Harbor
PulseGate's liveness check found it on 14 Sep 2026; it is registered on GitHub and has been in the index since 10 Jul 2026. How this is checked
Harbor is an open-source CLI framework designed for evaluating and optimizing AI agents and models in sandboxed environments. It allows developers and researchers to specify, run, and analyze agent tasks securely, supporting robust experimentation and benchmarking. Ideal for AI practitioners seeking controlled evaluation workflows.
Inferred · not functionally tested
Overview
5 featuresPurpose: Developers need a way to safely evaluate and optimize AI agents and models in controlled, sandboxed environments.
Inferred · not functionally tested
Audience: AI researchers and developers
Inferred · not functionally tested
Functions: agents, analytics
Inferred · not functionally tested
Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI · deployment: cli, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: harborframework.com · github.com. These links do not verify the individual claims.
Harbor is an Agent evaluation & testing project. Inferred · not functionally tested: Developers need a way to safely evaluate and optimize AI agents and models in controlled, sandboxed environments. Inferred · not functionally tested: Harbor is an open-source project aimed at AI researchers and developers. Basis unknown · not verified: The project is open source (Apache-2.0). Basis unknown · not verified: It runs on the command line, and it can be self-hosted.
Harbor first shipped in 2025. Development happens publicly on GitHub with 3.1k stars and 514 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include agent evaluation, sandboxed tasks, and CLI interface.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Agent evaluation
- Sandboxed tasks
- CLI interface
- Optimization tools
- Documentation
Topics: Inferred · not functionally tested
Built with & integrations
- Next.js
- x-nextjs-prerender header · /_next/static/ in the HTML · __next_f in the HTML
- Vercel
- x-vercel-id header · x-vercel-cache header
Trust & compliance
Indexing history
What PulseGate has recorded for this listing
Frequently asked questions about Harbor
- What does Harbor do?
- Inferred · not functionally tested: Developers need a way to safely evaluate and optimize AI agents and models in controlled, sandboxed environments. It is catalogued under Agent evaluation & testing on PulseGate.
- Who should use Harbor?
- Inferred · not functionally tested: Harbor is an open-source project built for AI researchers and developers.
- Is Harbor free?
- Basis unknown · not verified: Yes — Harbor is open source under the Apache-2.0 license and free to use.
- What platforms does Harbor run on?
- Basis unknown · not verified: Harbor runs on the command line. It can also be self-hosted.
- Is Harbor still active?
- PulseGate's liveness check found it on 14 Sep 2026. Its GitHub repository shows 514 commits in the last 90 days.
- What projects are similar to Harbor?
- Similar projects tracked by PulseGate include Harbor, Harbor, and Harbor.HarborHarborHarbor
- When did Harbor launch?
- Harbor first shipped in 2025.
- Is Harbor open source?
- Basis unknown · not verified: Yes — Harbor is open source under the Apache-2.0 license, developed on GitHub.
Similar projects
Closest matches by what these projects do