MemWhale
Active·★ 147·MIT·Updated 2026-10-27
MemoryWhale is a local-first persistent debugging memory system for developers and coding agents. It records commands, output, failures, and fixes into a local SQLite database, allowing recovery of development history across sessions and tools without relying on hosted services.
#Debugging Tool#Persistent Memory#Local-first#Coding Agents#SQLite Database#CLI#Terminal Capture#Context Management
01
Features
01Persistent recording of development events: commands, environment, output, failures, and successful fixes.
02Unified local memory across different coding agents and stdio MCP clients.
03Local-first operation with no account, hosted service, or per-token memory costs.
04Interactive TUI browser and web dashboard for memory exploration.
05Generates compact context from past errors for agents and chat interfaces.
02
Compatibility
Linux
Runtime
Verified via docs
macOS
Runtime
Verified via docs
Windows
Runtime (via WSL)
Verified via docs
Rust
Build/Runtime
Verified via docs
stdio MCP
Agent Integration
Verified via docs
03
Quick start
1
$ curl -fsSL https://raw.githubusercontent.com/wuisabel-gif/MemWhale/main/install.sh | sh
04
Use cases
↳Debugging complex builds, dependencies, Git issues, environments, or deployments.
↳Maintaining context when using coding agents across multiple sessions or switching between tools.
↳Working over SSH or across multiple development machines while retaining history.
↳Ensuring recurring failures and their fixes remain searchable and discoverable.
↳Developers who prefer local storage solutions over hosted memory services.
05
Alternatives
Waggle-mcp★ 44
MCP server for external memory layer for AI agents + more . Download from pypi , and get started
remem★ 34
Local-first persistent memory for Claude Code & Codex CLI - Rust CLI, hooks, MCP server, SQLite/SQLCipher, auditable recall for long-running coding work.
deja-vu★ 1.3k
Your agents already solved this. deja finds it — retroactive search and MCP recall over the session logs your coding agents already wrote. Cross-agent, SSH-portable, one zero-dep binary, fully local.
okf-agent-memory★ 843
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.
projectmem★ 870
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.
engrim★ 300
The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, Codex CLI, and OpenCode. Zero cloud lock-in.
Comments
Log in to leave a comment
No comments yet. Be the first!