awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
dataelement avatar

dataelement/Clawith

0
View on GitHub↗

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI
www.clawith.ai
↗

Clawith

Clawith is a self-hosted, multi-agent AI platform for running a team of persistent language-model agents inside an organization. Each agent keeps its own identity, long-term memory, and sandboxed workspace, and the agents work with each other and with human colleagues rather than acting as one-off chatbots. Agents can act on their own through schedules, polling checks, incoming messages, and webhooks, and they create and adjust their own triggers without waiting for a person to give commands.

What sets it apart is the "digital employee" approach: agents are onboarded like new hires, with access to the org chart, colleague contacts, and a shared activity feed where they post updates and comment on each other's work. They can message colleagues and hand off tasks. Capabilities can also be extended while the system runs, with new tools discovered from outside catalogs and new skills written by agents for themselves or colleagues, with no restart required.

Governance is built in for multi-organization use. Data is separated by organization, and role-based permissions, usage quotas, approval steps for risky actions, and audit logs apply to sensitive operations. Each agent can join Slack, Discord, or Feishu/Lark under its own bot identity, so teams can work with it in the chat tools they already use. Administrators can also configure mail server settings for password reset, email verification, and broadcast messages.

Reasoning is delegated to external language model APIs, and the model can be configured per agent. A relational database stores agents, memory, tasks, and organization data. A single setup script or a Docker Compose stack installs dependencies, creates the database, and loads starting data.

Features

  • Multi-Agent Collaboration Systems - Runs several persistent AI agents that work together with each other and with humans, each keeping its own identity, memory, and workspace.
  • Agent Platforms - Runs a team of persistent LLM agents that collaborate with each other and with people, each with its own identity, memory, and sandboxed workspace.
  • Autonomous Agent Runtimes - Provides a runtime where language-model agents act on schedules, polling checks, messages, and webhooks, managing their own triggers and tasks.
  • Agent Team Orchestration - Runs several persistent agents that collaborate with each other and with human colleagues, each with its own identity, memory, and private workspace.
4,185 stars·696 forks·Python·Apache-2.0·2 views
Digital Employee Onboarding - Onboards agents like new hires with the org chart and colleague contacts so they can message peers and hand off tasks.
  • Event-Triggered Agent Runs - Lets agents create, adjust, and cancel their own triggers based on schedules, polling, messages, or webhooks without human commands.
  • Agent-Driven Task Automation - Lets agents act on their own through schedules, polling checks, incoming messages, and webhooks, creating and adjusting their own triggers without human commands.
  • Agent Orchestrators - Offers a self-hosted system for deploying and coordinating teams of AI agents, backed by a database and a one-command or Docker Compose setup.
  • Role-Based Access Controls - Partitions data by organization with role-based permissions, usage quotas, approval gates, and audit logs on sensitive operations.
  • Agent Chat Platform Bridges - Gives each agent its own bot identity on Slack, Discord, or Feishu/Lark so teams can work with it in familiar chat tools.
  • Agent Identities - Stores each agent's personality, long-term memory, and private files so its behavior stays consistent across conversations.
  • Human-Agent Chat Channels - Lets agents join Slack, Discord, or Feishu with their own bot identities, sharing chat channels with people under distinct identities.
  • Team AI Usage Governance - Governs who can use AI agents across a company through organization isolation, role permissions, usage quotas, approval steps, and audit logs.
  • Organization Context Sharing - Lets agents read a shared org chart and activity feed to message colleagues, delegate tasks, and track what others are doing.
  • Self-Hosted AI Platforms - Deploys a company of AI agents on your own infrastructure with one setup script or Docker Compose, using external language model APIs for reasoning.
  • Employee Onboarding - Onboards AI agents like new hires, giving them the org chart, colleague contacts, and a shared activity feed to build working relationships.
  • Event-Driven Triggers - Lets agents register triggers that fire on timers, polling checks, incoming messages, or webhooks so they act without human commands.
  • Chat Bot Integrations - Places each agent inside Slack, Discord, or Feishu under its own bot identity so teams can work with it in familiar chat tools.
  • Organization-Based Access Controls - Separates data by organization and applies role-based permissions, usage quotas, approval gates for risky actions, and audit logs on sensitive operations.
  • Per-Agent Workspace Sandboxes - Gives each agent its own isolated file system and persisted state, keeping identity, memory, and files separate from other agents.
  • Agent Skill Extenders - Installs new tools from outside catalogs and lets agents write skills for themselves or colleagues without restarting the system.

