A local multi-agent framework where your AI agents keep their memory, work together, and never ask you to re-explain context
Cross-referenced across 55 tracked directories
#3328
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
2/27/2026
Created
319
GitHub Stars
46
Forks
3
Contributors
3
Open Issues
11/17/2026
Last Commit
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
Yashvardhan 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.
...moreNORTHTEKDevs
DNA-inspired memory layer for AI agents: zero-LLM-call ingestion, retrieval that beats full-context on overflowing histories.
...moreBrightbeam AI <[email protected]>
CHAP adapter for AG2 (AutoGen): record a human-decision envelope at the human-input turn.
NextEleven LLC
Local DeadBolt sidecar client and optional OpenAI Agents SDK function-tool integration