An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine that drafts and verifies its own tokens.

53 stars 5 forks 53 watchers Python GNU Affero General Public License v3.0
ai-agents dgx-spark exl3 inference-engine llm-inference local-ai nvfp4 quantization qwen self-hosted speculative-decoding
3 Open Issues Need Help Last updated: Oct 16, 2026

Open Issues Need Help

View All on GitHub

An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine that drafts and verifies its own tokens.

Python
#ai-agents#dgx-spark#exl3#inference-engine#llm-inference#local-ai#nvfp4#quantization#qwen#self-hosted#speculative-decoding

An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine that drafts and verifies its own tokens.

Python
#ai-agents#dgx-spark#exl3#inference-engine#llm-inference#local-ai#nvfp4#quantization#qwen#self-hosted#speculative-decoding

An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine that drafts and verifies its own tokens.

Python
#ai-agents#dgx-spark#exl3#inference-engine#llm-inference#local-ai#nvfp4#quantization#qwen#self-hosted#speculative-decoding