Explicit powers. Enduring duties. An Apache-licensed authority and continuity layer for agent workflows.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/zerohourzulu/continuity && cp continuity/*.md ~/.claude/agents/Subagents overview
> **Core 0.3 preview:** [Build a fresh case](docs/CORE-0.3-QUICKSTART.md), [try the protected MCP tool](docs/MCP-PACKAGE.md), or [run the public tests](docs/CORE-0.3-TESTING.md). The original 0.2.2 evaluation releases remain available. [](https://zerohourzulu.github.io/continuity/) [](https://zerohourzulu.github.io/continuity/) # Continuity — agents change; responsibility remains **[Explore the interactive demo →](https://zerohourzulu.github.io/continuity/)** · [Start here](docs/START-HERE.md) · [Developer guide](docs/DEVELOPER.md) · [Security and limits](SECURITY.md) **Developer preview · Apache 2.0.** [Release status](RELEASE-STATUS.md). A process supervisor can start Agent B. Continuity records which role B occupies, which powers it has, what happened before, and which unfinished duties survive the change. A replacement receives its explicitly granted powers; an unfinished duty does not silently grant more authority. The demonstration follows a security investigation interrupted by an agent replacement. The old request is refused, the investigation stays OPEN, and the successor’s review permission is checked independently. ## Choose your path | You want to… | Start here | What you will learn | |---|---|---| | Understand the idea without installing anything | [The story and answer key](docs/READ-THE-RESULT.md) | Why an unfinished duty and permission are separate. | | Run and inspect a replacement | [Tutorial](docs/TUTORIAL.md), then [operator commands](docs/OPERATOR.md) | What was refused, who holds the duty and what B may do. | | Evaluate or integrate the code | [Core 0.3 quickstart](docs/CORE-0.3-QUICKSTART.md) | Create your own permissions, try a protected tool, then connect a framework or policy engine. | ## Run the tutorial Use **Node 22.18+ (22.x), 24.x or 26.x** on macOS or Linux. Prefer the latest patch of your chosen release. No global pnpm or Python is needed for this tutorial. [Full quickstart, including archive extraction](docs/QUICKSTART.md). Get the public source; no GitHub account is needed: <!-- quickstart:clone --> ```sh git clone https://github.com/zerohourzulu/continuity.git cd continuity ``` <!-- /quickstart --> **See the result first, without installing dependencies:** <!-- quickstart:recorded --> ```sh node examples/recorded.mjs ``` <!-- /quickstart --> Expect ALLOW for reviewing the investigation and DENY for collecting another packet. This inspects a bundled recorded case; it does not execute a new action. **Generate your own evidence:** <!-- quickstart:run --> ```sh node tools/setup.mjs node tutorial/start.mjs ``` <!-- /quickstart --> Expect **PASS — duty remains OPEN; B has no collection power**, then **VERIFIED**. Setup downloads locked dependencies with scripts disabled. The tutorial then runs locally using synthetic data and public test keys. It prints your new case name and exact follow-up commands. Rerunning creates another case and preserves earlier evidence. Change one permission: <!-- quickstart:compare --> ```sh node tutorial/start.mjs --deny-review ``` <!-- /quickstart --> B still inherits the duty, but its review permission becomes DENY. [Expected output and explanation](docs/TUTORIAL.md) · [Setup checks and recovery](docs/TROUBLESHOOTING.md). ## Choose your holder of record. Keep records locally, or choose a chain-backed deployment to make selected history publicly verifiable. Cryptographic commitments can let authorized reviewers check private records without publishing their contents. This tutorial runs locally; each deployment has its own privacy, availability and finality requirements. ## Explore and build | Your next step | Where to go | |---|---| | See the idea and recorded comparison | [Interactive demo](https://zerohourzulu.github.io/continuity/) | | Inspect your new run and optional recorded Linux evidence | [Operator guide](docs/OPERATOR.md) | | Integrate an authority check | [Developer guide](docs/DEVELOPER.md) · [Executable reader example](examples/read-investigation.mjs) | | Try optional native enforcement mechanics | [Disposable Linux lab](docs/LINUX-LAB.md) | | Review source provenance and validation | [Validation](VALIDATION.md) · [Presentation checks](docs/PRESENTATION-VALIDATION.md) · [Provenance](SOURCE-PROVENANCE.json) | | Extend the presentation | [Website maintenance](docs/WEBSITE.md) | Presentation maintainers can find the separate owner-private edition in [website maintenance](docs/WEBSITE.md). The public walkthrough needs no account. ## Contribute and explore Read the [short development history](docs/DEVELOPMENT-HISTORY.md) from Core 0.1 to the current reference implementation. [Contributions](CONTRIBUTING.md) and [public RFCs](docs/RFC.md) are welcome; an RFC is useful for changes to protocol behavior or security boundaries. ## Scope Core 0.2.2 is local reference software. It is not a hostile-agent sandbox, production credential system or autonomous cyber defender. The website selects recorded results; the downloaded tutorial executes Core. Real integrations must mediate every consequential operation through a protected executor. [Security boundaries](SECURITY.md). The source, tutorial, tests, reader and website are included here and in the complete evaluation download. Earlier editions remain available as historical releases; use evaluation.6 for the commands above. [Package overview](docs/PACKAGE-OVERVIEW.md) · [Presentation provenance](PRESENTATION-PROVENANCE.json). [Release status and licensing](RELEASE-STATUS.md) · [Apache 2.0 license](LICENSE) · [Third-party notices](THIRD-PARTY-NOTICES.md) ## Embed the engine Try the [standalone developer package](docs/SDK-QUICKSTART.md): install the supplied JavaScript SDK tarball in a separate application, create one authorized synthetic packet, and inspect why refused requests create none. Includes TypeScript declarations and an offline consumer check. This is an evaluation interface around unchanged Core0.2.2. ## Shared Core integration preview The [shared-package preview](docs/SHARED-CORE.md) connects the cooperating remote tools and MCP evidence tool to one Core dependency. Try [native LangChain tools and lost-reply recovery](packages/remote-tools/README.md), or the [MCP evidence tool](docs/MCP-PACKAGE.md).
What people ask about continuity
What is zerohourzulu/continuity?
+
zerohourzulu/continuity is subagents for the Claude AI ecosystem. Explicit powers. Enduring duties. An Apache-licensed authority and continuity layer for agent workflows. It has 0 GitHub stars and its last recorded update is dated 2026-09-23.
How do I install continuity?
+
You can install continuity by cloning the repository (https://github.com/zerohourzulu/continuity) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is zerohourzulu/continuity safe to use?
+
Our security agent has analyzed zerohourzulu/continuity and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains zerohourzulu/continuity?
+
zerohourzulu/continuity is maintained by zerohourzulu. The last recorded GitHub activity is dated 2026-09-23, with 0 open issues.
Are there alternatives to continuity?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy continuity to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/zerohourzulu-continuity)<a href="https://claudewave.com/repo/zerohourzulu-continuity"><img src="https://claudewave.com/api/badge/zerohourzulu-continuity" alt="Featured on ClaudeWave: zerohourzulu/continuity" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.