OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

Clawith

Clawith is an open-source platform for coordinating teams of AI agents, giving each agent a persistent identity, long-term memory and its own workspace for collaborating with other agents and a human user.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Clawith — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Clawith when a workflow calls for multiple agents that retain identity and memory, coordinate with each other, and respond to schedules or events. Its local deployment depends on external LLM API access.

Who it is for

  • Teams exploring collaborative AI agent workflows.
  • Developers and operators evaluating a self-hosted multi-agent platform.
  • Organizations seeking agents that can retain context and coordinate tasks over time.

Documented uses

  • Create a team of AI agents with distinct persistent identities and workspaces.
  • Have agents message one another, delegate tasks and share updates.
  • Use triggers to support scheduled, recurring or event-driven agent activity.
  • Connect agents to external LLM providers for inference.
Before you choose

Requirements & limits

The project offers a hosted Cloud service and a shared live demo; the README says the demo is not guaranteed stable. Self-hosting instructions are available in the public Apache-2.0 repository.

  • Clawith is a web application; its main implementation language is Python.
  • The README requires Python 3.12+, Node.js 20+, a database option and network access to external LLM APIs for local deployment.
  • Inference is provided by external model APIs rather than models running locally.
  • The README describes organization-based role access, usage quotas, approval workflows, audit logs and agent connections to Slack, Discord or Feishu/Lark.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare a self-hosted Clawith installation

Set up Clawith's local runtime environment using the repository's documented setup script.

Before you start

  • Python 3.12+
  • Node.js 20+
  • PostgreSQL 15+ or SQLite for quick testing
  • Network access to external LLM API endpoints
  • The README lists 2 CPU cores, 4 GB RAM and 30 GB disk as the minimum local configuration.

Steps

  1. Clone the Clawith repository and change into its directory.

  2. Run the command below for production runtime dependencies, or the command below to include development and test tools.

    Documented command
    bash setup.sh
    Documented command
    bash setup.sh --dev

  3. The setup process creates .env from .env.example and prepares the database environment.

Expected outcome

The documented setup process prepares the local application environment; further configuration and launch steps are not included here.

Guide limitations

  • Clawith requires external LLM API access and does not run AI models locally.
  • The README identifies setup options but the available instructions do not describe completing a launch or using the application.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
ClawithCreate a team of AI agents with distinct persistent identities and workspaces.Cloud, Self-hosted, WebThe project offers a hosted Cloud service and a shared live demo; the README says the demo is not guaranteed stable. Self-hosting instructions are available in the public Apache-2.0 repository.
Insurance Agentic AIRoute insurance questions to a life, home or auto specialist.Docker, Self-hosted, Web
AI ChatkitCreate and orchestrate agents with custom behavior logic.Linux, Self-hosted, Server, WebThe repository is public and identified as open source. Its README documents a local development setup with Python and Node-based frontend tooling.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
dataelement/Clawith · Official homepage title · retained in its source language
How we review sourcesSuggest a correction