Morph MORPH
SIGN IN SIGN UP
janhq / jan UNCLAIMED

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

0 0 4 TypeScript

COMMITS

main
April 17, 2026
A
fix: prevent CUDA paths from being overwritten by library path setup (#7978)
Akarshan Biswas committed
9fad861
April 16, 2026
J
fix: restore MCP startup error dialog (#7038) (#7940)
Jordan committed
3d9cecb
J
fix: normalize MCP tool schemas for strict provider validation (#7017) (#7941)
Jordan committed
afeb55c
K
Hide Gemma models reasoning tags (#7948)
Kirsa Denis committed
def32f8
A
test: add comprehensive JS test coverage (#7970)
Akarshan Biswas committed
68164ff
April 15, 2026
W
fix: prevent long non-breaking URLs from overflowing project view (#7… (#7961)
web-dev0521 committed
e601157
F
fix(web): detect real Tauri runtime on localhost (#7962)
Full Stack Engineer committed
104c62c
A
CI: Add Rust coverage job to CI workflows (#7964)
Akarshan Biswas committed
bad0d98
A
fix: embeddings/inline inject ux (#7963)
Akarshan Biswas committed
ece9466
April 14, 2026
D
feat: File attachment progress bar (#7942)
dataCenter430 committed
a41f294
April 12, 2026
B
refactor: extract duplicated window instance object into helper (#7938)
BitCompass committed
630385b
April 10, 2026
J
fix: restore Gemini SDK adapter for MCP tool calls (#7535) (#7927)
Jordan committed
5ffbe87
F
fix: remove core default permissions to unblock Tauri dev build (#7902)
Full Stack Engineer committed
8233454
April 9, 2026
J
fix: centralize Jan data folder path resolution (#7522) (#7929)
Jordan committed
e652737
S
fix: improve llama.cpp context meter for tool-heavy chats (#7913)
SmartCoder committed
d62517e
April 8, 2026
Y
docs: add Chinese translation (README.zh.md) (#7745)
YE committed
64d0573
J
fix: restore no-mmproj-offload flag wiring for multimodal models (#7924) (#7925)
Jordan committed
0451320
A
fix: don't select CUDA backend if GPU has insufficient memory (#7894)
Anatoli Babenia committed
5de83fa
A
chore: Fix warnings and move foundation models to MacOS only (#7923)
Akarshan Biswas committed
db9dd18
F
fix(desktop): persist app config in Tauri app data dir (#7903)
Full Stack Engineer committed
372ad15
B
fix: add Flatpak CUDA library path discovery and GL extension support for NVIDIA GPU access (#7905)
BitToby committed
7696d71
April 7, 2026
F
fix: remove font style last used assistant options (#7910)
Faisal Amir committed
37b6d0c
R
fix: handle pdf parser panic and enforce file size limit (#7157)
Roushan Kumar Singh committed
27a96bb
J
fix: verify stdio MCP tools/list before emitting ready event (#7892)
JD Mills committed
3e7cabc
F
Merge pull request #7909 from janhq/fix/responsive
Faisal Amir committed
d97f171
F
fix: responsive setting
Faisal Amir committed
9f53a38
S
fix: hide llama.cpp backend update prompt when provider is disabled (#7906)
SmartCoder committed
479c9df
April 6, 2026
T
feat: expand supported file types for document attachments to include many other extensions (#7859)
Tony committed
fecf314
A
fix: avoid CoT wrapper when group has no reasoning parts (#7899)
Akarshan Biswas committed
3f20255
A
feat: implement initial Chain of Thought (#7897)
Akarshan Biswas committed
a2e0522