52 projects
kayak
Mojo-first late-interaction retrieval engine
retrain
RLVR training framework for LLMs
playstack
Add your description here
gameplay
Add your description here
splay
Add your description here
actu
Add your description here
ambo
Add your description here
ordeal
Automated chaos testing for Python — fault injection, property assertions, and stateful exploration.
vauban
LLM red-teaming and adversarial testing framework
tmesis
Add your description here
bistouri
Add your description here
speedrl
Add your description here
textpolicy
Reinforcement learning for text generation on MLX (Apple Silicon): GRPO/GSPO, environments, rollout, rewards, LoRA/QLoRA
enzu
Budgeted LLM task orchestration with hard limits and long-context RLM.
reor
Add your description here
reri
Add your description here
hule
Add your description here
vectis
Add your description here
adjoint
Add your description here
trainerkit
Add your description here
mlx-rl
train models using MLX
purp
None
mcp-sql
Add your description here
materl
Add your description here
campus
Add your description here
manoeuvre
Add your description here
supplychain
Add your description here
kushim
A framework for building high-quality, verifiable evaluation datasets for LLMs.
remamba
Add your description here
enbu
Add your description here
binet
Add your description here
neau
Add your description here
mcp-eval
Evaluate MCP models
yaufrl
Add your description here
jiki
A flexible LLM orchestration framework with tool calling capabilities via MCP protocol
deltavar
Tools to calculate the Delta Variance for epistemic uncertainty estimation in PyTorch, using torch.func.
trainar
Add your description here
morphing
Add your description here
mcp-trainer
Add your description here
poietic
Add your description here
hapax
A type-safe graph execution framework built on top of OpenLit for LLM pipelines
reallm
Reinforcement Agent Learning Language Model
oteilo
A collection of intuitive Python utilities for common development tasks
quantmax
Quantization made with Max efficiency.
patchfinder
Plug-and-play document readability and extraction toolkit for VLMs.
operatio
None
inferencemax
None
maxinference
None
potaras
None
ragga
None
apoo
Automatic Prompt Optimizer
convector
A tool for transforming conversational data to a unified format
