memo
Active·★ 24·MIT·Updated 2026-10-22
Memo provides a 100% local, persistent, and searchable memory solution for AI coding agents, eliminating amnesia across sessions. It uniquely offers token-efficient context management, historical querying, contradiction detection, and autonomous maintenance, saving costs and improving agent performance.
#AI Memory#Local-first#Coding Agent#Context Management#Token Efficiency#RAG#Developer Tool#Knowledge Base
01
Features
01100% local, persistent, and searchable memory for various AI coding agents (e.g., Claude Code, Cursor), requiring no cloud or external databases.
02Token-efficient context management designed to reduce overhead and save costs for AI interactions.
03Time-machine capability to query knowledge as it was at any historical point, aiding in understanding past decisions.
04Contradiction radar that detects and helps resolve conflicting facts within the knowledge corpus.
05Autonomous nightly maintenance pipeline to optimize memory, resolve conflicts, and pre-warm embeddings.
02
Compatibility
macOS (Apple Silicon)
Runtime
Verified via docs
Linux / Ubuntu
Runtime
Verified via docs
Docker
Deployment
Verified via docs
Python 3.13+
Language
Verified via docs
03
Quick start
1
$ curl -fsSL https://raw.githubusercontent.com/jagoff/memo/v4.9.0/install.sh | bash
04
Use cases
↳Providing continuous memory and context for AI coding agents across multiple sessions to prevent 'amnesia'.
↳Storing and retrieving important decisions, facts, or project-specific knowledge for AI agents.
↳Analyzing the evolution of project knowledge and understanding the rationale behind past decisions using historical queries.
↳Managing changing project requirements by detecting and resolving contradictions in stored knowledge.
↳Enhancing AI agent responses by injecting relevant, token-optimized memory before model answers.
05
Alternatives
remnic★ 228
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
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.
squish-memory★ 12
Local-first memory runtime for AI agents. One command to connect Claude Code, Codex, ChatGPT, MCP workflows, and local agents.
rms-memory-mcp★ 40
Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency
projectmem★ 868
Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
perseus-vault★ 72
Perseus Vault — persistent, deterministic memory for AI agents. They guess. We remember. SQLite + FTS5, AES-256-GCM, bi-temporal history, crypto-chained audit, 57 MCP tools. Local-first, single Rust binary. (formerly Mneme/Mimir)
Comments
Log in to leave a comment
No comments yet. Be the first!