Audience
Mac users and developers seeking to run private local AI models and autonomous agents that can access files, tools, memory, and workflows
About Osaurus
Osaurus is a native AI harness for macOS that lets users run open models entirely on their Mac, connect cloud models when greater capability is needed, and carry shared memory across them. Built in Swift for Apple Silicon, it works fully offline with local models through Ollama, MLX, or LM Studio, keeping conversations, code, files, settings, agents, skills, and provider keys on the device unless the user explicitly chooses a cloud provider. A system-wide chat overlay provides quick access from any app, while separate agents can be created for coding, research, file organization, and other jobs, each with its own prompt, history, and memory. Osaurus distills past conversations into relevant facts, loads packaged skills when tasks require them, and gives agents scoped access to working folders, file search, Git, and other tools. Agents can run code in an isolated sandbox, delegate work to subagents, operate on schedules, respond to folder changes, use voice input, and generate images.
Other Popular Alternatives & Related Software
dcode
dcode is an open-source terminal coding agent for developers and software teams. Built on the Deep Agents SDK, it can plan and execute coding tasks, inspect and edit project files, run tools, and delegate work to subagents. Its interactive terminal interface streams responses and lets users resume conversations across sessions; headless mode supports scripted and CI workflows. Users select a compatible model provider and supply their own credentials, then customize models, tools, plugins, skills, memory, middleware, hooks, and approval rules. Tool calls can be approved or rejected, and code can run locally or in supported remote sandboxes. dcode supports MCP tools and can connect to LangSmith for tracing prompts, responses, tool calls, errors, and token usage. It is intended for developers who want to configure and inspect an AI coding agent rather than use a fixed coding assistant.
Learn more about dcode
eve
eve is an open source framework for building AI agents that you own, designed around a file-system-based structure and production-ready runtime. An instructions.md file is enough to define an agent, while optional building blocks such as model configuration, skills, tools, sandboxes, channels, connections, subagents, schedules, and evals can be added as the agent grows. Tools are created by dropping TypeScript files into the tools directory, and skills are written as Markdown playbooks that load only when relevant. Agents can connect to services such as GitHub, Stripe, and Linear through authenticated connections and can surface through Slack, Discord, Teams, web chat, APIs, cron jobs, CLIs, and custom applications from the same codebase. Specialized subagents can handle delegated work with their own prompts, tools, and sandboxes.
Learn more about eve
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.
Learn more about Autopilot by Directionally Local
OpenCraft AI
OpenCraft AI (Ocai) is an AI agent platform for individuals, professional teams, and enterprises. Users can delegate multi-step work to agents that use code, files, web search, and sandboxed tools; agents can run subagents in parallel, retain project context across sessions, and switch models when a task stalls. The platform supports research, document and data analysis, coding, content production, retrieval, and multimodal work. It offers a browser-based service and a desktop app for workflows involving projects and local files. Agencies, founders, lawyers, content creators, and enterprise departments can use it for research, drafting, code analysis, marketing content, sales materials, and operations documentation. Self-serve pricing uses pay-as-you-go credits, with free credits to start.
Learn more about OpenCraft AI
Pricing
Free Version:
Free Version available.
Integrations
Company Information
Osaurus
United States
osaurus.ai/
Videos and Screen Captures
Other Useful Business Software
Build Agents and Models on One Platform
Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
Product Details
Platforms Supported
Mac
Training
Documentation
Support
Online
Osaurus Frequently Asked Questions
Q: What kinds of users and organization types does Osaurus work with?
Osaurus works with these users and organization types: Mid Size Business, Small Business, Enterprise, Freelance, Nonprofit, Government, and Startup.
Q: What languages does Osaurus support in their product?
Osaurus supports these languages: English.
Q: What kind of support options does Osaurus offer?
Osaurus offers support via online.
Q: What other applications or services does Osaurus integrate with?
Osaurus integrates with: ChatGPT, Claude Duet, Claude for Legal, Claude, Git, Gemini, LM Studio, Hardskills, Ollama, and Swift.
Q: What type of training does Osaurus provide?
Osaurus provides training in the form of documentation.
