Category
Local inference engine for DeepSeek V4 Flash/PRO and GLM 5.2
Agentic AI framework for the JVM
Open-source AI coding agent you can leave running locally.
Run huge LLMs on low-end GPUs with minimal VRAM
Accelerate AI applications with caching technology
Compress LLM context before it reaches the model
Self-host API execution for AI agents
Next-gen coding agent harness for efficient workflows
Smart AI Router with 3-Tier Fallback
Open-source GEO tracker: see how LLMs describe your brand
Self-hosted AI coding assistant server for private team deployment
Delegate scoped coding tasks in isolated, reviewable agent sessions
