Core AI Models
The repository ships three concrete layers: Python export recipes for popular Hugging Face models, reusable PyTorch primitives for…
VerifiedOSS
View tool Inference Engines & Infra
ML infrastructure, inference, and ops.
Project Huginn
Hugin pools heterogeneous GPUs from across its network — ranging from 2GB to 32GB+ VRAM — and routes training jobs through a six-step…
VerifiedFreemium
View tool 
SigmaShake
SigmaShake intercepts tool calls from agents running in Claude Code, Cursor, VS Code Copilot, and Gemini CLI, evaluating each action…
Verified
View tool 
PandaProbe Cloud
The core loop is trace, eval, monitor: capture every span across a session, run research-grounded scoring against those traces, then…
VerifiedFreemium
View tool 
ArXiv Scholar
ArXiv Scholar is an open-source RAG infrastructure that indexes roughly 5,600 curated AI engineering papers from arXiv and exposes them…
VerifiedOSS
View tool 
PromptShark
PromptShark is a local MITM proxy written in Go and C++ that sits between your agent and any OpenAI-compatible API endpoint. Every request…
VerifiedOSS
View tool 
gate-oc-audit
Gate operates as a drop-in proxy: your agent points at one endpoint, Gate inspects every outbound prompt and every inbound response, then…
VerifiedOSS
View tool 
Dream Server
The installer handles the assembly: LLM inference via Ollama, a chat interface, voice input/output, RAG over private documents, local image…
VerifiedOSS
View tool 
ComplyEdge
ComplyEdge is an open-source compliance engine that runs on every production request your AI agent processes, enforcing EU AI Act Article 5…
VerifiedOSS
View tool