Subconscious

Local-first semantic memory layer for MCP agents with recall, remember, forget, and stats tools backed by ChromaDB.

Visit Site GitHub
Category MCP Servers
Added May 23, 2026
Views 92

About

Subconscious is a local-first memory MCP server that enables AI agents to persist and retrieve semantic memories across sessions. Using ChromaDB with Hugging Face sentence-transformers for 384-dimensional embeddings, it provides tools to remember task answers, recall semantically similar past knowledge, forget entries, and view usage statistics. All data stays on the local machine with no external calls.

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/subconscious.svg)](https://hifriendbot.com/ai-list/subconscious/)
Listed on AiList

Compare

Subconscious vs mnemosyne Subconscious vs BlueColumn Subconscious vs Stellar Memory

Similar Projects

mnemosyne

151

Local-first long-term memory for AI agents: an MCP server, TypeScript SDK, CLI and HTTP service over one SQLite file. Evidence-backed recall, corrections that retire stale guidance, temporal history. 409/500 on LongMemEval-S with the misses published.

MCP Servers

BlueColumn

Persistent semantic memory for AI agents — remember, recall, and store observations across sessions with vector search.

Agents

Stellar Memory

Persistent local-first AI memory system using orbital mechanics for importance-based recall.

MCP Servers

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project