Alternatives to Teebots

Compare Teebots alternatives for your business or organization using the curated list below. SourceForge ranks the best alternatives to Teebots in 2026. Compare features, ratings, user reviews, pricing, and more from Teebots competitors and alternatives in order to make an informed decision for your business.

  • 1
    Kimi K3

    Kimi K3

    Moonshot AI

    Kimi K3 is Moonshot AI’s most capable model, built for frontier intelligence scenarios such as software engineering, knowledge work, deep reasoning, and multimodal understanding. The model has 2.8 trillion parameters and uses Kimi Delta Attention, a hybrid linear attention mechanism, along with Attention Residuals for long-context performance. Kimi K3 supports a 1 million token context window, making it useful for analyzing large codebases, long documents, complex knowledge bases, and multi-step workflows. It includes native visual understanding for images and videos, with support for structured message formats, base64 image input, uploaded video files, and multimodal reasoning. Developers can use Kimi K3 through an OpenAI-compatible API with support for streaming, structured JSON output, partial mode, custom tools, dynamic tool loading, and automatic context caching.
    5.0 out of 5 stars 1 Rating for Kimi K3
    Starting Price: $3 per 1M tokens (input)
  • 2
    Kimi K2.7 Code

    Kimi K2.7 Code

    Moonshot AI

    Kimi K2.7 Code is an open-source, coding-focused agentic AI model developed by Moonshot AI for long-horizon software engineering tasks. It is designed to improve coding performance, agent workflows, and real-world development assistance compared with earlier Kimi K2 versions. The model supports a 256K context window, making it useful for working with large codebases, long technical documents, and complex multi-step programming tasks. Kimi K2.7 Code is available through Kimi Code and API access, with OpenAI- and Anthropic-compatible options for easier integration into developer workflows. It is also listed on Hugging Face and supports deployment through inference engines such as vLLM, SGLang, and KTransformers. With improved agentic capabilities, long-context support, and reduced thinking-token usage compared with K2.6, Kimi K2.7 Code gives developers a flexible open-source option for AI-assisted coding.
  • 3
    Run BiOS

    Run BiOS

    UltraSafe AI Inc.

    Run BiOS is serverless, OpenAI-compatible inference. Point the OpenAI SDK at the Run BiOS endpoint and keep your code. Six model families — Claude, DeepSeek, GLM, Kimi, MiniMax and Qwen — plus bios-adaptive, which routes each request for quality, speed and budget against a published price ceiling. Prompts and responses live in memory and are discarded when the request completes: no request logs, no content store, no archive. Fine-tuning and dedicated GPU endpoints run from the same account if you later want weights you own, billed per second of GPU time. Pricing is usage-based from a pre-paid balance, published per million tokens, and an endpoint pauses rather than running up a debt if the balance reaches zero.
  • 4
    OpenWorker

    OpenWorker

    OpenWorker

    OpenWorker is an open source, local-first AI coworker that gets everyday tasks done from start to finish instead of only returning answers. Users ask for an outcome, such as a renewal brief, incident report, follow-up message, calendar update, sprint summary, or finished document—and OpenWorker works across the tools where the information already lives. It can connect with Slack, Gmail, Outlook, Google Calendar, Notion, HubSpot, GitHub, Attio, Google Drive, Jira, Linear, Asana, Dropbox, Box, files, and other services through one-click or manual connections. It supports cloud, open-weight, and fully local models, including providers such as OpenAI, Anthropic, Google, xAI, Mistral, DeepSeek, Kimi, Qwen, and Ollama, and users can switch models when a task calls for something different. OpenWorker researches, gathers context, performs multi-step work, creates polished outputs in chat, Slack, Markdown, PDF, images, or files, and checks in before consequential actions.
  • 5
    DS Bot

    DS Bot

    DS Bot

    DS Bot is a desktop application and DeepSeek Harness plugin for managing a team of persistent AI bots. Each bot has a model, profile, permissions and memory, and can work in private chats or group conversations. A main bot can coordinate the team, delegate tasks and organize larger work into stages. Users can add MCP servers and skills, connect services such as GitHub and Gmail, and link bots to Telegram, WeChat, Feishu, DingTalk, WeCom, QQ, Discord or Slack. Supported local coding-agent command-line tools can also run as bots. The app includes computer-use controls and approval of sensitive actions. Bots can create and edit Word, PowerPoint and Excel files; some file-generation and rendering features require the desktop app or DeepSeek Harness Desktop. DS Bot is open source, runs on Windows, macOS and Linux, and also supports Docker deployment. Model use and third-party services may incur separate charges.
  • 6
    PyGPT

