GoKawiil๐๏ธ Our Founder! of this project is battling cancer. Your Stars and Forks are appreciated. ๐๏ธ
๐ฆพ Agent! for macOS 26.4+ Agentic AI for your ๏ฃฟ Mac Desktop Open Source replacement for Claude Code, Cursor, Cline, OpenClaw
What's New ๐
Apple AI as a real tool-calling agent: On-device Apple Intelligence (FoundationModels.Tool) handles UI automation requests like "take a photo using Photo Booth" locally โ multi-step tool calls, zero cloud LLM tokens, falls through to the cloud LLM only on failure.
On-device Apple Intelligence (FoundationModels.Tool) handles UI automation requests like "take a photo using Photo Booth" locally โ multi-step tool calls, zero cloud LLM tokens, falls through to the cloud LLM only on failure. SDEF + runtime app discovery: Bundle ID resolution is now zero-hardcoded. Apps in Agent/SDEFs/ plus every .app in /Applications , /System/Applications , ~/Applications are discovered at runtime โ installing a new app extends what the agent can target with no code edit.
Bundle ID resolution is now zero-hardcoded. Apps in plus every in , , are discovered at runtime โ installing a new app extends what the agent can target with no code edit. Prompt caching for every OpenAI-format provider: Z.ai, OpenAI, Grok, Mistral, DeepSeek, Qwen, Gemini, BigModel, Hugging Face โ cached_tokens is parsed from the response and shown in the LLM Usage panel. JSON request bodies use .sortedKeys so byte-stable prefixes actually hit the provider's cache.
Z.ai, OpenAI, Grok, Mistral, DeepSeek, Qwen, Gemini, BigModel, Hugging Face โ is parsed from the response and shown in the LLM Usage panel. JSON request bodies use so byte-stable prefixes actually hit the provider's cache. On-device token compression: Apple AI summarizes old conversation turns when context exceeds 30K tokens (Tier 1 of tieredCompact ) โ free, private, no API tokens consumed. Toggleable in the brain icon popover.
Apple AI summarizes old conversation turns when context exceeds 30K tokens (Tier 1 of ) โ free, private, no API tokens consumed. Toggleable in the brain icon popover. Anti-hallucination prompt rule: Every system prompt now includes explicit guidance against fabricating findings from incomplete tool reads. The 10-consecutive-reads guard pushes the model toward "narrow or call done()" instead of "guess".
Every system prompt now includes explicit guidance against fabricating findings from incomplete tool reads. The 10-consecutive-reads guard pushes the model toward "narrow or call done()" instead of "guess". Autonomous task loop, Xcode integration, AXorcist desktop automation, privileged daemon, multi-tab LLM config, Ollama pre-warming via LLMRegistry โ all the previously-shipped fundamentals are still there.
One app. Any AI. Total command over your Mac.
... continue reading