One-line install via Claude Code:

hljs language-bash

Copy

/install-plugin github:soolaugust/0CompactMem

The problem: context compaction kills your flow

If you use Claude Code, you know this pain:

⚠️ Auto-compact: conversation is approaching context limit...

Every time this happens, your AI loses track of decisions, constraints, and hard-won context. You re-explain. It re-learns. Hours of accumulated understanding — gone in one compaction event.

And if you run multiple agents? They can't share what they've learned. Each one starts from zero.

This isn't a model limitation. It's a missing infrastructure layer.

The solution: persistent memory that survives compaction

0CompactMem gives your AI agents persistent, retrievable memory that lives outside the context window. When compaction happens, nothing is lost — because the important stuff was never only in the context window to begin with.

The result: zero effective compaction. Your AI retains every decision, constraint, and lesson across sessions, across compactions, across agents.

How it works

You speak
  → 0CompactMem retrieves relevant memories → injects into context
  → AI responds with full context
  → Session ends → decisions and insights auto-extracted → persisted
  → Compaction happens? No problem — memories survive outside the window
  → Next session starts → working set restored automatically

The whole pipeline runs inside Claude Code hooks. There is no manual memory management.

Why "0CompactMem"?

Zero compaction impact. Zero context loss. Zero re-explanation.

Under the hood: OS memory management for AI

The secret sauce? We didn't invent new algorithms. We borrowed what the Linux kernel has been doing for 40 years:

How is this different from mem0 / Letta / Zep?

TL;DR. If you're tired of context compaction wiping your AI's memory, and you want a solution that's pip install, runs as a sidecar on a laptop, shares between several Claude Code / Cursor / custom agents, and never loses a pinned constraint — 0CompactMem is built for that.

Performance at a glance

Quick start

One-line install (recommended).

/install-plugin github:soolaugust/0CompactMem

Manual install.

git clone https://github.com/soolaugust/0CompactMem
cd 0CompactMem
pip install -e .
mkdir -p ~/.claude/memory-os

Detailed Claude Code hook configuration, daemon management, and troubleshooting live in docs/SETUP.md.

Architecture

Three layers:

1. Hooks — sit at the Claude Code syscall boundary (SessionStart, UserPromptSubmit, Stop, PostToolUse) and call into the store.
2. Store — single SQLite file (WAL mode) with FTS5 full-text index, behind a unified VFS interface (store.py / store_vfs.py / store_criu.py).
3. Daemons & IPC — persistent retriever daemon (Unix socket), async extractor pool (kworker-style), cross-agent notify bus.

For the full layered diagram, on-disk schema, and the rationale behind each subsystem, see docs/ARCHITECTURE.md. For the comprehensive OS-and-cognitive-science primitive mapping, see docs/DESIGN_PHILOSOPHY.md.

Roadmap

• Distributed 0CompactMem — cgroup-style multi-agent quotas, network-replicated stores
• Adaptive watermarks — eviction tuning that follows observed agent behavior
• arXiv preprint — formal evaluation against mem0 / Letta / Zep
• Per-chunk embedding routing — different models for code vs prose

What landed already (1,051+ tuning iterations, eight major capability rounds) is summarized in CHANGELOG.md. Pain points it has resolved along the way are in docs/PROBLEMS_SOLVED.md.

Testing

# stable test subset
python3 -m pytest tests/test_agent_team.py tests/test_chaos.py -q

Coverage: per-session DB isolation, concurrent-write safety, cross-agent IPC delivery, extractor-pool queue semantics, CRIU checkpoint validation, goals-progress idempotency.

Dependencies

No GPU. No external API. Everything runs locally.

Paper

📄 Beyond Eviction: Full OS Memory Semantics for LLM Agent Persistence (PDF, 8 pages)

Technical paper describing the complete OS→agent-memory mapping: demand paging, kswapd, DAMON, mlock, CRIU, kworker, and shared memory.

Citation

@software{su2026compactmem,
  title = {0CompactMem: Full OS Memory Semantics for LLM Agent Persistence},
  author = {Su, Zhidao},
  year = {2026},
  url = {https://github.com/soolaugust/0CompactMem}
}

Contributing

Each subsystem hides behind a clean VFS interface, so components are testable in isolation. Issues, design proposals, and pull requests are welcome — see the Discussions tab for design questions, and please run the test subset above before submitting a PR.