PG-Git Semantic Memory

2

PostgreSQL-backed semantic Git storage for AI coding agents with pgvector embeddings, local Ollama models, and temporal decay scoring.

GitHub
Category Models
Added May 23, 2026
Views 39

About

PG-Git Semantic Memory persists the Git DAG in PostgreSQL with vector embeddings generated by Ollama, enabling AI agents to find code based on what it does rather than syntax alone. It applies temporal decay to reduce relevance of older commits, stores all data locally for privacy, and supports concurrent multi-agent access via ACID-compliant transactions.

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/pg-git-semantic-memory.svg)](https://hifriendbot.com/ai-list/pg-git-semantic-memory/)
Listed on AiList

Compare

PG-Git Semantic Memory vs Krusch Memory PG-Git Semantic Memory vs Continuum PG-Git Semantic Memory vs Medha

Similar Projects

Krusch Memory

4

Persistent local-first semantic memory for AI agents with vector embeddings, temporal decay, and SQLite/PostgreSQL support.

Agents

Continuum

7

Local-first developer memory system that captures coding context from git commits with temporal decay and cross-project learning.

MCP Servers

Medha

13

Git-backed memory system that stores and organizes memories as markdown files in local or remote repositories, providing persistent context across conversations through recall, storage, linking, and temporal queries with automatic synchronization and intelligent organization by tags, categories, or

MCP Servers Go

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project