julianfleck

Collective Agent Memory — Development skill for Claude Code

Development community

Semantic search over Claude Code / OpenClaw session history.

How to install Collective Agent Memory

This entry records only its repository, not the path inside it, so there is no exact command to give. Open julianfleck/collective-agent-memory and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Collective Agent Memory does

Semantic search over Claude Code / OpenClaw session history.

Alternatives in Development

Mempalace Search — Search your memories across the MemPalace using semantic search with wing/room filtering 58.6k ★
Serena — Code Intelligence Advanced code navigation and semantic search 14k ★
Agentic Stack — One brain, many harnesses 2.2k ★

README

█▀▀ ▄▀█ █▀▄▀█            🇨🇴🇱🇱🇪🇨🇹🇮🇻🇪
█▄▄ █▀█ █░▀░█            🇦🇬🇪🇳🇹 🇲🇪🇲🇴🇷🇾

Collective Agent Memory

Shared, searchable agent memory across machines

CAM indexes sessions from Claude Code, Cursor, OpenClaw, and Codex CLI, segments them into searchable topics, and optionally syncs them across machines via GitHub. Your agents can search previous work, decisions, and code patterns from any session on any machine.

What It Does

Context recovery - Continue previous work with one command: cam context "topic"
Search past sessions - Find previous work with fast weighted keyword search
Entity search - Find sessions mentioning specific tools, files, concepts, or people
Filter by time - Get only recent results: last 2 hours, last day, last week
Filter by agent - Search only Claude, OpenClaw, or other specific agents
Shared memory - Sync sessions across machines so all agents can search everything
Topic segmentation - Sessions are automatically split into coherent topics with keywords
Entity extraction - Typed entities (tools, files, concepts, etc.) are extracted and indexed
Fast local search - SQLite FTS5, no embeddings needed, sub-second results

Install

curl -fsSL https://raw.githubusercontent.com/julianfleck/collective-agent-memory/main/install.sh | bash

The installer will:

Install CAM and its dependencies
Detect your host RAM and prompt for local or headed mode (see below)
Download ML models (~1.5GB) for embeddings and entity extraction (local mode only)
Detect your coding agents (Claude Code, Cursor, OpenClaw, Codex)
Index existing sessions into searchable session segments
Optionally set up GitHub sync for cross-machine access
Install the /cam skill to your agents

**Tip:** Set `HF_TOKEN` before installing for faster model downloads (see [Configuration](#configuration)). The installer + `cam init` writes t