AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Memory & Context/
MAMA
MAMA logo

MAMA

Active·★ 15·MIT·Updated 2026-10-17

MAMA OS provides local operating memory for AI agents, enabling them to connect diverse data sources like chats and documents into a searchable memory substrate. It allows agents to understand context, cite evidence, track decision evolution, and operate within defined boundaries to produce better briefings and actions.

#Local Operating Memory#AI Agents#Knowledge Graph#Context Management#Provenance#Security#Hybrid Search
© 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.

Guides
#Workflow Automation
$ Install
$ claude auth login && npx @jungjaehoon/mama-os init && mama start
↗ Visit site★ GitHub
01

Features

01Enables AI agents to read the board, cite evidence, and operate within explicit boundaries using local operating memory.
02Integrates diverse data sources like chats, documents, decisions, and work logs into a unified local memory substrate.
03Builds a knowledge graph that tracks decision evolution, including relationships like 'supersedes', 'builds on', and 'debates'.
04Features strict and balanced search modes that reject vector-only noise unless confirmed by lexical, entity, raw, or seed evidence.
05Ensures agent security through signed runtime envelopes, scope boundaries, and destination limits enforced before tool calls.
02

Compatibility

Node.js
Runtime
Verified via docs
Claude Code CLI
Tool Integration
Verified via docs
Codex CLI
Tool Integration
Verified via docs
SQLite
Database
Verified via docs
03

Quick start

1
$ claude auth login
2
$ npx @jungjaehoon/mama-os init
3
$ mama start
04

Use cases

↳Assess Project Risk: An agent can assess project risk by synthesizing information from emails, Slack, PR status, and QA checklists.
↳Generate Cited Reports: Produce detailed situation reports and briefings for humans, explicitly citing evidence and separating judgment from inference.
↳Automate Workflow Triggers: An agent authors its own triggers from recurring situations, recalling relevant memory and folding everything into owner situation reports.
↳Manage Company Memory Twin: Maintain an append-only company memory twin that agents can inspect, simulate, and cite, preserving raw evidence and its evolution.
05

Alternatives

⚡Top VS:
VSmcp-local-memory★60→VScruxible★17→VSmnemo★12→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
VS
infimium-agent
★25
→
mcp-local-memory logo
mcp-local-memory★ 60
A lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.
VSCompare→
cruxible logo
cruxible★ 17
Governed state engine and typed knowledge graph for AI agents, declared in YAML.
VSCompare→
mnemo logo
mnemo★ 12
Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.
VSCompare→
infimium-agent logo
infimium-agent★ 25
Infimium helps agents find the right code, docs, and dependencies — before they edit. Local-first, open-source, MCP-compatible.
VSCompare→
okf-agent-memory logo
okf-agent-memory★ 827
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
VSCompare→
AgentRecall-X logo
AgentRecall-X★ 371
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
VSCompare→
remnic logo
remnic★ 228
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
VSCompare→
aictx logo
aictx★ 59
Repo-local continuity runtime for AI coding agents. Preserves work state, decisions, failures, validation evidence and repo context across sessions, helping agents behave less like cold-start rookies.
VSCompare→
See all alternatives →
jungjaehoon-lifegamez /
MAMA
↗

Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their evolution. SQLite + on-device embeddings, no cloud.

15MIT
Last commit5d ago
StatusActive
CategoryMemory & Context
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