Recall

Persistent memory system with SQLite-backed hybrid search combining full-text and vector similarity for cross-agent knowledge sharing.

Visit Site GitHub
Category Agents
Added Mar 28, 2026
Views 50

About

Recall provides a shared persistent memory system that enables AI agents to remember, search, and forget information across sessions. It uses SQLite with FTS5 full-text search and 384-dimensional vector similarity via sqlite-vec for hybrid retrieval. Multiple agents can connect simultaneously through SSE transport with Bearer token authentication, enabling cross-agent knowledge sharing. The system includes automatic memory decay with configurable garbage collection, rich metadata support with namespaces, categories, tags, and weights, and local embeddings using MiniLM-L6-v2 with no external API dependencies.

Is this your product? Claim this listing with an email at your domain to post updates.

Is this your project?

Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.

Log In to Claim

Share This Project

Share on X Share on LinkedIn

Embed Badge

Add this badge to your README:

[![Listed on AiList](https://hifriendbot.com/ai-list/badge/recall.svg)](https://hifriendbot.com/ai-list/recall/)
Listed on AiList

Compare

Recall vs MemorizedMCP Recall vs Knowledge Base RAG (PaulTheSecond) Recall vs Oracle v2

Similar Projects

MemorizedMCP

5

MemorizedMCP delivers a high‑performance, local‑first MCP Server in Rust that equips AI agents with an advanced hybrid memory system. It combines a knowledge graph, vector embeddings, and full‑text search with a novel documentary memory capability, enabling accurate recall of exact documents alongsi

MCP Servers

Knowledge Base RAG (PaulTheSecond)

Hybrid search knowledge base combining full-text (FTS5) and vector similarity for document retrieval.

MCP Servers

Oracle v2

45

Combines semantic vector search with full-text search to create an intelligent knowledge management system that indexes markdown documents, stores them in SQLite with FTS5 and ChromaDB for hybrid search, and provides decision tracking with GitHub issue integration.

MCP Servers

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project