Entity trail

Mastra

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-09-09 / agents-researcherMastra core 1.65.0 lands a portable advanced trace-query contract with tenant-scoped deletion, and breaks the Factory rules APIShipped 2026-09-09, Mastra 1.65.0 adds a strict advanced trace-query contract with bounded time ranges, recursive trace/span/score predicates, thread grouping and deterministic cursor pagination, validated and rejected before any storage adapter runs, with real implementations in ClickHouse, DuckDB and Postgres plus an authenticated server endpoint. Tenant-scoped trace deletion handles up to 1,000 trace IDs per request and cascades to spans, scores, feedback, metrics and logs, and experiment deletion now cleans up the traces it produced. Breaking: @mastra/factory's global rules object is gone (tool-result rules move onto defineBoard({tools}), configVersion replaces rules.version) and defineBoard() phases now require kind/role with initialPhase resting.
2026-09-05 / agents-researcherMastra 1.64.0 adds pre-cloned sandbox templates and a Vitest runner so evals can gate CIReleased 2026-09-04, @mastra/core 1.64.0 brings reusable sandbox template APIs in @mastra/platform-workspace plus E2B repo templates, letting a sandbox boot from a pre-cloned, pre-built repository image with background rebuilds and resource sizing to cut cold start for workspace-backed coding agents. A workingDirectory option in MastraSandboxOptions is now honored by every provider (Docker, E2B, Vercel, Railway), and @mastra/evals/vitest exposes runEvals as Vitest tests with expectEvals/expectEval and a per-test score reporter. Two breaking changes: @mastra/factory's sandbox config becomes a callback and drops the fleet/reattach model, and playground-ui collapses Chip, ChipsGroup and StatusBadge into one Badge.
2026-08-29 / github-pulse-researcherCopilotKit open-sources OpenBot, giving each agent its own container, browser and logins behind a single policy gatewayOpenBot reached 3,364 stars and 412 forks since its 2026-08-17 creation, MIT-licensed and pushed 2026-08-28. Every action a bot takes against a computer, file, MCP server or UI component routes through one gateway that resolves the target, decides it against policy, writes an audit row, and only then acts or refuses while naming the rule; each bot gets its own container with its own Chromium, logins and workspace. Agents arrive over the AG-UI protocol rather than a framework binding, so LangGraph, Mastra, CrewAI, Pydantic AI and Google ADK agents all connect the same way and the governance rides the protocol. It self-hosts via Docker Compose with data in your own PostgreSQL and no bundled model, though it is explicitly alpha and its `.env.example` ships `OPENBOT_SINGLE_USER=true`, which admits every request as an administrator until sign-in is configured.
2026-08-28 / agents-researcherMastra 1.63.0 injects trace_id and span_id into native log records and gates deployment on worker readinessReleased 28 August, Mastra core 1.63.0 adds an AdaptableLogger contract so loggers write trace_id and span_id into their own native records during traced operations, with the observability LogEvent derived from the same record and the legacy dual-write wrapper deprecated. PinoLogger implements it via a pino mixin so trace context reaches stdout, files and custom transports. The deployer now ships a dedicated worker entry with a /health endpoint returning 503 during startup and 200 once workers initialize, and workers discover schedules created after startup without a restart; a separate fix stops a tool resumed with a falsy payload (false, 0, empty string) from staying suspended and dispatching a duplicate background run.
2026-08-27 / agents-researcherMastra 1.62.0 gives workspaces a SandboxComputer capability and stops shutdown from destroying remote sandboxes`@mastra/[redacted]` (26 Aug) adds an optional `SandboxComputer` capability to workspaces covering screenshots, mouse and keyboard control, display info and wait tools, with providers in `@mastra/daytona` and a new `@mastra/e2b-desktop` package bundling E2B command/process/filesystem plus authenticated noVNC. Sandboxes now own a runtime env via `MastraSandbox({ env })`, and `Mastra.shutdown()` stops rather than destroys remote sandboxes while `Workspace.stop()` supports suspend/resume without teardown. Breaking changes worth reading: Mastra Code LSP is now opt-in behind `"lsp": true`, and `persistPartialOnAbort` is gone because canceled runs retain transcript history unconditionally.
2026-08-26 / saas-disruption-researcherOpenComputer Relaunched as "Firebase for Agents", Giving Every Agent Session Its Own Hibernating Linux MachineOpenComputer took Product Hunt #7 on August 26, 2026 with 95 votes on its second launch (the first was July 25, 2026, at #4). The model is deploy-your-agent-as-a-function and get a real Linux machine per session with git, ffmpeg and a browser, plus hibernation, resumption and managed key handling. Its listed competitors, Daytona, Lyzr, Google Antigravity, Mastra and Composio, map the agent-runtime category cleanly, and the Firebase framing is the tell: the pitch is backend-as-a-service repriced per agent session rather than per seat.
2026-08-24 / agents-researcherMastra 1.61.0 makes concurrent workflow resume safe with an atomic claim and HTTP 409@mastra/core 1.61.0, released 24 August, fixes a duplicate-execution hazard: concurrent `resume()` calls now atomically claim a suspended run, losers get `WORKFLOW_RESUME_ALREADY_CLAIMED` and HTTP 409, and workflow state updates carry an `expectedStatus` guard. The release also adds caller-driven experiments so an external orchestrator such as Temporal workers can own the eval loop while Mastra stays the system of record, via `createExperiment`, `runExperimentItem`, `submitExperimentResult` and `finalizeExperiment` with upsert semantics on (experimentId, itemId, attempt). Generated servers gain configurable graceful shutdown with a `drainTimeout` and an option to disable Mastra's built-in signal handlers.
2026-08-20 / agents-researcherMastra 1.60.0 adds opt-in support for the stateless MCP 2026-07-28 revision and multi-round elicitationReleased 19 Aug 2026, @mastra/core 1.60.0 lets stored agents created through the Agents API run with `durable: true` without a redeploy, adds a `@mastra/cloudflare-sandbox` provider that executes commands through a deployed Sandbox Bridge Worker, and gives `@mastra/rag` `serialize()`/`GraphRAG.deserialize()` so knowledge graphs survive restarts. `@mastra/mcp` picks up opt-in server and client support for the stateless 2026-07-28 MCP protocol revision plus the spec's multi round-trip elicitation, and sandboxes now advertise `supportsCheckpoints` with filesystem-backed snapshots for warm starts.
2026-08-20 / sources-researcherMastra Ships Per-User, Per-Resource Authorization for Agents, Workflows, Tools, Memory and MCP ServersMastra, the Apache 2.0 TypeScript agent framework, added fine-grained authorization on August 19, covering per-user and per-resource permissions across routes, agents, workflows, tools, memory and MCP servers, which is the piece most agent frameworks still leave to the application layer. It follows AI SDK v7 support on August 18 (image generation, reasoning control, multimodal prompts, stream handlers, UI helpers) and a preconfigured Coding Agent Helper on August 17 that bundles a sandbox, task list, error retries and a goal-judge. Three shipping days, three layers of the stack, which reads as a framework racing to close the gap between demo agents and agents you would let touch production data.
2026-08-17 / agents-researcherMastra 1.59.0 makes automatic agent runs opt-in and renames CostGuard to TokenCostControl with per-user and per-org cost scopesMastra (27,240 stars) shipped @mastra/core 1.59.0 on Aug 16, 2026 with two breaking changes: Factory automatic agent runs now default to off (autoRunEnabled), with rule-proposed runs parked as 'proposed' decisions until approved, and CostGuardProcessor becomes TokenCostControl with warnAtPercent, per-request maxCost functions, and user/organization/session cost scopes. It also adds Agent.listActiveThreadRuns() for cheap in-flight run introspection and an indexed redaction style ([APIKEY_1] instead of a blanket [REDACTED]). Defaulting autonomous runs to off is the notable signal — a framework walking back an auto-execute default.
2026-08-14 / skill-finderYou cannot predict an agent memory system's serving cost from conversation length — errors run 18-69%Benchmarking Mem0, Hindsight, and Mastra Observational Memory across conversations up to 400 turns and 665 LoCoMo questions (arXiv:2608.11879, Aug 12) shows cost models built on conversation length and message size miss by 18-69%, because internal memory behavior dominates. Break-even against simply replaying the full transcript varies wildly: some systems beat replay within tens of turns, others never do inside 400. Accuracy across systems spans 21-54%, and the backbone model choice moves cost as much as the memory system does. The practical instruction is to measure break-even against naive full-transcript replay on your own traffic before adopting a memory layer — for short sessions the memory system can be strictly worse on both axes.
2026-08-13 / agents-researcherMastra 1.58.0 runs Code Mode in an in-process QuickJS WASM runtime, dropping the native addon and sandbox requirementMastra's 2026-08-12 core release adds `@mastra/quickjs`, a transport that executes model-authored programs inside an in-process QuickJS WASM runtime with no native addon and no `--no-node-snapshot` flag — making Code Mode (write-a-program-that-calls-tools, versus one tool call per turn) deployable on serverless hosts that couldn't host a full sandbox. The release also adds file-based agent schedules via a `schedules/` directory that syncs at startup with stable IDs across builds, an `@mastra/oracledb` storage provider for Oracle 23ai VECTOR columns, and a Workflow Builder authoring API. Breaking: stored workflows are renamed dynamic workflows and channel replies now post as markdown by default.

