# Claw-AI-Lab/Claw-AI-Lab

One dashboard. An entire research team.

Repository: https://github.com/Claw-AI-Lab/Claw-AI-Lab
Canonical: https://ross.abutalabs.com/products/claw-ai-lab
Homepage: https://clawailab.ai/
Language: Python
License Family: other
Last push: 2026-06-15T12:39:02+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 87, release rhythm 35, longevity 11
- inputs: {"age_days": 167, "days_push": 79, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1353, forks 67 (observed 2026-08-28T04:04:28.618488+00:00)

## What it is
Claw AI Lab is a self-hosted multi-agent platform that simulates a full AI research lab from a single prompt, orchestrating specialized agents (literature review, experiment design, coding, GPU execution, writing) through a five-layer hierarchical pipeline with FIFO scheduling. It includes a web dashboard for monitoring projects, inspecting artifacts, and intervening with human-in-the-loop feedback, rollback, and continuation.

## Use cases
- run an autonomous ai research team from one prompt
- automate literature review and hypothesis generation
- orchestrate multiple ai agents on parallel research projects
- auto-generate and execute machine learning experiments
- simulate a research lab with customizable agent roles
- keep humans in the loop while ai agents do research
- automate paper drafting with peer review agents

## When to choose
- you want an end-to-end autonomous research pipeline from idea to written paper
- you need parallel multi-agent orchestration with cross-project knowledge sharing
- you want a visual dashboard with rollback and human feedback at every stage
- you want customizable lab roles like VLM or world-model specialists

## When to avoid
- you need a production-hardened tool - it is a young preview release with no license file
- you just want a single-agent coding assistant or chatbot
- you lack GPU/compute resources for the execution sandbox
- you need guaranteed stability or commercial support

## Facets
- artifact type: application
- maturity: experimental
- function: agent-framework, llm-inference, workflow-automation, chat-interface, scheduling
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, self-hosted, cross-platform
- tags: multi-agent, autonomous-research, human-in-the-loop, ai-scientist, dashboard, fifo-scheduling, code-execution-harness, ai-agents, research-automation, nodejs, web-server

## Member repositories
- Claw-AI-Lab/Claw-AI-Lab (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:28.618488+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 2026-08-30T04:42:04.898612+00:00, confidence not recorded.
  - readme: https://github.com/Claw-AI-Lab/Claw-AI-Lab (fetched 2026-08-28T04:04:28.618488+00:00, sha f3a7aba3ef35)
  - homepage: https://clawailab.ai/ (fetched 2026-08-29T12:00:29.636133+00:00, sha f79ee9fb6654)
- Data as of 2026-08-30T08:39:29.467469+00:00.