    PyGPT

    PyGPT

    PyGPT is an open source, personal desktop AI assistant for Linux, Windows, and Mac, written in Python. It works similarly to ChatGPT, but locally on a desktop computer, with chat, vision, agents, image and video generation, tools, voice control, and more. PyGPT supports multiple models, including OpenAI GPT-5, GPT-4, o1, o3, o4, Google Gemini, Anthropic Claude, xAI Grok, Perplexity Sonar, DeepSeek, Mistral AI, and models accessible through Ollama and LlamaIndex. It offers 12 modes of operation, including chat, chat with files, realtime + audio, research, completion, image and video generation, vision, assistants, experts, computer use, agents, and autonomous mode. Users can chat with their own files and data using integrated LlamaIndex support. PyGPT includes built-in vector database support, automated files and data embedding, full conversation context, short- and long-term memory, internet access through Google, Microsoft Bing, and DuckDuckGo, plus speech synthesis and recognition.
  • 7
    Vibe Island

    Vibe Island

    Vibe Island

    Vibe Island is a macOS notch panel for AI coding agents. It tracks sessions from 26 agents - Claude Code, Codex, Gemini CLI, Cursor, OpenCode, Kimi Code, DeepSeek, Copilot, and more - in one place, with real-time status, per-agent brand colors, and one-click precise jump to the exact terminal tab, split pane, or VS Code window where each session runs (20+ terminals supported, tmux included). Built for developers running several agents in parallel, it also shows remaining usage quota for Claude, Codex, Kimi, GLM, and DeepSeek subscriptions with live reset countdowns, and lets you approve permissions, answer agent questions, and review plans without leaving the notch. Works with local sessions and remote servers over SSH. Native Swift, no Electron, under 100 MB RAM. Free trial, then a one-time purchase - no subscription.
  • 8
    Tobs

    Tobs

    BotHarness

    Tobs is an open-source AI agent plugin for DeepSeek Harness. It lets users create persistent PersonaBots with distinct roles and conversation histories. Bots keep inspectable, file-based memory with Git version history, work in direct and group chats, delegate background assignments, run scheduled tasks, and connect to Slack, Discord, Lark/Feishu, QQ, or personal WeChat. Users configure a model provider and credentials in DeepSeek Harness; Tobs runs on a Windows, macOS, or Linux computer they manage. Beta iOS and Android companion apps provide remote chat, notifications, and approval controls. Optional browser and desktop-control tools can be permission-gated. Use cases include research, writing, coding, task handoffs, and reminders. Tobs is for people who want configurable agents that retain context across conversations and work with authorized files and messaging channels, rather than a fully managed hosted agent service.
  • 9
    Raydo Agent OS
    Raydo Agent OS is a desktop AI-agent application for people and teams who want to automate work across a browser, local files, and connected tools. Users can describe a task and have an agent carry out multi-step work, create or update materials, and return deliverables for review. Runs include a step-by-step activity history, and workflows can pause for human approval before an action or handoff. The product combines a desktop workspace with controls for managing agent runs and accessing local resources. Raydo offers the application for macOS and Windows, with optional cloud-based model and execution services alongside local capabilities. It is intended for general productivity and task automation rather than a single industry or department.
  • 10
    Agent S

    Agent S

    Simular

    Agent S is an open-source agentic framework built to enable autonomous computer use through an Agent-Computer Interface (ACI). It allows AI agents to operate graphical user interfaces similarly to humans by perceiving screens, reasoning through objectives, and executing actions across macOS, Windows, and Linux systems. The latest release, Agent S3, achieves state-of-the-art results on the OSWorld benchmark and surpasses human-level performance in complex multi-step computer tasks. By combining powerful foundation models such as GPT-5 with grounding models like UI-TARS, the framework translates visual inputs into accurate executable commands. Agent S supports multiple deployment options, including CLI, SDK, and cloud environments. It integrates seamlessly with leading model providers such as OpenAI, Anthropic, Gemini, Azure, and Hugging Face endpoints.
  • 11
    SinoGate

    SinoGate

    SHANXUAN TECHNOLOGY LIMITED

    SinoGate is a hosted API gateway for developers who want to use Chinese large language models through a single OpenAI-compatible API. It provides one API key and endpoint for models including Qwen, DeepSeek, Kimi, and GLM, so existing applications can connect without implementing a separate provider-specific interface for each model. Developers can select an available model for language-model features such as chat, text generation, and coding assistance. The service is designed for global builders and software teams integrating Chinese LLMs into applications. It uses cloud-hosted access and USD billing through Stripe; supported models and their capabilities may vary.
  • 12
    BetterToken

