osaurus-ai/

osaurus

GitHub Website

Osaurus is a macOS native Swift harness for AI agents that runs offline on Apple Silicon, offering memory, tools, identity, and MCP server capabilities. It supports multiple providers, local and cloud models, and a plugin/registerable tool ecosystem.

7.5kstars

428forks

152issues

MITlicense

2025since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

affaan-m/

ECC

▲ 2.9k/wk

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

238k36kJavaScript

headroomlabs-ai/

headroom

▲ 1.7k/wk

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

65k4.9kPython

sansan0/

TrendRadar

▲ 183/wk

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

61k25kPython

upstash/

context7

▲ 330/wk

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

60k2.9kTypeScript

NousResearch/

hermes-agent

▲ 3.5k/wk

The agent that grows with you

225k44kPython

n8n-io/

n8n

▲ 886/wk

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

199k60kTypeScript

Compareosaurus vs ECC osaurus vs headroom osaurus vs TrendRadar

Reviewgenerated from repository data · Aug 5, 2026

What it is

Osaurus is the AI harness for macOS written in Swift. It runs fully offline, supports local and cloud models, and provides agents with memory, tools, and cryptographic identity. It includes an MCP server and plugin/registry mechanisms.

How it works

The project exposes an interface between users, agents, memories, and tools. It supports local models from a curated MLX-based library, Apple Foundation Models on macOS 26+, and cloud providers. It includes features like private local databases, self-scheduling for agents, a sandboxed Linux VM for agent execution, memory consolidation, privacy filtering, a secure channel for agent communication, and a relay to expose agents via secure WebSocket tunnels. It also offers subagents, a built-in browser per agent, and image generation capabilities, with plugin support and an MCP stdio bridge.

Getting started

Install:

brew install --cask osaurus

Or download the latest .dmg from Releases. After installing, launch from Spotlight or the CLI:

osausurus ui       # Open the chat UI
osaurus serve    # Start the server
osaurus status   # Check status

Requires macOS 15.5+ and Apple Silicon.

Recent releases

Latest release: 0.22.16 Osaurus 0.22.16 (2026-08-04):

chat import improvements (#2251) by @RaajeevChandran
Add optional shadow style for chat input (#2256) by @hkay-dev
Repin vMLX to the disk-store offset guard (#2276) by @jjang-
wa-helper-v0.2.3 osaurus-wa helper v0.2.3 (2026-08-04): WhatsApp Web bridge helper for the Osaurus WhatsApp channel.

Changes since v0.2.2 include various fixes and repins.

Traction

Stars: 7514 Forks: 428 Open issues: 152

Behind the repo

Not provided in the excerpt.

Caveats

License: MIT Created: 2025-08-17 Last push: 2026-08-04 Platform note: macOS 15.5+ and Apple Silicon required.

SharePost on X LinkedIn