Run many AI agents at once on your Mac, up to 3x faster: an OpenAI- and Ollama-compatible MLX server with batched decoding, a prompt cache, and tool calls and JSON that always parse
Cross-referenced across 55 tracked directories
#3023
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
10/12/2026
Created
743
GitHub Stars
37
Forks
2
Contributors
7
Open Issues
11/4/2026
Last Commit
Recently added to the ecosystem
NORTHTEKDevs
DNA-inspired memory layer for AI agents: zero-LLM-call ingestion, retrieval that beats full-context on overflowing histories.
...moreYashvardhan Thanvi <[email protected]>
Cut your LLM prompt size by 40-70% in one line of code -- semantic chunking + extractive summarization that preserves meaning, instructions, and key entities.
...moreBrightbeam AI <[email protected]>
CHAP adapter for AG2 (AutoGen): record a human-decision envelope at the human-input turn.
"deepset.ai" <[email protected]>
LLM framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data.
...more