    BetterToken

    BetterToken

    BetterToken is a hosted LLM API gateway that provides API access to models from providers including Anthropic, OpenAI, Moonshot, Z.ai, DeepSeek, Alibaba Cloud and MiniMax through BetterToken account keys. It offers OpenAI-compatible and Anthropic-compatible endpoints, with a Responses-compatible setup for Codex, and lets developers connect coding tools, applications, agents and automation workflows using a custom base URL. Users can choose models from a live catalog, view token usage and request charges in the workspace, and pay through prepaid balance or monthly quota plans. Model costs vary by input, output and supported cached or media tokens. Setup guides cover tools such as Claude Code, Codex, Cursor, Dify and n8n. BetterToken is intended for developers and teams integrating hosted language models into software and automated workflows.
  • 13
    qorqbot

    qorqbot

    49 Agents

    qorqbot is a local AI agent for business workflows and complex, long-running tasks. It works with coding agents such as Claude Code and OpenAI Codex, adding shared context, operational tools, and an interface for coordinating work across clients, CRM systems, tables, and communications. Users can create custom skills, workflows, and tools, connect supported services through MCP, and approve sensitive actions before they proceed. Its browser-based control panel lets users configure agents, schedule tasks, monitor activity, and review runs, while execution takes place on the user's computer. Developers and teams can use qorqbot to automate recurring workflows and coordinate agent activity while working with local files and connected tools. It offers downloadable builds for macOS, Windows through WSL2, and Linux. Personal use is free; commercial use requires a per-person license. It is designed for people who want agent automation to run on a computer they control.
  • 14
    Xinference

    Xinference

    Xinference

    Xinference is a self-serve Model API for Kimi K3 and DeepSeek, hosted in Australia on dedicated GPUs. Developers and teams call both models through one OpenAI-compatible API, at the same per-token price as the model vendor. Switching from another OpenAI-compatible provider means changing the base URL and API key. No prompt or response content kept by default, and no training on your data. Don't see the model you need? Talk to us about adding it. For teams that need models in their own environment, Xinference Dedicated Inference runs open models in your VPC, data centre or servers. Xinference is in the process of becoming SOC 2 and ISO 27001 compliant.
  • 15
    DeepSeek R1

    DeepSeek R1

    DeepSeek

    DeepSeek-R1 is an advanced open-source reasoning model developed by DeepSeek, designed to rival OpenAI's Model o1. Accessible via web, app, and API, it excels in complex tasks such as mathematics and coding, demonstrating superior performance on benchmarks like the American Invitational Mathematics Examination (AIME) and MATH. DeepSeek-R1 employs a mixture of experts (MoE) architecture with 671 billion total parameters, activating 37 billion parameters per token, enabling efficient and accurate reasoning capabilities. This model is part of DeepSeek's commitment to advancing artificial general intelligence (AGI) through open-source innovation.
  • 16
    AITarea

    AITarea

    Black Mamba Systems SL

    AITarea is a Windows desktop application that coordinates AI agents to perform multi-step tasks on a user's computer. Users describe a goal in natural language; the application plans the work, delegates subtasks to specialized agents and produces files or other deliverables in a selected workspace. Its tools can interact with local files and folders, Windows applications, websites and browser sessions. Users can let tasks run autonomously, approve a plan before execution, or review steps as work progresses. The product is intended for business users who want to automate varied research, document and operational work without designing each process from scratch. AITarea is licensed for Windows 10/11 computers and uses an internet connection and the customer's own AI-provider API key for model access. Task data is stored locally, while model processing depends on the provider configured by the customer.
    Starting Price: €1,735 one-time
  • 17
    Puter.js

    Puter.js

    Puter Technologies Inc.

    Puter.js is the backend for AI-generated apps. Use your existing AI coding tool to build production-ready apps with up to 90% fewer AI tokens. Auth, cloud storage, database, OpenAI, Claude, Gemini, Grok, Kimi, DeepSeek, and more, all through a single JavaScript library. No API keys. Zero setup.
  • 18
    OfoxAI

    OfoxAI

    OfoxAI

    OfoxAI is a unified, OpenAI-compatible API gateway that gives developers and teams instant access to 100+ large language models — GPT, Claude, Gemini, DeepSeek, and more — through a single endpoint and one API key. Stop juggling multiple provider accounts, SDKs, and invoices: integrate once, switch models freely, and scale from a solo prototype to a full production team. Key features: One API Key, 100+ Models — Always up-to-date with the latest models from OpenAI, Anthropic, Google, DeepSeek, and more. Three Native Protocols — Full OpenAI, Anthropic, and Gemini SDK compatibility. Zero code migration — just swap the base URL. Low-Latency Access — Global routing with under 300ms average latency. Zero Markup Pricing — Pay official provider rates, with no surcharges or hidden fees. Built for Teams — Shared billing dashboard, per-member usage tracking, and budget controls. Flexible Payments — Credit card, PayPal, and major regional payment methods supported.
  • 19
    OrcaRouter

