Eugene Sukhodolskiy
authored
on 24 Apr
|
|
.. |
|
|
|
|
api
|
Make server I/O non-blocking; update docs
|
2 months ago
|
|
|
core
|
Set temperature=1.0, top_k=64, top_p=0.95 for all profiles (Google recommended for gemma4)
|
2 months ago
|
|
|
llm
|
Set temperature=1.0, top_k=64, top_p=0.95 for all profiles (Google recommended for gemma4)
|
2 months ago
|
|
|
memory
|
Improve memory search: normalize query, AND-first, relevance scoring
|
2 months ago
|
|
|
profiles
|
Set temperature=1.0, top_k=64, top_p=0.95 for all profiles (Google recommended for gemma4)
|
2 months ago
|
|
|
tools
|
Add Ollama multi-server fallback with in-memory blacklisting
|
2 months ago
|
|
|
workers
|
Autonomous reasoning improvements: budget, anchoring, anti-stall, validation
|
2 months ago
|
|
|
__init__.py
|
Initial implementation of the agent system core
|
2 months ago
|
|
|
config.py
|
Add Ollama multi-server fallback with in-memory blacklisting
|
2 months ago
|
|
|
exceptions.py
|
Add Ollama multi-server fallback with in-memory blacklisting
|
2 months ago
|
|
|
main.py
|
Add standalone debug page at /debug
|
2 months ago
|
|
|
session_files.py
|
Make server I/O non-blocking; update docs
|
2 months ago
|
