cavemem
by JuliusBrussee (personal account)
Frozen — cross-agent persistent memory for coding assistants. Still works; the compressed-memory core now ships inside JuliusBrussee/caveman. (description from the project’s GitHub page)
Repository facts
- Stars
- 677
- Forks
- 59
- Open issues and pull requests
- 12
- Primary language
- TypeScript
- License
- MIT License (MIT)
- Owner
- JuliusBrussee · Personal account
- Created
- Apr 18, 2026
- Last push
- Aug 14, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 7,441: agentic-box/memora
Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.
742 starsPythonMITLast push Oct 18, 2026
Rank 32: JuliusBrussee/caveman
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
113,414 starsGoApache-2.0Last push Oct 18, 2026
Rank 7,853: JayPokale/Chisle
Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, publis…
684 starsJavaScriptMITLast push Oct 18, 2026
Rank 679: MemTensor/MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
11,920 starsTypeScriptApache-2.0Last push Oct 17, 2026
Rank 8,413: benmaster82/Kwipu
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples…
611 starsPythonMITLast push Sep 7, 2026
Rank 39: 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 sess…
101,568 starsTypeScriptApache-2.0Last push Oct 18, 2026