Harbor
PulseGate's liveness check found it on 6 Oct 2026; it has been in the index since 27 Sep 2026. How this is checked
Harbor captures decisions, conventions, and gotchas from team communication, pull requests, and documentation, then supplies relevant rules to coding agents during their work. It is designed for engineering teams using agents such as Claude Code and Codex.
Inferred · not functionally tested
Overview
6 featuresPurpose: Keeping coding agents aligned with a team's decisions, conventions, and project-specific gotchas.
Inferred · not functionally tested
Audience: software engineering teams using AI coding agents
Inferred · not functionally tested
Functions: agents, rag, collaboration
Inferred · not functionally tested
Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: unknown
Recorded constraints: pricing: unknown · license: Proprietary · platforms: WEB · deployment: browser, cli, macos, windows, linux, cloud_managed
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: gethrbr.com. These links do not verify the individual claims.
In the Memory & skills space, Harbor takes a focused approach. Inferred · not functionally tested: It focuses on keeping coding agents aligned with a team's decisions, conventions, and project-specific gotchas. Inferred · not functionally tested: It is built as a B2B product for software engineering teams using AI coding agents. Basis unknown · not verified: It runs on the web, the command line, macOS, Windows, and Linux.
Harbor builds and maintains Harbor. Inferred · not functionally tested: Key capabilities include decision capture, agent context, and rule citations. Basis unknown · not verified: Catalogued interfaces include an MCP server. Access is currently waitlist-only.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Decision capture
- Agent context
- Rule citations
- Slack learning
- Pull request learning
- Documentation learning
Topics: Inferred · not functionally tested
Built with & integrations
- AWS
- x-amz-cf-id header · x-amz-cf-pop header · via header
- Next.js
- x-nextjs-cache header · x-nextjs-prerender header · /_next/static/ in the HTML
Trust & compliance
Indexing history
2What PulseGate has recorded for this listing
- Indexed6 Oct · 11:31 UTCDo coding agents need memory or documentation? seen via Hacker News firehose (Algolia)Source: Hacker News firehose (Algolia) · Open
- Indexed27 Sep · 15:19 UTCIs AGENTS.md useful? What the research found seen via Hacker News firehose (Algolia)Source: Hacker News firehose (Algolia) · Open
Frequently asked questions about Harbor
- What is Harbor?
- Inferred · not functionally tested: Harbor focuses on keeping coding agents aligned with a team's decisions, conventions, and project-specific gotchas. It is catalogued under Memory & skills on PulseGate.
- Who is Harbor for?
- Inferred · not functionally tested: Harbor is a B2B product built for software engineering teams using AI coding agents.
- What platforms does Harbor run on?
- Basis unknown · not verified: Harbor runs on the web, the command line, macOS, Windows, and Linux.
- Is Harbor still active?
- PulseGate's liveness check found it on 6 Oct 2026.
- What are alternatives to Harbor?
- Similar projects tracked by PulseGate include Harbor, Harbor, and Hyts.HarborHarborHyts
- Who makes Harbor?
- Harbor is developed by Harbor.
- Does Harbor have an API or integrations?
- Basis unknown · not verified: Yes — Harbor exposes an MCP server.
Similar projects
Closest matches by what these projects do