    OrcaRouter

    OrcaRouter

    OrcaRouter is an OpenAI-compatible AI model router that sends each prompt to the right model across OpenAI, Anthropic, Gemini, DeepSeek, Qwen, Kimi, and 200+ frontier and open source models. It is built to preserve frontier answer quality while reducing AI inference spend by grading every prompt and routing hard reasoning to frontier models and routine work to lower-cost open source models. The routing is quality-graded, never a blind, cheap-model swap, and each request shows the difficulty grade, selected model, provider, and cost so routes are visible, auditable, and reproducible. Developers can switch by changing the API base URL, while existing SDKs, model names, and streaming behavior continue to work as before. OrcaRouter supports automatic failover, so if a provider goes down mid-stream, traffic can switch transparently, and the application avoids user-facing errors. It also includes API key management with spend caps, model allowlists, rate limits, budget enforcement, and more.
  • 20
    Paperclip.inc

    Paperclip.inc

    Paperclip.inc

    Paperclip.inc is a control plane for hiring and managing AI agents that can support engineering, growth, operations, research, and other company workflows. It lets users run multiple AI agents from a single inbox instead of juggling separate model tabs and scattered conversations. The platform supports agents such as Claude, Codex, Cursor, Gemini, DeepSeek, Qwen, GLM, Kimi, MiniMax, and others. Paperclip.inc includes approvals, permissions, budgets, audit logs, goals, routines, and scheduled heartbeats to help companies manage AI work with structure and accountability. Teams can install pre-built AI companies with defined org charts, agent configurations, and skill sets for areas like engineering, agencies, research labs, and digital studios. With EU-hosted managed infrastructure, open-source foundations, and per-company pricing, Paperclip.inc helps organizations scale AI work while maintaining control over cost, direction, and governance.
  • 21
    OpenChiip Harness
    OpenChiip Harness is a self-hosted AI agent runtime and orchestration framework for developers building local or coordinated agent workflows. It combines LLM conversations, skill orchestration, tool execution, multi-layer memory, resource monitoring, and multi-agent collaboration in a React administration dashboard. Run it as a local service or connect it to the OpenChiip platform for collaborative scheduling. Its CLI, web dashboard, HTTP API, and WebSocket interface support chat, tools, sessions, memory, task management, and monitoring. It supports Baidu ERNIE, OpenAI-compatible model providers, and delegation to Codex or Claude Code. Install via pip or deploy with Docker, Linux packages, systemd, or Windows installers; macOS supports pip installation. Licensed under AIGCGPL-1.0.
  • 22
    OpenCheese AI

    OpenCheese AI

    OpenCheese AI

    OpenCheese AI is a hosted AI gateway and API for developers who want to connect applications and coding tools to multiple AI models through a unified service. It provides OpenAI-compatible endpoints and an Anthropic Messages-compatible interface, with model selection, API-key management, usage and balance tracking, and access to models from providers including OpenAI, Anthropic, Google, and DeepSeek. Developers can configure supported coding clients and applications to send requests through OpenCheese rather than managing separate provider credentials for each connection. The service offers both credit-based usage and time-limited plans with included balances; available models, rates, and free-model options depend on the selected model and plan. It is intended for developers evaluating or building text, coding, and image-generation workflows with hosted AI models.
  • 23
    Globster

    Globster

    Globster

    Globster provides secure and reliable AI agents built for organizations, giving teams agents that work across their apps, files, and business processes while following the boundaries the organization controls. Agents can connect to monday.com, Google Workspace, Slack, HubSpot, Notion, Salesforce, Google Sheets, and thousands of other apps, helping them find context and move work forward. Users can also interact with agents through WhatsApp, Telegram, or Slack, hand off tasks, and receive updates where they already work. Recurring work can be turned into agentic workflows with triggers, defined steps, monitoring, and judgment-based actions. Each agent includes its own browser for researching and navigating websites and can use models such as GPT, Claude, NVIDIA Nemotron, Kimi, Qwen, and DeepSeek through a single AI gateway.
  • 24
    Myra AI Workspace

    Myra AI Workspace

    Myra Security

    Myra AI Workspace combines an AI gateway with a governed workspace for organizations using AI with sensitive data. Employees use chat, projects, knowledge sources, file imports, and document-generation tools, while administrators manage access, models, and guardrails. The gateway connects to 20+ model providers, including OpenAI, Anthropic, Gemini, Azure OpenAI, AWS Bedrock, Mistral, Groq, DeepSeek, and xAI, through one OpenAI-compatible endpoint. BYOK support lets organizations use provider contracts. A color-coded privacy indicator shows whether data stays on Myra infrastructure with open-weight models, is PII-masked before reaching external models, or requires administrator approval. Features include configurable guardrails, PII masking, tamper-evident audit logs, three-level budget controls, MCP connectors, SCIM, and SIEM forwarding. The platform runs on Myra's EU infrastructure.
  • 25
    SPIRITT

