Recalld

About Recalld

Recall, not retrain. Persistent, curated memory for AI agents that returns only the facts that matter.

In the maker’s words

Recalld is a memory layer for AI agents and chats. It can ingest conversations, documents or code. The input is decomposed into facts, then saved into a vector database. I built Recalld because I couldn't find a reliable memory layer that let my agents retrieve accurate data without noise. The facts from each add operation are compared with existing facts, and Recalld then decides whether each one is an addition, an update or a replacement of existing facts. Agents can retrieve context via two methods. The first is search, which is faster and cheaper and performs a vector search. The second option is recall which uses an LLM to select relevant facts. In our published benchmark on LoCoMo benchmark run, it returned an average of about 243 context tokens per question. See the benchmarks for more details: https://github.com/bit-robotics/recalld-benchmarks Recalld can be accessed via API or M…

Where people found it

• Hacker NewsShow HN: Recalld – A memory layer for AI agents that returns only relevant facts4 points0 comments5 days ago