Zeroshot is an open-source AI coding agent harness and orchestration framework developed by The Open Engine organization. Designed to coordinate agentic workflows with strict validation gates, it provides a structured runtime environment where AI agents can execute development tasks, invoke custom skills, and verify repository modifications safely. In day-to-day development, Zeroshot operates through terminal commands, automated hooks, and pre-commit integrations. It orchestrates agent execution by pairing language model workflows with deterministic runtime verifications, integrating specialized toolsets like Opcore to maintain graph states, enforce repository policies, and generate verifiable command proofs before changes are accepted. What distinguishes Zeroshot from unconstrained code-generation CLIs is its emphasis on guardrails, change verification, and graph-assisted repository awareness. Rather than simply streaming code edits to disk, it executes within a structured framework that enforces continuous validation across agent hooks, local test suites, and CI pipelines. Zeroshot is open-source software distributed via GitHub. The repository reflects an actively maintained codebase combining Node.js and Rust components with strong automated test coverage and community contributions.
Opcore gate enforcement — Integrates with Opcore to validate introduced repository changes against strict operational criteria. - Automated change validation — Enforces verification steps across agent lifecycle hooks, pre-commit triggers, command proofs, and CI pipelines. - Persistent graph maintenance — Tracks repository state and dependency relationships to inform agent context and prevent regressions. - Skill-based agent architecture — Organizes capabilities into modular agent skills located directly within repository configuration paths. - Hybrid Node.js and Rust runtime — Leverages a performant core with Node 22 compatibility for cross-platform task orchestration. - CI/CD pipeline readiness — Seamlessly integrates automated status checks and gating logic into automated pull request workflows.
Use cases
Use Case: Safe Agent-Driven Refactoring Developers can deploy Zeroshot to execute complex codebase refactors while automated Opcore gates and introduced-change validation ensure that no untested or policy-breaking modifications bypass local checks.
Use Case: Continuous CI Agent Validation Teams can integrate Zeroshot into CI workflows to automatically run change proofs, verify graph consistency, and confirm that automated PR modifications meet repo-level policies before merging.
Use Case: Modular Agent Skill Execution Engineers can build and execute custom agent skills within .agents/skills/ to automate specialized tasks like documentation generation, graph updates, or dependency migrations under a unified CLI harness.
Who it is for
Zeroshot is aimed at software engineers, platform teams, and repository maintainers who need strict guardrails, policy gates, and verifiable proofs when running AI coding agents against production codebases. It is less suitable for casual developers looking for a lightweight, zero-configuration single-file code assistant.
Install guide
Installation Zeroshot requires Node.js 22+. Clone the repository and install dependencies locally: bash git clone https://github.com/the-open-engine/zeroshot.git cd zeroshot npm install(Note: Package manager binary distribution commands may vary as releases mature; building from source via npm is standard).
First Run Verify that the environment meets operational requirements and that the Opcore validation engine is active: bash # Verify status and repo graph readiness npm run opcore:check opcore status --repo . --json Run the test suite to ensure runtime integrity: bash npm test npm run typecheck
Example Session Execute agent verification and status inspection against the current workspace: bash # Run change proof validation before committing agent edits opcore status --repo . npm run lint
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,…