    SPIRITT

    SPIRITT

    SPIRITT is a cloud-based AI agent workspace for founders, startups, and enterprise teams. Its agents use dedicated cloud computers, browsers, and memory to handle engineering, sales, operations, and administrative work, including writing, testing, and deploying production apps. Agents connect with more than 1,500 business tools, build missing integrations, and communicate through Slack, Microsoft Teams, email, and WhatsApp. Scheduled routines run around the clock, even when a user's laptop is closed. Sensitive actions can require approval, and per-agent budgets help control spending. SPIRITT combines models from Claude, GPT, Gemini, Grok, and its own Kay models for individual tasks. Agents can place and answer calls. A desktop app is available for Windows, macOS, and Linux, with scoped access to local files and terminal actions. Enterprise options include bring-your-own-cloud, air-gapped deployment, and white labeling.
  • 26
    UncensoredLLM

    UncensoredLLM

    Uplink Switch LLC

    UncensoredLLM is a hosted, OpenAI-compatible API gateway for uncensored, abliterated, derestricted, and roleplay-tuned language models. Developers can select models by ID and connect from code or compatible chat, writing, and coding clients using a base URL and API key. The catalog includes builds from model families such as DeepSeek, GLM, Qwen, Gemma, Kimi, and Llama, with separate input and output token rates. The same key also provides access to image- and video-generation endpoints, billed per image or video second. Usage is deducted from a prepaid balance, and a browser playground offers a limited number of free daily turns on selected models. Public model pages show catalog details and prices, and each model receives a daily fixed-prompt check that compares reported input-token counts.
  • 27
    AnyModelBot

    AnyModelBot

    Havenbyte

    AnyModelBot is a local-first AI agent application for people who want persistent, configurable assistants on their own Windows, macOS, or Linux computer. Users can create bots with separate personas, models, workspaces, and local memory, then chat with them in the app or through connected messaging services. Bots can read and write files, run commands, manage background tasks and scheduled rules, and operate a desktop with configurable permissions and approval prompts for actions outside a workspace. The app supports multiple model providers through Modelflare, with model usage billed by token rather than an AnyModelBot subscription. It can also run in Docker on a server and provides a local web console for remote access. Conversations, memory, files, and credentials are stored locally, while model requests pass through Modelflare to the selected provider.
  • 28
    Lapu AI

    Lapu AI

    Lapu AI

    Lapu AI is a desktop AI agent for macOS and Windows. Users describe multi-step work in plain language; the agent plans and executes tasks on the local computer using files, desktop apps, Excel, and terminal with permission prompts before sensitive actions. Unlike browser-only chatbots, Lapu operates real apps on the machine. Free plan available; paid from $20/month.
  • 29
    Kimi Claw

    Kimi Claw

    Moonshot AI

    Kimi Claw is a cloud-based deployment solution that allows users to launch OpenClaw instantly with just one click. OpenClaw is an AI assistant designed with personality and long-term memory capabilities to create more engaging and contextual interactions. With Kimi handling the deployment process, there is no need for complicated setup or server management. The assistant stays online 24/7, ensuring continuous availability for conversations and task execution. Kimi Claw comes configured with Kimi K2.5 Thinking, enhancing its reasoning and problem-solving abilities. It also includes ready-to-use skills that enable proactive task completion across different workflows. The assistant can operate across multiple messaging apps, allowing users to chat freely and manage tasks seamlessly from various platforms.
  • 30
    Astah Professional

    Astah Professional

    Change Vision, Inc.

    Astah Professional is an all-in-one modeling tool for software and system design, developed by Change Vision, Inc. It supports UML 2.x, ER diagrams, data flow diagrams (DFD), flowcharts, requirement diagrams, CRUD, and mind maps in a single tool. Unlike drawing tools, Astah creates models: a change to a model element is reflected in every diagram that uses it, so your diagrams stay consistent. AI features include AI Chat Copilot and AI-assisted code reverse engineering, which use your own API key for OpenAI, Azure OpenAI, Claude, Gemini, or an OpenAI-compatible service. A local MCP server lets external AI agents work with your Astah models. Conventional reverse engineering of Java, C#, and C++ code is also included. Astah Professional is a desktop application for Windows, macOS, and Linux, with a bundled Java runtime, so no separate Java installation is required. A 20-day free trial is available. Latest version: 12.0 (released July 15, 2026).
  • 31
    Scalattice

    Scalattice

    Robottik

    Scalattice is a managed inference API and distributed GPU network for developers running open models and GPU owners providing compute. Developers submit chat-completion and image-generation requests through OpenAI-compatible endpoints, choose catalog models, and manage API keys, credits, usage, model access, and regional policies through Scalattice Cloud or its command-line interface. Requests run on provider machines, and the service tracks usage and distributes provider payouts. GPU providers install the Scalattice agent on compatible Windows, Linux, or Apple Silicon macOS computers, set availability, and monitor jobs and earnings. The service is intended for application developers, AI builders, and GPU operators seeking hosted inference capacity or a way to contribute compute. Model availability and prices depend on the catalog and available capacity.
  • 32
    Termio

