openclaw-amem 1.2.2 → 1.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/README.md +9 -4
  2. package/dist/index.js +767 -100
  3. package/openclaw.plugin.json +63 -3
  4. package/package.json +5 -4
package/README.md CHANGED
@@ -1,18 +1,23 @@
1
1
  # openclaw-amem
2
2
 
3
3
  <p align="center">
4
- <img src="https://raw.githubusercontent.com/heichaowo/amem/main/docs/public/logo.webp" width="120" alt="A-MEM Logo" />
4
+ <img src="https://raw.githubusercontent.com/heichaowo/amem/main/docs/public/logo.webp" width="120" alt="amem logo" />
5
5
  </p>
6
6
 
7
7
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow?style=for-the-badge)](../../LICENSE)
8
8
  [![npm](https://img.shields.io/npm/v/openclaw-amem?style=for-the-badge&logo=npm&logoColor=white)](https://www.npmjs.com/package/openclaw-amem)
9
9
  [![arXiv](https://img.shields.io/badge/arXiv-2502.12110-b31b1b?style=for-the-badge)](https://arxiv.org/abs/2502.12110)
10
10
 
11
- **A-MEM agentic memory backend for [OpenClaw](https://github.com/openclaw/openclaw)** — memories **evolve**, not just accumulate.
11
+ **Memory for [OpenClaw](https://github.com/openclaw/openclaw) agents that catches its own contradictions.**
12
12
 
13
- The first open-source A-MEM memory plugin for OpenClaw: dynamic graph linking, hybrid (BM25 + dense) retrieval with 2-hop graph expansion, and LLM-driven memory evolution. Backed by Qdrant + local Transformers.js. **No Python required.**
13
+ A nightly pass re-reads what changed and flags memories that no longer agree with each other — the failure mode every long-lived memory store eventually has. The rest: facts extracted instead of transcripts stored, notes rewritten as new ones arrive, linked into a Zettelkasten-style graph, retrieved with hybrid BM25 + dense search over 2-hop expansion. Memories are scoped per agent (`owner`/`readers`/`writers`) and per subject, both enforced inside the Qdrant query rather than filtered after it.
14
+
15
+ Runs on a small model — `gpt-4o-mini`, `haiku`, a local Ollama. No Python.
16
+
17
+ 中文走 [jieba](https://github.com/messense/node-jieba) 分词，提示词有完整中文版（`AMEM_PROMPT_LOCALE=zh`），embedding 模型本身多语言。
18
+
19
+ Requires a local [Qdrant](https://qdrant.tech). Implements [A-MEM](https://arxiv.org/abs/2502.12110) (arXiv 2502.12110); the engine itself is [`@heichaowo/amem-core`](../amem-core).
14
20
 
15
- > 🧠 The memory **engine** lives in **[`amem-core`](../amem-core)**; this package is the thin OpenClaw plugin around it.
16
21
  > 📖 Full guides, architecture & references: **[amem.owo.lc](https://amem.owo.lc)**.
17
22
 
18
23
  ⭐ Useful? [Star it on GitHub](https://github.com/heichaowo/amem).