https://github.com/thedotmack/claude-mem

[windsheep@infosec.exchange]

GitHub - thedotmack/claude-mem: Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More - thedotmack/claude-mem

GitHub (github.com)

Claude-Mem seamlessly preserves context across sessions by automatically capturing tool usage observations, generating semantic summaries, and making them available to future sessions. This enables Claude to maintain continuity of knowledge about projects even after sessions end or reconnect.

#claude #memory #tokensavings

[windsheep@infosec.exchange]

I also tested lean-ctx and agentmemory.

GitHub - yvgude/lean-ctx: The Context OS for AI Development. Reduce token waste in Cursor, Claude Code, Copilot, Windsurf, Codex, Gemini & more by 60–95% (up to 99% on cached reads) Shell Hook + MCP Server · 49 tools · 10 read modes · 90+ patterns · Single Rust binary

The Context OS for AI Development. Reduce token waste in Cursor, Claude Code, Copilot, Windsurf, Codex, Gemini & more by 60–95% (up to 99% on cached reads) Shell Hook + MCP Server · 49 tools · 10 read modes · 90+ patterns · Single Rust binary - GitHub - yvgude/lean-ctx: The Context OS for AI Development. Reduce token waste in Cursor, Claude Code, Copilot, Windsurf, Codex, Gemini & more by 60–95% (up to 99% on cached reads) Shell Hook + MCP Server · 49 tools · 10 read modes · 90+ patterns · Single Rust binary

GitHub (github.com)

* not many savings; seems mostly tool calls and bash
* this is only useful in devcontainer settings because it reads all bash (incl. interactive outside claude or other tools)

GitHub - rohitg00/agentmemory: #1 Persistent memory for AI coding agents based on real-world benchmarks

#1 Persistent memory for AI coding agents based on real-world benchmarks - rohitg00/agentmemory

GitHub (github.com)

* new immature software (dies during use), Docker container is flaky
* good ideas though

Currently I run claude-mem + Caveman lite

GitHub - JuliusBrussee/caveman: 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman - JuliusBrussee/caveman

GitHub (github.com)

#leanctx #agentmemory #claude #caveman #tokensavings #devcontainer