    Termio

    Termio

    Termio is a desktop terminal and SSH client for developers and operations professionals who work across local shells and remote hosts. It organizes connections into project workspaces with folders, favorites, startup commands, and reusable scripts or files attached to individual connections. Users can arrange independent local, SSH, WSL, and PowerShell sessions in tabs and resizable split panes, compose multiline commands, and upload files to remote connections. An AI copilot can use terminal context and run configured tools, while users choose an OpenAI-compatible endpoint. Workspace files remain local and can be shared through Git repositories or other file-transfer methods. Termio stores SSH credentials in the operating system's credential store and is available as an installed application for macOS, Windows, and Linux.
  • 33
    ApiGo

    ApiGo

    ApiGo

    ApiGo is a hosted AI model gateway for developers and teams building applications with language models. It provides a unified API endpoint for sending requests to supported model providers, with OpenAI-compatible request formats and model selection through a shared interface. The service includes model routing and fallback configuration, API key management, request and usage logs, per-model token pricing, workspace balance controls, and dashboards for reviewing consumption. Developers can use documented setup guides to connect coding assistants and agent tools such as Cursor, Claude Code, Codex CLI, OpenCode, Kimi Code, and OpenClaw. ApiGo is intended for teams that want to manage model-provider access, usage, and billing through one hosted gateway rather than configure each provider separately.
    Starting Price: $0.10/1M input tokens
  • 34
    Atomic Agent

    Atomic Agent

    Atomic Agent

    Atomic Agent is an open-source, local-first AI agent that runs on your own machine from the terminal. It drives your real tools — shell, files, and browser — and keeps every session on your own disk. Point it at a local model through llama.cpp, or connect a hosted model when you want more power. You choose the model, you own the data, you stay in control. No cloud lock-in. Install with a single command on macOS, Linux, or Windows. Built for developers and power users who want a capable autonomous agent without shipping their work to someone else's cloud.
  • 35
    Astah UML

    Astah UML

    Change Vision, Inc.

    Astah UML is a UML 2.x diagramming tool for software design, developed by Change Vision, Inc. It covers the core UML diagrams, including class, use case, sequence, activity, state machine, component, and deployment diagrams, plus mind maps. Astah creates models rather than drawings: when you change a model element, every diagram that uses it is updated, so your design stays consistent. AI features include AI Chat Copilot and AI-assisted code reverse engineering, which use your own API key for OpenAI, Azure OpenAI, Claude, Gemini, or an OpenAI-compatible service. A local MCP server lets external AI agents work with your Astah models. Conventional reverse engineering of Java, C#, and C++ code is also included. Astah UML runs on Windows, macOS, and Linux with a bundled Java runtime. A free license is available for students, and a 20-day free trial is available. Latest version: 12.0 (released July 15, 2026).
  • 36
    Surf.new

    Surf.new

    Steel.dev

    Surf.new is a free, open-source playground for testing and using AI agents that can browse the web. These agents surf the web and interact with webpages similarly to how a human would, making tasks like automation and web research easy and intuitive. Whether you're a developer evaluating web agents for production use or someone looking to automate repetitive tasks like checking flights, scraping product information, or booking reservations, Surf.new provides an accessible environment to quickly experiment and see how web agents perform. Key Features: Swap between AI Agent Frameworks with a button: Supports Browser-use, an experimental Claude Computer-use-based agent, and integrates smoothly with LangChain—allowing easy experimentation with different approaches. Diverse AI Model Compatibility: Compatible with popular models including Claude 3.7, DeepSeek R1, OpenAI models, Gemini 2.0 Flash, and others—giving you the flexibility to choose what works best.
  • 37
    Velokey

    Velokey

    Velokey

    Velokey is a unified AI model API platform that gives developers access to leading text, image, and video models through one interface. The platform supports LLM APIs, image generation APIs, and video generation APIs, allowing teams to switch models without rebuilding integrations. Developers can use an OpenAI-compatible SDK by changing the base URL and API key, then selecting the model they want to call. Velokey includes models from families such as GPT, Claude, Gemini, DeepSeek, Grok, Kimi, Qwen, GLM, Seedance, Kling, Veo, Wan, Nano Banana, GPT Image, and more. The platform also provides smart model routing, automatic failover, usage tracking, latency visibility, spend monitoring, and transparent pricing across tokens, images, and video seconds. Built for developers and AI teams, Velokey helps simplify model access, reduce integration overhead, and manage multiple AI providers from one API and one bill.
  • 38
    Kimi K2.5