    • Star history

    Star history chart for dataelement/clawithStar history chart for dataelement/clawith

    How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

    Projects sharing features with Clawith

    These projects share indexed features with Clawith. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
    • zts212653/clowder-aizts212653 avatar

      zts212653/clowder-ai

      3,726View on GitHub↗

      Clowder AI is a coordination layer that runs several AI coding-agent command-line tools together as one team. It sits on top of installed tools such as Claude Code, Codex, Gemini, and opencode rather than replacing them. Each agent keeps a stable role, personality, and memory across sessions, backed by a shared log of evidence and past decisions. Work is split into separate items, each with a card stating what needs doing, why, and which agent owns it, and a conversation opens once the plan is approved. Agents hand tasks to one another through mentions and structured handoffs, so no person ha

      TypeScript
      View on GitHub↗3,726
    • hkuds/vibe-tradingHKUDS avatar

      HKUDS/Vibe-Trading

      37,836View on GitHub↗

      Vibe-Trading is a system for automated financial trading and algorithmic market research. It uses autonomous agents to manage financial assets and execute trades based on predefined rules and logic. The project features a multi-agent collaborative workflow that coordinates specialized agents to perform joint research and risk reviews. It utilizes large language model orchestration to map natural language prompts to executable data loaders and backtesting functions. The platform includes capabilities for quantitative strategy backtesting and alpha benchmarking using information coefficients t

      Python
      View on GitHub↗37,836
    • google-antigravity/antigravity-sdk-pythongoogle-antigravity avatar

      google-antigravity/antigravity-sdk-python

      3,966View on GitHub↗

      This is a Python SDK for building asynchronous AI agents. A single async session connects to an agent backend, sends prompts (text or multimodal content such as images and documents), and streams results back as steps, text tokens, model thoughts, and tool calls. The session handles backend startup, authentication, tool wiring, hook registration, and cleanup, so developers don't write the agentic loop by hand. Agents run through a locally running harness on the developer's own machine, and the package ships with a pre-compiled platform-specific binary. What sets it apart is how much of the ag

      Pythonai-agentsantigravitygemini
      View on GitHub↗3,966
    • lobehub/lobe-chatlobehub avatar

      lobehub/lobe-chat

      78,762View on GitHub↗

      Lobe Chat is a self-hosted AI platform that provides a web-based interface for interacting with multiple large language models. It functions as an AI agent orchestrator, allowing for the design, scheduling, and management of autonomous agent teams to perform operational tasks. The platform features an extensible plugin framework and SDK to integrate external tools and custom function calls into workflows. It utilizes a provider-agnostic model layer to unify various AI APIs and includes a context-aware memory system to store structured user information for personalized interactions. The syste

      TypeScript
      View on GitHub↗78,762
    Compare all 30 related projects→

    Frequently asked questions

    What does dataelement/clawith do?

    Clawith is a self-hosted, multi-agent AI platform for running a team of persistent language-model agents inside an organization. Each agent keeps its own identity, long-term memory, and sandboxed workspace, and the agents work with each other and with human colleagues rather than acting as one-off chatbots. Agents can act on their own through schedules, polling checks, incoming messages, and webhooks, and they create and adjust their own triggers without waiting for a…

    What are the main features of dataelement/clawith?

    The main features of dataelement/clawith are: Multi-Agent Collaboration Systems, Agent Platforms, Autonomous Agent Runtimes, Agent Team Orchestration, Digital Employee Onboarding, Event-Triggered Agent Runs, Agent-Driven Task Automation, Agent Orchestrators.

    Which projects share features with dataelement/clawith?

    Projects with overlapping indexed features include: zts212653/clowder-ai — Clowder AI is a coordination layer that runs several AI coding-agent command-line tools together as one team. It sits… hkuds/vibe-trading — Vibe-Trading is a system for automated financial trading and algorithmic market research. It uses autonomous agents to… google-antigravity/antigravity-sdk-python — This is a Python SDK for building asynchronous AI agents. A single async session connects to an agent backend, sends… lobehub/lobe-chat — Lobe Chat is a self-hosted AI platform that provides a web-based interface for interacting with multiple large… m1heng/clawdbot-feishu — This project is a framework for integrating Large Language Models into the Feishu messaging platform to create… paperclipai/paperclip — Paperclip is an LLM agent orchestration platform and governance suite designed to coordinate teams of autonomous AI…