Fetching metadata from the HF Docker repository...
-
Add persistent memory, memory tools, live btop-style monitor, new 3-column UI
Hermes Agent
-
Add Phi-4-mini-3.8B model with auto-download
Hermes Agent
-
Add append-only chat.log + /logs endpoint
Hermes Agent
-
Fix tool hallucination: only multiply allowed, no get_tools
Hermes Agent
-
Robust /start: kill zombies, wait for free port, health check
Hermes Agent
-
Wake up space
Hermes Agent
-
Remove unsupported DiffusionGemma 26B, keep only Qwen-Coder models, 3B default
Hermes Agent
-
Fix llama.cpp clone: full clone with origin/master checkout
Hermes Agent
-
Update Dockerfile to latest ggml-org/llama.cpp main branch for diffusion-gemma support
Hermes Agent
-
Set DiffusionGemma 26B as default model
Hermes Agent
-
Frontend v2: loading bar, processing indicator with timer, auto-poll server ready
Hermes Agent
-
Add DiffusionGemma 26B model option to dropdown
Hermes Agent
-
Fix tool-call hallucination: only real tools, 3B default, tool-call rendering
Hermes Agent
-
Add llama-server start/restart button to chat UI + auto-start
Hermes Agent
-
Frontend: disable reasoning/thinking tags, enforce direct tool-call JSON
Hermes Agent
-
Use health-check for server_running() instead of /proc scan
Hermes Agent
-
Fix Python 3.9 type hints for HF Space compatibility
Hermes Agent
-
Add OpenAI-compatible /v1/chat/completions proxy, tool-ready frontend, httpx dep
Hermes Agent
-
Add chat frontend (HTML/CSS/JS) and static file serving
Hermes Agent
-
llama.cpp integration: update deps, add FastAPI endpoints for model download/chat/server
Hermes Agent
-
Create Dockerfile
-
Create app.py
-
Create requirements.txt
-
initial commit