AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Vision / Multimodal/
vestige
vestige logo

vestige

Active·★ 655·AGPL-3.0·Updated 2026-10-20

Vestige is a cognitive engine built on 130 years of memory research, designed to provide AI with persistent memory capabilities. It prevents AI from forgetting information between sessions through advanced techniques like spaced repetition and memory dreaming, all running locally with a 3D neural visualization dashboard.

vestige sits in the Vision / Multimodal category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward 3D Memory Dashboard with real-time neural visualization.. A representative use case is Providing AI agents with persistent, long-term memory to prevent forgetting between sessions.. The listed license is AGPL-3.0. GitHub stars are currently 655. Relevant tags include Cognitive Engine, AI Memory.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#Cognitive Engine#AI Memory#Spaced Repetition#Knowledge Graph#Rust#3D Visualization#Local AI#NLP
$ Install
$ curl -L https://github.com/samvallad33/vestige/releases/latest/download/vestige-mcp-aarch64-apple-darwin.tar.gz | tar -xz && sudo mv vestige-mcp vestige vestige-restore /usr/local/bin/
↗ Visit site★ GitHub
01

Features

013D Memory Dashboard with real-time neural visualization.
02Implements advanced cognitive science techniques like FSRS-6 spaced repetition and memory dreaming.
03100% local operation ensures privacy and zero cloud dependency.
04HyDE Query Expansion dramatically improves search quality for conceptual queries.
05Compatible with various AI tools and IDEs via the Model Context Protocol (MCP).
02

Why choose it

+3D Memory Dashboard with real-time neural visualization.
+Implements advanced cognitive science techniques like FSRS-6 spaced repetition and memory dreaming.
+Providing AI agents with persistent, long-term memory to prevent forgetting between sessions.
+Supports 5 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

Rust
Runtime
Verified via docs
Local Systems
Deployment
Verified via docs
Model Context Protocol (MCP)
Standard
Verified via docs
AI IDEs
Integration
Verified via docs
npm
Package Manager
Verified via docs
05

Quick start

1
$ curl -L https://github.com/samvallad33/vestige/releases/latest/download/vestige-mcp-aarch64-apple-darwin.tar.gz | tar -xz
2
$ sudo mv vestige-mcp vestige vestige-restore /usr/local/bin/
06

Use cases

↳Providing AI agents with persistent, long-term memory to prevent forgetting between sessions.
↳Automatically learning and recalling user preferences and project-specific context for improved AI interactions.
↳Consolidating and synthesizing insights from past interactions through "memory dreaming."
↳Integrating with various IDEs and AI tools to enhance their context-awareness and knowledge retention.
07

Alternatives

⚡Top VS:
VSshodh-memory★314→VSConcat★10.5k→VSPPTAgent★5.1k→VSmemorix★854→
shodh-memory logo
shodh-memory★ 314
Cognitive brain for Claude, AI agents & edge devices — learns with use, runs offline, single binary. Neuroscience-grounded 3-tier architecture with Hebbian learning.
VSCompare→
Concat logo
Concat★ 10.5k
The truly free, and open-source cross-platform CapCut replacement (supports MCPs).
VSCompare→
PPTAgent logo
PPTAgent★ 5.1k
An Agentic Framework for Reflective PowerPoint Generation
VSCompare→
memorix logo
memorix★ 854
Cross-Agent Memory Bridge Persistent memory for AI coding agents across Cursor, Windsurf, Claude Code, Codex, Copilot, Kiro via MCP. Never re-explain your project again.
VSCompare→
CodeFuse-muAgent logo
CodeFuse-muAgent★ 777
An Innovative Agent Framework Driven by KG Engine
VSCompare→
rms-memory-mcp logo
rms-memory-mcp★ 40
Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency
VSCompare→
kaeru logo
kaeru★ 40
Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
VSCompare→
dense-mem logo
dense-mem★ 39
Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and Neo4j.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
samvallad33 /
vestige
↗

Cognitive memory for AI agents — FSRS-6 spaced repetition, 29 brain modules, 3D dashboard, single 22MB Rust binary. MCP server for Claude, Cursor, VS Code, Xcode, JetBrains.

655AGPL-3.0
Last commit3d ago
StatusActive
CategoryVision / Multimodal
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.