @mastra/core@1.79.0: what's new, verdict & setup", last updated 2026-10-25, https://theagenticweekly.com/tools/mastra
Keep the Reported or Tested label when you quote a verdict. Plain-text version: https://theagenticweekly.com/tools/mastra.md. More for AI assistants: /ai, /tools.json, /llms.txt.
Free · weekly · about six minutes
Want the next verdict in your inbox?
What shipped this week, what is worth switching to, and what to ignore. We run what we can and label what we only read.
- One email a week. Each release gets one call: update now, worth a look, or skip.
- Every claim shows its evidence. Reported means we read the sources; Tested means we ran it, with the exact scope and the failures left in.
- A free AI Tools Cheat Sheet (web page and printable PDF) lands in your inbox when you confirm.
Free. Unsubscribe anytime. No spam. We email a confirmation link first and add you only after you click it. We use your email only to send this newsletter and never sell it. Privacy