![\"\"](\"https://raw.githubusercontent.com/open-multi-agent/open-multi-agent/main/.github/brand/logo-mark-light.svg\"){kind=logo}
\n OMA\n
\n \n Agents your organization can own, approve, and audit.
\n OMA (Open Multi-Agent) is a self-hosted TypeScript agent runtime: consequential actions wait for durable, tamper-evident approvals, and every run leaves a record you can verify offline, byte for byte.\n
\n ![\"npm](\"https://img.shields.io/npm/v/@open-multi-agent/core\")
![\"Node.js](\"https://img.shields.io/node/v/@open-multi-agent/core\")
![\"CI\"](\"https://github.com/open-multi-agent/open-multi-agent/actions/workflows/ci.yml/badge.svg\"){kind=icon}
\n ![\"Supply](\"https://github.com/open-multi-agent/open-multi-agent/actions/workflows/supply-chain-audit.yml/badge.svg\"){kind=icon}
\n ![\"MIT](\"https://img.shields.io/badge/license-MIT-green\"){kind=icon}
![\"codecov\"](\"https://codecov.io/gh/open-multi-agent/open-multi-agent/graph/badge.svg\"){kind=icon}
\n
\n Website ·\n Docs ·\n npm ·\n Discussions\n
\n\n\n English · 中文\n
\n\n\n ![\"OMA](\"https://raw.githubusercontent.com/open-multi-agent/open-multi-agent/main/.github/brand/demo-dashboard-hero.gif\")
\n
The offline Run Viewer replaying a real run from the trace store: task DAG, span waterfall, and per-task evidence, with no hosted service involved.
\n\n### Run store and execution leases\n\nA checkpoint says what a run can resume from; it does not say who is allowed to resume it, so two workers can load the same snapshot and both advance it. The opt-in `runStore` adds the missing authority: one authoritative record per run holding its lifecycle status, an execution lease, and a monotonic fencing token. A worker acquires the lease before it dispatches anything, every checkpoint write is fenced with its token, and a run taken over by another worker stops instead of overwriting the new owner's state. Suspended runs stop depending on a live process, and an operator can cancel or resume one from outside the worker. Off by default, unchanged behavior when off, and documented in the [run store guide](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/run-store.md).\n\n### Run journal\n\nWhen a long run goes wrong, the record usually missing is what each agent actually saw at the moment it was asked. The opt-in run journal keeps it: every message and tool result as an appended event, plus the exact block a context strategy put in place of the turns it dropped, so a finished run can be read back instead of reconstructed by guesswork. `verifyRun()` then checks offline that every block the model saw is reproducible from the log rather than trusting the log's own account of itself, which establishes order and lineage rather than tamper-evidence, and `restore()` can resume from the last appended event instead of the last snapshot. It is off by default, costs nothing when off, and is documented in the [run journal guide](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/run-journal.md).\n\n## Documentation\n\n| Area | Guides |\n|---|---|\n| Build agents | [Providers](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/providers.md), [structured input](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/structured-input.md), [tools](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/tool-configuration.md), [sandbox and shell](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/sandbox-and-shell.md), [MCP](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/mcp.md), [context](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/context-management.md) |\n| Run reliably | [Evaluation](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/evaluation.md), [evaluation in CI](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/evaluation-ci.md), [checkpoint & resume](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/checkpoint.md), [run store and leases](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/run-store.md), [durable approvals](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/durable-approvals.md), [adaptive recovery](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/adaptive-recovery.md), [execution routing](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/execution-routing.md), [model routing](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/model-routing.md), [consensus](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/consensus.md), [errors](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/errors.md) |\n| Control workflows | [Coordinator](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/coordinator.md), [plan preview & replay](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/plan-replay.md), [shared memory](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/shared-memory.md), [hooks and callbacks](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/hooks-and-callbacks.md), [streaming](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/streaming.md), [budgets and limits](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/budgets-and-limits.md), [external agents](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/external-agents.md) |\n| Operate | [Observability](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/observability.md), [Run Viewer](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/run-viewer.md), [CLI](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/cli.md), [production checklist](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/production-checklist.md), [glossary](https://github.com/open-multi-agent/open-multi-agent/blob/main/docs/glossary.md), [production examples](examples/production/README.md) |\n\n## Contributing\n\nIssues and PRs are welcome. For production examples, follow the [acceptance criteria](examples/production/README.md); for code changes, see the [contribution guide](https://github.com/open-multi-agent/open-multi-agent/blob/main/.github/CONTRIBUTING.md).\n\n## Contributors\n\n\n