# humanlayer/humanlayer

The best way to get AI coding agents to solve hard problems in complex codebases.

Repository: https://github.com/humanlayer/humanlayer
Canonical: https://ross.abutalabs.com/products/humanlayer
Homepage: https://humanlayer.dev/code
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: agents, ai, human-in-the-loop, llm, llms, humanlayer, amp, claude-code, codex, opencode
Last push: 2026-06-19T03:27:53+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 88, release rhythm 50, longevity 54
- inputs: {"age_days": 758, "days_push": 75, "days_rel": 253, "gap_med": 1, "n_releases_24m": 74}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11340, forks 942 (observed 2026-08-28T04:10:46.805083+00:00)

## What it is
HumanLayer is a multiplayer coding agent IDE and cloud control plane for orchestrating AI coding agents, bringing agent sessions, plan artifacts, and code diffs together for team collaboration. The original open-source repo is deprecated, with the project rebuilt as a commercial product at humanlayer.com.

## Use cases
- run AI coding agents on complex large codebases
- collaborate with a team on agent sessions and code diffs
- manage plan artifacts and design docs alongside agent work
- orchestrate background coding agents in the cloud
- review and refine agent-generated designs before implementation
- bring your own compute and agent harness to a shared workspace

## When to choose
- your team uses AI coding agents like Claude Code, Codex, or Amp on shared codebases
- you want human-in-the-loop review of agent plans and artifacts
- you need a multiplayer workspace for coordinating agent-driven engineering work

## When to avoid
- you want the actively developed open-source version - this repo is deprecated
- you need a simple single-user agent runner without team collaboration
- you require a permissive open-source license - the rebuild is commercial

## Facets
- artifact type: application
- maturity: abandoned
- function: agent-framework, developer-tools, workflow-automation
- domain: developer-tools, large-language-models
- platform: windows, cross-platform, cloud
- tags: human-in-the-loop, coding-agents, ai-coding, claude-code, multiplayer, deprecated, ai-agents, automation, macos, linux

## Member repositories
- humanlayer/humanlayer (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:46.805083+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:15:43.183609+00:00, confidence not recorded.
  - readme: https://github.com/humanlayer/humanlayer (fetched 2026-08-28T04:10:46.805083+00:00, sha 026a6c9e1372)
  - homepage: https://humanlayer.dev/code (fetched 2026-08-29T08:14:48.439082+00:00, sha 58347c2399c3)
- Data as of 2026-08-30T08:39:29.467469+00:00.