Ordewell is an open-source task orchestration harness for coding agents. Built as a TypeScript monorepo, it accepts high-level software engineering goals and decomposes them into ordered, dependency-aware plans that coordinate multiple agent executions. In daily use, developers interact with Ordewell through a dedicated terminal user interface (TUI), a VS Code extension with a React webview, or a local HTTP/WebSocket daemon on localhost. Each task in an execution plan can be individually configured with a specific runner backend, model resolution, thinking effort tier, and operational mode. Ordewell executes the dependency graph sequentially or concurrently, validating outcomes via a built-in VerdictEngine that assesses concrete execution evidence rather than model self-assertions. What differentiates Ordewell from standard CLI coding agents is its decoupled orchestration architecture. It separates planning, model resolution, execution runner plugins, and verdict evaluation into discrete modules. It also incorporates an extensible slash-command skills system and an offline benchmarking harness with mock providers to test agent workflows without live API keys. Ordewell is distributed as open-source software via npm (under the `ordewell` and `@ordewell/cli` packages) and the VS Code Marketplace.
Dependency-aware task planning — Converts complex engineering objectives into directed task graphs with granular task-level configurations. - Evidence-based verdict engine — Evaluates task success against measurable execution results and build artifacts rather than model opinion. - Modular runner registry — Routes individual subtasks to distinct agent runners, models, and thinking effort settings. - Multiple interfaces — Supports a pure reducer-based terminal TUI, a VS Code extension webview, and a local WebSocket/HTTP daemon. - Built-in skills subsystem — Supports custom and built-in slash-command skills (such as specification generation and plan interrogation). - Offline test harness — Includes benchmark tooling with mock providers for executing end-to-end orchestration tests without network access or API keys.
Use cases
Use Case: Multi-Stage Codebase Refactoring Orchestrate multi-step architectural migrations by decomposing tasks into dependency graphs. Developers can assign fast models to lightweight file moves and high-reasoning models to complex logic transformations while tracking execution state in the TUI.
Use Case: Verified Automated Implementation Execute agent tasks that require strict validation before downstream tasks begin. Ordewell's VerdictEngine checks build output, tests, and diffs to confirm success before marking milestones complete.
Use Case: Agent Harness Testing and Benchmarking Validate orchestration logic, prompt adjustments, and runner behavior offline. Developers can run local benchmark drives using mock providers without incurring LLM API token costs.
Who it is for
Ordewell is designed for software engineers and tooling authors who need structured, multi-step task planning with deterministic verification across CLI and IDE environments. It is not suitable for developers looking for a simple single-turn chatbot or an unguided, single-prompt shell assistant.
Install guide
Installation Install the Ordewell CLI globally via npm: bash npm install -g ordewell Alternatively, install the scoped CLI package directly: bash npm install -g @ordewell/cli
First Run Launch the Ordewell TUI in your project directory: bash ordewell Configure your provider API keys in your environment (for example, ANTHROPIC_API_KEY or OPENAI_API_KEY) or run against the offline mock provider during development.
Example Session Start an orchestration session with a specific objective: bash ordewell "Refactor auth middleware to support JWT refresh tokens and add unit tests"
SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
Agent Runbook — Agent Runbook is an open-source contract-based multi-agent skill framework developed by KnoxOps. It acts as an orchestrator and compiler that…
Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…