l33tdawg

l33tdawg / sage

Public

(S)AGE - (Sovereign) Agent Governed Experience

orcid.org0009-0001-7248-2411 agentic-ai artificial-intelligence bft-consensus bft-network distributed-systems
19
2
100% credibility
Found Mar 08, 2026 at 19 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Go
AI Summary

SAGE provides a local, consensus-validated memory system for AI agents like ChatGPT, enabling persistent recall and learning across sessions via browser extensions and easy deployment.

How It Works

1
🔍 Discover persistent AI memory

You hear about SAGE, a way to give your AI chats like ChatGPT a real memory that sticks between conversations, making it smarter over time.

2
📥 Download the easy launcher

Grab the simple app for your computer that sets everything up with a few clicks—no tech skills needed.

3
🧙 Run the friendly setup wizard

Follow the guided questions to connect your personal memory brain, and it launches ready to use.

4
🧠 Add to ChatGPT with browser helper

Install the little brain button extension, connect it, and teach ChatGPT to use its new memory.

5
💭 Chat and watch it remember

As you talk, ChatGPT pulls up past details automatically and saves new insights, feeling like it truly learns from you.

🚀 Your AI gets smarter every day

Over time, conversations build on real history—smarter answers, fewer repeats, and a helpful companion that grows with you.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 19 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is sage?

SAGE builds a sovereign blockchain for AI agent memory using Go and CometBFT consensus. Agents submit natural-language facts, observations, or inferences via a REST API—tagged by domain, embedded with Ollama, and validated by Proof-of-Experience voting before commitment to PostgreSQL with vector search. Developers get tamper-proof recall through similarity queries, confidence scoring with decay, and lineage tracking, solving agent amnesia without cloud reliance.

Why is it gaining traction?

Unlike centralized vector DBs, SAGE offers local Docker Compose testnets with 4 validators, Ed25519-signed API calls, Python SDK, and a ChatGPT Chrome extension for seamless tool calls like sage_turn or sage_recall. GitHub sage attention roots draw devs experimenting with governed experiences, while graph sage github vibes appeal to knowledge graph builders. No vendor lock-in hooks self-sovereign agent teams.

Who should use this?

AI engineers building persistent agents for ChatGPT or local LLMs, needing domain-specific recall like crypto intel or vuln research. Devs prototyping decentralized memory for multi-agent systems, or teams wanting voting-based curation over raw embeddings. Ideal for github sage proteomics or steam modders tracking shared recipes.

Verdict

Grab it for agent memory prototypes—Docker setup shines, API is intuitive. But 19 stars and 1.0% credibility score mean it's raw; expect iteration on stability before production.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.