Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

lint fix (#18081)
Daniel Hiltgen committed 2 months ago
f96e7aa
Clean up dead code (#17381)
Daniel Hiltgen committed 2 months ago
6879311
f4025ed
app: synchronize macOS app handoff (#18056)
Parth Sareen committed 2 months ago
39f7f91
app: restore system dark mode (#18049)
Eva H committed 2 months ago
a67fe8c
app: consume Claude recommendation mappings (#18042)
Parth Sareen committed 2 months ago
13f2fb8
mlx: remove the text-only gemma3 model
Jesse Gross committed 2 months ago
3b96a89
launch: respect OLLAMA_HOST when configuring Pi (#18039)
Daniel Hiltgen committed 2 months ago
91cf995
linux: fix llama.cpp docker build (#18040)
Daniel Hiltgen committed 2 months ago
d3a8af4
MLX: Qwen3.8 Flash Next support (#18032)
Daniel Hiltgen committed 2 months ago
18ea9de
docs: claude docs (#18006)
Parth Sareen committed 2 months ago
e2c6c7e
docs: document Claude Desktop integration (#18004)
Parth Sareen committed 2 months ago
9dbf139
mlxrunner: add structured output support
Jesse Gross committed 3 months ago
147509c
7027546
llama.cpp: version bump b10630 (#18003)
Daniel Hiltgen committed 2 months ago
3d86a55
MLX: version bump (#17955)
Daniel Hiltgen committed 2 months ago
d465dc7
ad94d52
ebf200f
075aa7e
6e19e91
f6c59d8
app: add Claude Desktop Auto mode setting (#17975)
Parth Sareen committed 2 months ago
82ad9fa
app: make integrations list scrollable (#17977)
Parth Sareen committed 2 months ago
60d83f8
9394251