#durable-execution

Agents you can inspect, replay and trust. An agent framework for TypeScript and Python, built on an append-only event log.

Host-neutral durable DAG workflows for Agents: CLI-native access, fixed MCP gateway, on-demand Skills, triggers, replay, and visual Canvas.

Local-first AI workflow orchestration with durable runs, explicit resume, project-root boundaries, 33 agents, and 7 skills.

Embeddable TypeScript engine for durable, budget-bounded, testable multi-agent LLM workflows: byte-deterministic journal replay, hermetic VCR cassettes, hard USD budgets, adaptive orchestration, ModelKnowledge. Apache-2.0.

Agents you can replay, fork and trust. An agent framework for TypeScript and Python, built on an append-only event log.

Governed actions, human approval, durable execution, reconciliation and audit for AI agents acting on real business systems.

Unofficial community mobile app for pi: run a coding agent loop on your Android phone, with a self-hosted sandbox and credentials that never enter it

中文版｜用 6 个固定故障场景，比较 Agent 在超时、限流、审批和重启后的行为。

Durable, approval-gated runtime for inspectable AI tasks

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, model routing, edge inference, RAG, memory, multi-agent orchestration, security, and observability. 14 runnable proof-of-concept phases.

Durable payout pipeline on Temporal - durable execution, retries, saga compensation, two-layer idempotency, human-in-the-loop review, and an advisory LLM analyst for grey-zone fraud cases. Demo project, not a real payment system.

Official SDKs and CLI for the nvoken durable agent runtime

A production-grade Rust framework for building typed, durable, and observable agent systems, with graph workflows and native MCP/A2A support.

Durable, resumable execution for long-horizon AI agents.