{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/frameworks.durable-long-run/",
    "json": "https://www.anchorterminal.com/niches/frameworks.durable-long-run/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/frameworks.durable-long-run/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/frameworks.durable-long-run/index.min.md"
  },
  "markdown": "No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 0 | 18 | 25 | 11 | 9 |\n\n## What counts as done\n\nState is written to a named durable store after each step, a run killed mid-way resumes from the last completed step with a documented rule for the tool call that was in flight, cancelling keeps what was already streamed, and the docs show resume across a code change or new agent ids.\n\nMeasured, for our own tests: kill the process during step 3 of 5 and count repeated tool calls on resume.\n\nHow agents ask for it: run this report for every customer each night; resume the agent where it stopped after a crash; keep the conversation after the server restarts; cancel a run and carry on the thread\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **AgentOS (Framers Lab, Inc.)**: SqlCheckpointStore (SQLite or Postgres) ships, and resume marks write and external nodes complete with their recorded output while failed nodes re-run. The docs don't cover resume across code changes or what a cancel keeps.\n- **Agno (Agno Inc.)**: Runs persist to SQLite or Postgres and continue by run_id in a new process. I found no rule for a tool call in flight at a crash, and resume across code changes isn't documented.\n- **BoxLang AI (Ortus Solutions, Corp.)**: A checkpointer memory (cache or jdbc) stores suspended state and cancelRun stops at the next beforeLLMCall or beforeToolCall. No documented rule for a tool in flight at a crash or resume across code changes.\n- **Claude Agent SDK (Anthropic, PBC)**: Sessions persist and resume by id, and a SessionStore mirrors transcripts to your own store so a new container can hydrate. I found no rule for a tool call in flight when the process died; state on the container disk is lost on restart without a store.\n- **CrewAI (CrewAI, Inc.)**: Checkpointing ships JsonProvider and SqliteProvider; a restore skips completed tasks and rehydrates memory. No Postgres or Redis store, no rule for an in-flight tool call, and lambdas and bound-method callbacks are not restored.\n- **Cursor Agent SDK (Anysphere, Inc.)**: Sessions keep an append-only record of messages and tool calls that survives a restart, stop records turn.failed as cancelled, and tool effects mark writes run-once. The store is not named and resume across code changes isn't covered.\n- **Docker Agent (Docker, Inc.)**: Every message, tool call and sub-agent run is stored in a SQLite session.db and a run resumes by session id. No rule for a tool call in flight at a crash, and resuming mid-run differs from continuing a conversation.\n- **Agent Development Kit (ADK) (Google LLC)**: ResumabilityConfig logs completed steps and reinstates tool results, re-running the interrupted tool so tools run at least once; resume after modifying the workflow is not supported, and resume isn't available from ADK Web or the CLI.\n- **guilds.run (Cigale AI)**: Runs live in PostgreSQL; on restart, unfinished committed tool calls get an interrupted result, pending group dispatch resumes, and routines wake agents on schedules. Resume across a code change isn't documented, and a run that hit its tool-call cap can't be resumed.\n- **LangGraph (LangChain, Inc.)**: Postgres, SQLite and MongoDB checkpointers ship; checkpoints land at super-step boundaries and resume re-runs the node at least once, with idempotency-key guidance. Accounts: cancelling a run loses state since the last checkpoint (langgraph #5672, open) and Redis resume failed (#5074).\n- **LlamaIndex Framework (LlamaIndex, Inc.)**: Context.to_dict() snapshots a run for any store, resume re-dispatches pending events and re-runs a step that was mid-execution (at-least-once), and a DBOS integration exists. You write the store; an account hit serialisation errors for Gemini function calls in Postgres (llama_index #19992).\n- **Mastra (Kepler Software, Inc.)**: Durable agents run the loop inside a workflow; with Inngest each tool call is a memoized step retried independently. Storage is libSQL, PostgreSQL or MongoDB. Agent run snapshots are deleted when the run finishes, and resume across code change isn't covered.\n- **Microsoft Agent Framework (Microsoft Corporation)**: Workflow checkpoints at superstep ends go to in-memory, file or Cosmos DB storage, and the Durable Task extension keeps agent sessions across crashes for days. Upgraded workers need replay-compatibility checks, and agent-id changes broke resume for one account (#4793).\n- **OpenAI Agents SDK (OpenAI OpCo, LLC)**: Sessions ship for SQLite, SQLAlchemy, Redis and Dapr, and a RunState serialises with to_string() to resume an interrupted or cancelled run. No rule for a tool call in flight at a crash was found.\n- **Pydantic AI (Pydantic Services Inc.)**: Nine durable engines (Temporal, DBOS, Prefect, Restate, AWS Lambda and more) journal model and tool calls so a run survives a crash mid-step, and StepPersistence saves, resumes and forks runs. The overview doesn't cover resume across code changes or what a cancel keeps.\n- **Strands Agents (Amazon Web Services, Inc.)**: Session managers persist to local disk or S3 (SnapshotSessionManager recommended), with snapshot_latest used to resume after a restart. No Postgres or Redis store and no rule for a tool call in flight; the in-memory history gap of strands #33 is closed.\n- **TradingAgents (Tauric Research)**: Opt-in --checkpoint saves LangGraph state after each node to a per-ticker SQLite database so a crashed run resumes from the last step. No rule for an in-flight tool call; its tools only read data, so repeats have no side effect.\n- **AI SDK (Vercel Inc.)**: WorkflowAgent from @ai-sdk/workflow runs each tool call as a durable workflow step with retries and survives restarts; ToolLoopAgent itself is in memory. Durability depends on Vercel Workflow, and WorkflowAgent applies no default step limit.\n\n- not this job: NitroStack (Nitrostack Inc.): MCP Tasks cover long-running tool calls with progress, cancellation and a TTL, but there is no agent run state or checkpoint store; an account saw tasks still working past their TTL deleted (nitrostack #329, open).\n- not this job: smolagents (Hugging Face, Inc.): No checkpoint store or resume page in the docs index; an open account proposes state serialisation because none exists (smolagents #364).\n\n## What stops agents finishing\n\n- only an in-memory or file checkpoint store ships\n- history with provider-specific function-call objects fails to serialise to the store\n- resume fails when agent ids or code change between runs\n- a cancelled run loses everything after the last checkpoint\n\n## Around it\n\nBefore: agent-harnesses.scheduled-job. After: human-in-the-loop.durable-wait, agent-observability.debug-failed-run.\n\n## Where this comes from\n\nWeight 11 of 100 in Agent frameworks \u0026 SDKs: 7 of 61 accounts have this as their main job (share 11.5, rounded by largest remainder to sum 100)\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/frameworks.durable-long-run.json, or the MCP tool get_use_case with id frameworks.durable-long-run. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Run a long or scheduled agent job that survives restarts",
        "url": ""
      }
    ],
    "description": "Run a long or scheduled agent job that survives restarts: 0 companies fully do it, 18 with a limit, 25 carry the tag. Every listing in Agent frameworks \u0026 SDKs with the reason and a source.",
    "facts": null,
    "h1": "Run a long or scheduled agent job that survives restarts",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/frameworks.durable-long-run/",
    "published": "",
    "section": "agents",
    "title": "Run a long or scheduled agent job that survives restarts | Anchor…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/frameworks.durable-long-run/"
  },
  "tokens": {
    "markdown": 2000,
    "slim": 430
  },
  "version": 1
}