    Kimi K2.5

    Moonshot AI

    Kimi K2.5 is a next-generation multimodal AI model designed for advanced reasoning, coding, and visual understanding tasks. It features a native multimodal architecture that supports both text and visual inputs, enabling image and video comprehension alongside natural language processing. Kimi K2.5 delivers open-source state-of-the-art performance in agent workflows, software development, and general intelligence tasks. The model offers ultra-long context support with a 256K token window, making it suitable for large documents and complex conversations. It includes long-thinking capabilities that allow multi-step reasoning and tool invocation for solving challenging problems. Kimi K2.5 is fully compatible with the OpenAI API format, allowing developers to switch seamlessly with minimal changes. With strong performance, flexibility, and developer-focused tooling, Kimi K2.5 is built for production-grade AI applications.
  • 39
    Autopilot by Directionally Local
    Autopilot is an open-source terminal coding agent and SDK for developers working in Git repositories. It reads a repository, plans tasks, edits files and runs commands, with plan, edit and automatic-approval modes. It connects to 25+ hosted model providers using your own credentials, supports local models through Ollama and LM Studio, and works with OpenAI-compatible endpoints. Autopilot runs on macOS, Linux and Windows for interactive sessions and unattended server jobs with runtime, token and cost budgets, checkpoint recovery and email notifications. It supports MCP servers, language-server features, hooks and local memory. Its headless SDK and JSONL-over-stdio RPC enable integration into other applications. On OpenRouter, subagents can run in read-only Hotcell sandboxes with short-lived, spend-capped tokens instead of the provider key. Autopilot is free and MIT-licensed; model-provider usage may incur separate charges.
  • 40
    Astah System Safety

    Astah System Safety

    Change Vision, Inc.

    Astah System Safety is a model-based safety analysis tool for safety-critical systems, developed by Change Vision, Inc. It combines SysML modeling with STAMP/STPA hazard analysis, GSN/D-Case assurance cases, ASAM SCDL safety concepts, and UAF in one tool. Safety analyses are linked to the system model, so control structures, hazards, and safety arguments stay traceable to requirements and architecture. Safety engineers in automotive, aerospace, railway, and embedded systems use it to build safety cases for standards such as ISO 26262. AI Chat Copilot and a local MCP server require your own API key from a supported AI service (OpenAI, Claude, Gemini, or an OpenAI-compatible endpoint). SysML models can be exchanged with Cameo Systems Modeler through XMI import and export. Runs on Windows and macOS. FTA, FMEA, and simulation are not included. A 40-day free trial is available.
  • 41
    APX

    APX

    Agent Project Context

    APX is a free, open-source desktop application and local agent workspace for coordinating AI agents around projects. Users can create role-specific agents, assign and delegate work, review activity on a shared task board, and keep conversations and project context together. APX also supports scheduled routines, a browser agents can operate with user oversight, and access through an Android companion and messaging channels including Telegram, WhatsApp, Discord, Slack, and iMessage. Users can connect supported model services, local models, coding tools, and MCP servers; model and connected-service charges may apply separately. Desktop releases are available for Windows, macOS, and Linux, with an option to run the core on a server the user controls.
  • 42
    RouterBase

    RouterBase

    RouterBase

    RouterBase is a unified API gateway that gives developers and teams access to 200+ AI models, including GPT, Claude, Gemini, Llama, Mistral and DeepSeek, through a single OpenAI-compatible endpoint. Instead of maintaining separate keys and billing for each provider, you switch models with one line of configuration. RouterBase adds smart routing, automatic failover across providers, and unified billing, so your application keeps running even when an upstream provider has an outage. A free tier is available with no credit card required.
  • 43
    Brigade

    Brigade

    Brigade

    Brigade is an open-source AI teammate platform for individuals and small teams that coordinates Claude Code and OpenAI Codex agents across support, marketing, sales, and software work. Users assign each teammate a role, connect apps such as Gmail, GitHub, Stripe, Notion, and Linear, and give agents separate computers and shared team memory. Teammates can work from conversations and configured triggers, including email, webhooks, and schedules, and request human approval for designated actions through a central review queue. The interface is also usable on a phone for reviewing requests. Brigade can run on a user's Mac or Linux computer, or use Brigade Cloud for persistent cloud computers that continue running when the user's computer is off. The software is intended for founders and small teams that want to delegate recurring operational and coding tasks while retaining oversight.
  • 44
    AtomCode

    AtomCode

    AtomGit

    AtomCode is an open source AI coding agent that lives in the terminal and autonomously reads files, edits code, runs commands, searches the web, executes tests, and self-verifies until a task is complete. It is designed as a multi-model alternative to tools such as Claude Code and Cursor Agent, supporting Claude, OpenAI, DeepSeek, GLM, Qwen, Ollama, SiliconFlow, and any OpenAI-compatible API. Its built-in code graph tools provide symbol indexing, reference lookup, caller and callee tracing, dependency analysis, and blast-radius analysis to help the agent understand large codebases more deeply than basic text search. Developers can attach screenshots and images, while vision preprocessing can extract useful context when the selected primary model does not support images directly. AtomCode integrates natively with AtomGit for OAuth login, repository management, issues, and pull requests, and supports MCP, reusable Skills, plugins, custom slash commands, hooks, and workflows.
  • 45
    ClinePass
    ClinePass is a subscription for open weight models in Cline, built to give developers generous quotas and reliable access to capable coding models without managing separate provider setup or API keys. It is designed for Cline IDE and CLI. The agent harness is built for open-weight model workflows, so developers can go from signup to coding in minutes; create an account, install Cline, select the ClinePass provider, and start coding. ClinePass includes open weight models from Z.ai, Moonshot AI, DeepSeek, MiniMax, MiMo, and Qwen, including GLM 5.2 for deep reasoning, Kimi K2.7 Code for coding tasks, Kimi K2.6 for agentic workflows, DeepSeek V4 Pro for large changes, DeepSeek V4 Flash for fast iteration, MiniMax M3 for general coding, MiMo V2.5 Pro for pro workloads, MiMo V2.5 for efficient edits, Qwen3.7-Max for heavy workloads, and Qwen3.7-Plus for balanced coding.
  • 46
    AG2