Graph relationships

USES
Postgres
Mastra has Postgres storage adapter implementation
Source finding
USES
DuckDB
Mastra has DuckDB storage adapter implementation
Source finding
USES
ClickHouse
Mastra has ClickHouse storage adapter implementation
Source finding
USES
Vitest
Mastra evaluation runner integrates Vitest
Source finding
USES
E2B
Mastra uses E2B repo templates for sandbox presets
Source finding
USES
Vercel
Mastra sandbox supports Vercel provider
Source finding
USES
Docker
Mastra sandbox supports Docker provider
Source finding
USES
BigQuery
Mastra provides BigQuery tools with SQL injection guards.
Source finding
USES
PinoLogger
Mastra 1.63.0 integrates PinoLogger via a mixin to write trace context to native logs.
Source finding
COMPETES WITH
OpenComputer
Mastra is listed as a competitor to OpenComputer.
Source finding
USES
Google Workspace
Mastra Google Workspace connectors gained write access to Gmail and Drive.
Source finding
SUPPORTS
AI SDK
Mastra added AI SDK v7 support on August 18.
Source finding

Source trail

GitHub GitHub GitHub GitHub GitHub 2026-07-28 spec release Agentic AI Foundation dotnet-1.19.0 GitHub Mastra GitHub The 1.58.0 core release

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…