# dataelement/Clawith

Your First AI Agents Company

Repository: https://github.com/dataelement/Clawith
Canonical: https://ross.abutalabs.com/products/clawith
Homepage: https://www.clawith.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, llm, multiagent, openclaw
Last push: 2026-08-25T12:05:10+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 13
- inputs: {"age_days": 183, "days_push": 8, "days_rel": 9, "gap_med": 2, "n_releases_24m": 32}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4138, forks 693 (observed 2026-08-28T04:08:36.246569+00:00)

## What it is
Clawith is an open-source multi-agent collaboration platform where each AI agent has a persistent identity, long-term memory, and its own workspace, and agents work together as a crew alongside humans. It includes an autonomous awareness system (Aware) with focus items and trigger bindings so agents proactively perceive, decide, and act.

## Use cases
- run a team of AI agents that collaborate on tasks
- give each AI agent persistent memory and its own workspace
- build an AI agents company with human-agent collaboration
- automate research, writing, and delivery pipelines with multiple agents
- let agents proactively track and act on tasks without waiting for commands
- simulate a quant or media team with specialized agent roles

## When to choose
- you need multi-agent collaboration rather than a single-agent assistant
- you want agents with persistent identity, memory, and workspaces
- you want a self-hostable, Apache-2.0 platform with a hosted cloud option
- you want agents that proactively manage focus items and triggers

## When to avoid
- you only need a simple single-agent chatbot
- you need a lightweight agent library to embed in your own code rather than a full platform
- you require guaranteed stability - the project is young and the demo environment is shared

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, chatbot, workflow-automation
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, self-hosted, cross-platform
- tags: multi-agent, openclaw, agent-identity, long-term-memory, agent-collaboration, crew, a2a, ai-agents, automation, docker, web-server

## Member repositories
- dataelement/Clawith (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:36.246569+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 2026-08-29T18:22:59.975305+00:00, confidence not recorded.
  - readme: https://github.com/dataelement/Clawith (fetched 2026-08-28T04:08:36.246569+00:00, sha e321c11bc0a4)
  - homepage: https://www.clawith.ai (fetched 2026-08-29T09:14:02.768491+00:00, sha 88586e97c4c9)
- Data as of 2026-08-30T08:39:29.467469+00:00.