    AG2

    AG2

    AG2 is the open source AgentOS for building production-ready AI agents and multi-agent systems in minutes, not months. Formerly AutoGen, it provides an open source Python framework for building, orchestrating, and scaling AI agents that can collaborate through shared context, use tools, execute workflows, and support both autonomous and human-in-the-loop patterns. AG2 is designed for developers who want to build systems, not prompts, with simple and intuitive syntax, built-in conversation patterns, and a flexible platform for multi-agent automation. Agents in AG2 can extend their capabilities with tools, allowing them to interact with external systems, fetch real-time data, execute code, search the web, process documents, and complete complex tasks beyond a model’s internal knowledge. It supports many LLM providers and local models, including OpenAI-compatible endpoints, Anthropic Claude, Gemini through Vertex AI, DeepSeek, and LM Studio.
  • 47
    Kimi Work

    Kimi Work

    Moonshot AI

    Kimi Work is a desktop AI productivity platform developed by Moonshot AI that acts as an intelligent local agent for knowledge workers. The application connects directly to local files, automates workflows, and performs browser-based tasks through its WebBridge automation capabilities. Users can delegate research, data collection, document generation, and repetitive tasks while Kimi Work executes them autonomously in the background. The platform includes scheduled task automation, allowing workflows, scripts, and AI-driven processes to run automatically at specified times. Kimi Work also supports agent collaboration through its Agent Swarm technology, enabling multiple specialized AI agents to work together on complex projects. By combining local file access, automation, web interaction, and AI-powered productivity tools, Kimi Work helps users streamline research, analysis, and knowledge work activities.
  • 48
    HostAiHub

    HostAiHub

    HostAiHub LTD

    HostAiHub is a managed hosting service for private instances of OpenClaw, Hermes, and n8n. Customers select an agent or workflow platform and deploy it in an isolated container with dedicated storage and an SSL-secured subdomain, without configuring servers themselves. A browser dashboard provides instance controls, while the service handles provisioning, updates, monitoring, and scheduled backups. Users can connect their own model-provider keys, with documented options including Anthropic, OpenAI, OpenRouter, DeepSeek, and Gemini; model usage is billed separately by the provider. HostAiHub also offers an OpenAI-compatible API service. Monthly, annual, and lifetime hosting plans are available, with prices varying by hosted platform and plan. The service is intended for founders, developers, agencies, and small teams that want to operate always-on AI agents or automated workflows without maintaining hosting infrastructure.
  • 49
    Odysseus

    Odysseus

    PewDiePie

    Odysseus is an open-source, self-hosted AI workspace that allows users to interact with language models directly on their own hardware. The platform combines AI chat, autonomous agents, research tools, model management, email assistance, and persistent memory into a single local-first environment. Users can connect their preferred language models and endpoints while maintaining complete control over their data and infrastructure. Built-in capabilities include tool integration, model comparison, deep research workflows, and support for MCP servers. Odysseus is designed with privacy in mind, operating without telemetry and keeping sensitive information within the user’s environment. By providing a unified workspace for AI-powered tasks, Odysseus helps users leverage advanced AI functionality without relying on third-party cloud platforms.
  • 50
    Macyou

    Macyou

    Macyou LLC

    Macyou rents dedicated Apple Silicon Macs for AI workloads. Users configure a Mac (M4 Mac mini to Mac Studio M3 Ultra with 256 GB unified memory), pick a pre-configured stack — local LLMs via Ollama (Llama, Qwen, Mistral, DeepSeek), agent frameworks (CrewAI, LangGraph), or ML dev environments (MLX, Jupyter) — and get a running deployment in about 5 minutes. Every deployment exposes an OpenAI-compatible API, so existing OpenAI SDK code works by changing base_url; access also includes SSH with root and a browser-based remote desktop. Each customer gets a dedicated physical machine with full-disk encryption and a disk wipe between tenants, hosted in a GDPR-friendly jurisdiction. Pricing is a fixed monthly fee per machine with no per-token charges; Thunderbolt 5 clustering pools unified memory across nodes for larger models. Published, measured inference benchmarks (raw JSON, CC BY 4.0) show real tokens per second per chip.