Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
1–24 of 108 tools for “durable-execution”
Clear allBuild resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. Covers the critic
OfficialSkillApache-2.0★ 918 in collectionNo key
Easily deploy Haystack pipelines as REST APIs and MCP Tools.
in the readmeand Agents as production APIs: REST, OpenAI-compatible chat, MCP, A2A, and durable executions that survive restarts.**  — low-level orchestration for durable execution, custom control flow, and stateful workflows. LangChain agents run on top
OfficialSkillMIT★ 1.3k in collectionNo key
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel,
in the skill texttime travel, Store, and subgraph persistence modes. LangGraph's persistence layer enables durable execution by checkpointing graph state: - **Checkpointer**: Saves/loads graph state at every super-step
OfficialSkillMIT★ 1.3k in collectionNo key
The open-source managed agent platform. A self-hostable alternative to Claude Managed Agents and OpenAI's Agents API.
Hosted by authorApache-2.0★ 2.9kNo key
Verifiable execution for durable AI agents: policy-bound workflow compiler, hash-chained journal, offline replay, and Merkle + Ed25519 proofs. Go.
GoMIT★ 188No key
Agentic-first Cursor Rules powered by MiniMax M3 - clarify-first prompting, interleaved thinking, and full tool orchestration for production-ready AI coding
in the readmeMiniMax M3 Cursor Rules #### A durable execution spine for repo-scale engineering on M3 + Cursor 3.7 — with frontier-agent coding judgment and reasoning protocols distilled into
SkillMIT★ 126No key
CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained t
in the readmeany language), and `src/continuum/otel.py` (OpenTelemetry bridge). Recipes are in `docs/recipes/` and `references/adapters.md`. | | Durable execution | What happened before a crash and what can be replayed without losing
PythonApache-2.0★ 24No key
Harness-oriented agent system framework for production-grade LLM agent applications
in the readmeSession references a DomainPack and optional Session profile. | | `Run` | Represents one durable execution under a Session. | | `Event` | Records source-of-truth facts from which state, replay
SkillApache-2.0★ 447No key
Druks runs agent apps on your own infrastructure: durable runs that survive restarts, human approvals, and full history. Apps install as Python packages.
in the readmerunbook for prerequisites, access control, verification, and rollback. ```text trigger ──> app workflow ──> durable step ──> agent ──> sandbox │ │ │ │ │ └─ harness CLI │ └─ result checkpointed in Postgres ├─ event ──> feed / app reaction
PythonMIT★ 17No key
Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop
in the readmeSonnet. (`rote emit` needs no LLM; see below.) # Default target is DBOS: durable execution as a plain Python library, # no orchestrator to run, SQLite for dev
PythonApache-2.0★ 8No key
A full agent framework on the Vercel AI SDK, durable from the core: exactly-once tool calls, deterministic replay, time-travel.
in the readmeTürkçe **A thin correctness layer on top of the Vercel AI SDK — durable execution without standing up a server.** It doesn't touch the AI SDK
Node.jsApache-2.0★ 2Few starsNo key
Django DRF's developer experience. Fully async. Built on FastAPI. With native MCP tooling and column-level control over what your LLM can see.
in the readmepath, generated model APIs, application policy and tenant enforcement, and opt-in durable execution. Choose it when that shared contract is useful enough to justify adopting
PythonMIT★ 18No key
Build and operate production-safe agents that run in your own environment.
in the readmeyour compute and governs it from a persistent control plane. ## Why Charter - **Durable execution.** A run parks for a human and resumes days later on another
PythonApache-2.0★ 17No key
Durable MCP Tasks on infrastructure you already own — local, SSH, and Slurm.
in the readmeAwaitless ` returns either: - `{ action: 'execute', execution?: ... }` — proceed, optionally attaching host policy/approval provenance; or - `{ action: 'return
Node.jsApache-2.0★ 1Few starsNo key
TypeScript agent framework with zero runtime dependencies — agents, memory, workflows, durable agents, signals, schedules. Now chasing mastra's proven feature surface inside that lightweight axis — se
in the readmethe roadmap . > **Status:** pre-1.0. Agents, memory, workflows, the harness trio — durable agents, signals, > schedules — and the eight capability packages are implemented and verified > ( roadmap
Node.jsApache-2.0★ 1Few starsNo key
Who stands behind it